CGNet: A Light-Weight Context Guided Network for Semantic Segmentation
Open accessThe DOI matches its Crossref record; 66 of the 84 references it cites were found in a registry or an index; 3 of the 23 sources its claims cite were checked for support.
Abstract
The demand of applying semantic segmentation model on mobile devices has been increasing rapidly. Current state-of-the-art networks have enormous amount of parameters hence unsuitable for mobile devices, while other small memory footprint models follow the spirit of classification network and ignore the inherent characteristic of semantic segmentation. To tackle this problem, we propose a novel Context Guided Network (CGNet), which is a light-weight and efficient network for semantic segmentation. We first propose the Context Guided (CG) block, which learns the joint feature of both local feature and surrounding context effectively and efficiently, and further improves the joint feature with the global context. Based on the CG block, we develop CGNet which captures contextual information in all stages of the network. CGNet is specially tailored to exploit the inherent property of semantic segmentation and increase the segmentation accuracy. Moreover, CGNet is elaborately designed to reduce the number of parameters and save memory footprint. Under an equivalent number of parameters, the proposed CGNet significantly outperforms existing light-weight segmentation networks. Extensive experiments on Cityscapes and CamVid datasets verify the effectiveness of the proposed approach. Specifically, without any post-processing and multi-scale testing, the proposed CGNet achieves 64.8% mean IoU on Cityscapes with less than 0.5 M parameters.
Overview
CoChat Summary
TL;DR
CGNet is a lightweight semantic segmentation network built from Context Guided (CG) blocks that combine local features, surrounding context, and global context in all stages. It achieves 64.8% mean IoU on Cityscapes test with less than 0.5 M parameters and no post-processing or multi-scale testing.
Key findings
- CGNet M3N21 reaches 64.8% mIoU on Cityscapes test with 0.5 M parameters, 6.0 GFLOPs, 334.0 M memory, and 56.8 ms running time at 2048×1024 input.
- On CamVid test, CGNet M3N21 reaches 65.6% mIoU with 0.5 M parameters, 14.3% higher than ENet (51.3%) and 1.9% lower than FCN (Res101) (67.5%) while using 110× fewer parameters.
- Ablations on Cityscapes validation: full surrounding context extractor improves mIoU from 54.6% to 59.7%; global context extractor from 58.9% to 59.7%; input injection from 59.4% to 59.7%; PReLU over ReLU from 58.1% to 59.7%; GRL over LRL from 57.2% to 63.5%; removing 1×1 convolution improves from 53.3% to 63.5%.
- CGNet M3N21 is 131× and 57× smaller than PSPNet and DenseASPP, with category-wise accuracy only 5.4% and 5.5% lower, and memory 10× less than DenseASPP (334.0 M vs. 3997.5 M).
Methods
- The CG block contains a local feature extractor (3×3 standard convolution), surrounding context extractor (3×3 atrous/dilated convolution), joint feature extractor (concatenation + BN + PReLU), and global context extractor (global average pooling + multilayer perceptron + scale layer), with local or global residual learning.
- CGNet uses 51 convolutional layers, three downsampling stages with channels 32, 64, and 128, CG blocks in stages 2 and 3, input injection, and a final 1×1 convolution; Cityscapes configuration uses M=3 and N=21.
- Experiments use Cityscapes (2,975 train / 500 val / 1,525 test images, 19 classes) and CamVid (367 train / 101 val / 233 test images, 11 classes), trained in PyTorch on 2× V100 GPUs with ADAM, poly learning rate, batch size 14, 60K iterations, and single-scale mean IoU evaluation.
Limitations
- The paper does not state a limitations section.
- Evident from the text: evaluation is limited to Cityscapes and CamVid, both road-scene datasets, so generalization to other domains is not demonstrated.
- Evident from the text: ablation studies and architecture choices (M=3, N=21) are tuned on the Cityscapes validation set, and comparisons include some methods using multi-scale testing while CGNet uses no testing tricks.
Model-written summary. Check it against the paper before relying on it.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
3 Valid · 0 Not valid · 10 Not checked · 43 Own results and interpretations
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“the accuracy of our approach is 4.5% higher than the very recent model ESPNet [22]”
What the sources say
- Partly supportedcites [22] [22] S. Mehta, M. Rastegari, A. Caspi, L. Shapiro, and H. Hajishirzi. Espnet: Efficient spatial pyramid of dilated convolutions for semantic segmentation. arXiv preprint arXiv:1803.06815 , 2018. - sourceExperimental — accuracy not yet measured
Our copy confirms the comparator itself: ESPNet is the recent efficient semantic-segmentation network, and its accuracy is reported (Sec. 4.2, p. 11: 'ESPNet is 2% more accurate than ENet', '8% lower category-wise mIOU than PSPNet'; Table 1, p. 12: 0.364M parameters, mIOU 63.01; Table 4, p. 27 category-wise values). So the citation correctly identifies the baseline model and its accuracy on Cityscapes. However, no passage in our copy states a 4.5-point difference against CGNet — CGNet/CGNet M3N21 is not mentioned anywhere in the paper, and our copy reports ESPNet's accuracy as mIOU/category-wise values rather than the single 'accuracy' figure the citing sentence subtracts from. The 4.5% magnitude therefore rests on the citing authors' own comparison, not on this source. (LLM, conf=0.70)
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Partly supported
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“However, this design is not suitable for the proposed CG block, since the local feature and the surrounding context in CG block need to maintain channel independence. Additional experiments also verify this observation.”
What the sources say
- Partly supportedcites [14] [14] A. G. Howard, M. Zhu, B. Chen, D. Kalenichenko, W. Wang, T. Weyand, M. Andreetto, and H. Adam. Mobilenets: Efficient convolutional neural networks for mobile vision applications. arXiv preprint arXiv:1704.04861 , 2017. - sourceExperimental — accuracy not yet measured
Our copy of MobileNets does describe a separable design pairing channel-wise (depthwise) convolution with a 1×1 convolution, but in the opposite order to the one the claim attributes to it: Section 3.1 (p. 3) states 'We use depthwise convolutions to apply a single filter per each input channel... Pointwise convolution, a simple 1×1 convolution, is then used to create a linear combination of the output of the depthwise layer', and Section 3.1 (p. 2) and Table 1 (p. 4) consistently order the layers depthwise-then-1×1. The rationale the claim rests on — that local feature and surrounding context must maintain channel independence, and hence that this design is unsuitable — is not in our copy either: MobileNets says only that depthwise convolution 'only filters input channels, it does not combine them', motivating the pointwise layer rather than warning against the arrangement, and the paper never discusses context-gathering/CG blocks. So the identification of the source's design is partly right (same two layer types) but mis-stated in order, and the unsuitability/channel-independence conclusion is the citing authors' own, not supported here. (LLM, conf=0.70)
plainstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Partly supported
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Under an equivalent number of parameters, the proposed CGNet significantly outperforms existing segmentation networks.”
- Also stated in: § 1. Introduction · p. 2 · plain
“Under an equivalent number of parameters, the proposed CGNet significantly outperforms existing segmentation networks (e.g., ENet and ESPNet).”
plainstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Also stated in: § 1. Introduction · p. 2 · plain
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“We try the 1 × 1 convolution in CG block but find it damage the segmentation accuracy.”
- Also stated in: § 4.2. Ablation Studies · p. 7 · plain
“we can improve the accuracy from 53 . 3% to 63 . 5% by removing the 1 × 1 convolutions.”
plainstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Also stated in: § 4.2. Ablation Studies · p. 7 · plain
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“our CGNet M3N21 achieves 64 . 8% in terms of mean IoU (only training on fine annotated images).”
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
26 more claims
Create a free account to see all 56 claims and to verify the 18 references still open.
- It may state two separate claims as one. 18
- The quote only partly states this claim. 6
- Probably not a substantial claim. 6
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“For vehicle detection, the Context-Guided (CG) module is introduced during the downsampling process to enhance feature extraction capabilities in complex scenarios.”
From Multi-Object Vehicle Detection and Tracking Algorithm Based on Improved YOLOv8 and ByteTrack (2024) · cites this paper as [14]
Experimental — accuracy not yet measured
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
Each contradiction between two passages listed here was confirmed by an independent check.
Rated minor: it would not touch a result — a value no result rests on, a p-value that stays on the same side of the significance level, or a conflict that is clerical, resolved elsewhere in the paper, or outside its own findings.
In the paper
§ 1. Introduction · p. 1
“e.g . ESPNet [22], ENet [35] and FCN [29]”
§ 2. Related Work · p. 2
“ENet [24] proposes to discard the last stage of the model”
Rated minor: it would not touch a result — a value no result rests on, a p-value that stays on the same side of the significance level, or a conflict that is clerical, resolved elsewhere in the paper, or outside its own findings.
In the paper
§ 2. Related Work · p. 2
“More recent ESPNet [23] introduces a fast and efficient convolutional network”
§ 4.2. Ablation Studies · p. 7
“ESPNet [22] | '18 | 4.0 | 0.4 | - | 60.3 | -”
Citations
Cites
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.90 · Cited by 235,474
Adam: A Method for Stochastic Optimization
Kingma, D. P., & Ba, J. (2014) · arXiv · doi:10.48550/arxiv.1412.6980 · Cited by 98,946
Densely Connected Convolutional Networks
Huang, G., Liu, Z., Van Der Maaten, L., & Weinberger, K. Q. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.243 · Cited by 48,566
Going deeper with convolutions
Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., Erhan, D., Vanhoucke, V., & Rabinovich, A. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298594 · Cited by 48,562
Fully convolutional networks for semantic segmentation
Long, J., Shelhamer, E., & Darrell, T. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298965 · Cited by 38,834
Squeeze-and-Excitation Networks
Hu, J., Shen, L., & Sun, G. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00745 · Cited by 35,667
MobileNetV2: Inverted Residuals and Linear Bottlenecks
Sandler, M., Howard, A., Zhu, M., Zhmoginov, A., & Chen, L.-C. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00474 · Cited by 28,755
Chen, L.-C., Papandreou, G., Kokkinos, I., Murphy, K., & Yuille, A. L. (2018) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2017.2699184 · Cited by 22,392
Chen, L.-C., Papandreou, G., Kokkinos, I., Murphy, K., & Yuille, A. L. (2016) · arXiv · doi:10.48550/arxiv.1606.00915 · Cited by 22,392
Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation
Chen, L.-C., Zhu, Y., Papandreou, G., Schroff, F., & Adam, H. (2018) · arXiv · doi:10.48550/arxiv.1802.02611 · Cited by 20,063 · cited 1×
“DFN [32] of 44.8 M, DeepLabv3+ [9] of 54.6 M and DenseASPP [30] of 28.6 M.”
BackgroundInfluential
Research works printed but not linked: 1
- liu, 2017, Learning affinity via spatial propagation networks, Proc Adv Neural Inf Process Syst, 1520
Cited by
SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers
Xie, E., Wang, W., Yu, Z., Anandkumar, A., Alvarez, J. M., & Luo, P. (2021) · arXiv · doi:10.48550/arxiv.2105.15203 · Cited by 5,090
CMX: Cross-Modal Fusion for RGB-X Semantic Segmentation With Transformers
Zhang, J., Liu, H., Yang, K., Hu, X., Liu, R., & Stiefelhagen, R. (2023) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2023.3300537 · Cited by 731
“We compare our models against RGB-only methods covering CNN-based [100], [117], [118], [120] and transformerbased [24], [46], [119] methods.”
MethodAn effective CNN and Transformer complementary network for medical image segmentation
Yuan, F., Zhang, Z., & Fang, Z. (2023) · Pattern Recognition · doi:10.1016/j.patcog.2022.109228 · Cited by 539
Pixel Difference Networks for Efficient Edge Detection
Su, Z., Liu, W., Yu, Z., Hu, D., Liao, Q., Tian, Q., Pietikainen, M., & Liu, L. (2021) · 2021 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.00507 · Cited by 500
A review on deep learning in UAV remote sensing
Osco, L. P., Marcato Junior, J., Marques Ramos, A. P., de Castro Jorge, L. A., Fatholahi, S. N., de Andrade Silva, J., Matsubara, E. T., Pistori, H., Gonçalves, W. N., & Li, J. (2021) · International Journal of Applied Earth Observation and Geoinformation · doi:10.1016/j.jag.2021.102456 · Cited by 458
Lednet: A Lightweight Encoder-Decoder Network for Real-Time Semantic Segmentation
Wang, Y., Zhou, Q., Liu, J., Xiong, J., Gao, G., Wu, X., & Latecki, L. J. (2019) · 2019 IEEE International Conference on Image Processing (ICIP) · doi:10.1109/icip.2019.8803154 · Cited by 411
GMNet: Graded-Feature Multilabel-Learning Network for RGB-Thermal Urban Scene Semantic Segmentation
Zhou, W., Liu, J., Lei, J., Yu, L., & Hwang, J.-N. (2021) · IEEE Transactions on Image Processing · doi:10.1109/tip.2021.3109518 · Cited by 344
nnFormer: Interleaved Transformer for Volumetric Segmentation
Zhou, H.-Y., Guo, J., Zhang, Y., Yu, L., Wang, L., & Yu, Y. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2109.03201 · Cited by 256
Self-citationLeViT-UNet: Make Faster Encoders with Transformer for Medical Image Segmentation
Xu, G., Zhang, X., He, X., & Wu, X. (2024) · Lecture Notes in Computer Science · doi:10.1007/978-981-99-8543-2_4 · Cited by 228
Lightweight Real-Time Semantic Segmentation Network With Efficient Transformer and CNN
Xu, G., Li, J., Gao, G., Lu, H., Yang, J., & Yue, D. (2023) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2023.3248089 · Cited by 185
GA-Nav: Efficient Terrain Segmentation for Robot Navigation in Unstructured Outdoor Environments
Guan, T., Kothandaraman, D., Chandra, R., Sathyamoorthy, A. J., Weerakoon, K., & Manocha, D. (2022) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2022.3187278 · Cited by 222
FBSNet: A Fast Bilateral Symmetrical Network for Real-Time Semantic Segmentation
Gao, G., Xu, G., Li, J., Yu, Y., Lu, H., & Yang, J. J. (2022) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2022.3157995 · Cited by 169
MSCFNet: A Lightweight Network With Multi-Scale Context Fusion for Real-Time Semantic Segmentation
Gao, G., Xu, G., Yu, Y., Xie, J., Yang, J. J., & Yue, D. (2021) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2021.3098355 · Cited by 157
Night-Time Scene Parsing With a Large Real Dataset
Tan, X., Xu, K., Cao, Y., Zhang, Y., Ma, L., & Lau, R. W. H. (2021) · IEEE Transactions on Image Processing · doi:10.1109/tip.2021.3122004 · Cited by 173
Self-citationShen, K., Zhou, X., & Liu, Z. (2024) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2024.3366221 · Cited by 153
Shim, S., Kim, J., Lee, S.-W., & Cho, G.-C. (2022) · Automation in Construction · doi:10.1016/j.autcon.2022.104139 · Cited by 127
Song, W., Wang, X., Guo, Y., Li, S., Xia, B., & Hao, A. (2024) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2024.3428349 · Cited by 136
MLFNet: Multi-Level Fusion Network for Real-Time Semantic Segmentation of Autonomous Driving
Fan, J., Wang, F., Chu, H., Hu, X., Cheng, Y., & Gao, B. (2022) · IEEE Transactions on Intelligent Vehicles · doi:10.1109/tiv.2022.3176860 · Cited by 132
PASS: Panoramic Annular Semantic Segmentation
Yang, K., Hu, X., Bergasa, L. M., Romera, E., & Wang, K. (2019) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2019.2938965 · Cited by 122
LMFFNet: A Well-Balanced Lightweight Network for Fast and Accurate Semantic Segmentation
Shi, M., Shen, J.-L., Yi, Q., Weng, J., Huang, Z., Luo, A., & Zhou, Y. (2022) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2022.3176493 · Cited by 123
A Highly Efficient Model to Study the Semantics of Salient Object Detection
Cheng, M., Gao, S., Borji, A., Tan, Y., Zheng, L. L., & Wang, M. (2021) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2021.3107956 · Cited by 122
Shi, M., Lin, S., Yi, Q., Weng, J., Luo, A., & Zhou, Y. (2024) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2023.3348631 · Cited by 109
Zhang, J., Yang, K., Constantinescu, A., Peng, K., Müller, K., & Stiefelhagen, R. (2022) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2022.3161141 · Cited by 109
Asymptotic Feature Pyramid Network for Labeling Pixels and Regions
Yang, G., Lei, J., Tian, H., Feng, Z., & Liang, R. (2024) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2024.3376773 · Cited by 114
Hierarchical Pyramid Diverse Attention Networks for Face Recognition
Wang, Q., Wu, T., Zheng, H., & Guo, G. (2020) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr42600.2020.00835 · Cited by 112
Self-citationContext and Spatial Feature Calibration for Real-Time Semantic Segmentation
Li, K., Geng, Q., Wan, M., Cao, X., & Zhou, Z. (2023) · IEEE Transactions on Image Processing · doi:10.1109/tip.2023.3318967 · Cited by 97
Ma, W., Zhang, Y., Ma, L., Liu, R., & Yan, S. (2023) · Expert Systems with Applications · doi:10.1016/j.eswa.2023.120084 · Cited by 86
Self-citationChen, B., Xia, M., Qian, M., & Huang, J. (2022) · International Journal of Remote Sensing · doi:10.1080/01431161.2022.2073795 · Cited by 91
PolypSeg +: A Lightweight Context-Aware Network for Real-Time Polyp Segmentation
Wu, H., Zhao, Z., Zhong, J., Wang, W., Wen, Z., & Qin, J. (2022) · IEEE Transactions on Cybernetics · doi:10.1109/tcyb.2022.3162873 · Cited by 94
A Detection Method With Antiinterference for Infrared Maritime Small Target
Zhang, X., Wang, A., Zheng, Y., Mazhar, S., & Chang, Y. (2024) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2024.3357496 · Cited by 84
LeaNet: Lightweight U-shaped architecture for high-performance skin cancer image segmentation
Hu, B., Zhou, P., Yu, H., Dai, Y., Wang, M., Tan, S., & Sun, Y. (2024) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2024.107919 · Cited by 88
Vehicle Detection for Autonomous Driving: A Review of Algorithms and Datasets
Karangwa, J., Liu, J., & Zeng, Z. (2023) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2023.3292278 · Cited by 102
Boundary-Guided Lightweight Semantic Segmentation With Multi-Scale Semantic Context
Zhou, Q., Wang, L., Gao, G., Kang, B., Ou, W., & Lu, H. (2024) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2024.3372835 · Cited by 94
Capturing Omni-Range Context for Omnidirectional Segmentation
Yang, K., Zhang, J., Reiß, S., Hu, X., & Stiefelhagen, R. (2021) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr46437.2021.00143 · Cited by 102
A survey on semantic communications: Technologies, solutions, applications and challenges
Liu, Y., Wang, X., Ning, Z., Zhou, M., Guo, L., & Jedari, B. (2023) · Digital Communications and Networks · doi:10.1016/j.dcan.2023.05.010 · Cited by 122
Tian, Y., Zhao, Y., Son, S., Luo, J., Oh, S., & Wang, Y. (2023) · Journal of Geophysical Research Atmospheres · doi:10.1029/2022jd037041 · Cited by 82
FsaNet: Frequency Self-Attention for Semantic Segmentation
Zhang, F., Panahi, A., & Gao, G. (2023) · IEEE Transactions on Image Processing · doi:10.1109/tip.2023.3305090 · Cited by 93
Small Object Augmentation of Urban Scenes for Real-Time Semantic Segmentation
Yang, Z., Yu, H., Feng, M., Sun, W. J., Lin, X., Sun, M., Mao, Z., & Mian, A. S. (2020) · IEEE Transactions on Image Processing · doi:10.1109/tip.2020.2976856 · Cited by 85
Visual fire detection using deep learning: A survey
Cheng, G., Chen, X., Wang, C., Li, X., Xian, B., & Yu, H. (2024) · Neurocomputing · doi:10.1016/j.neucom.2024.127975 · Cited by 96
Dual-Branch Network for Cloud and Cloud Shadow Segmentation
Chen, L., Xia, M., Qian, M., & Chen, B. (2022) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2022.3175613 · Cited by 77
Unseen Object Amodal Instance Segmentation via Hierarchical Occlusion Modeling
Back, S., Lee, J., Kim, T., Noh, S., Kang, R., Bak, S., & Lee, K. (2022) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra46639.2022.9811646 · Cited by 99
Li, Q., Yang, W., Liu, W., Yu, Y., & He, S. (2021) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.00716 · Cited by 83
FDDWNet: A Lightweight Convolutional Neural Network for Real-Time Semantic Segmentation
Liu, J., Zhou, Q., Qiang, Y., Kang, B., Wu, X., & Zheng, B. (2020) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp40776.2020.9053838 · Cited by 88
Joint pyramid attention network for real-time semantic segmentation of urban scenes
Hu, X., Jing, L., & Sehar, U. (2021) · Applied Intelligence · doi:10.1007/s10489-021-02446-8 · Cited by 64
Li, J., Zi, S., Song, R., Li, Y., Hu, Y., & Du, Q. (2022) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2022.3152587 · Cited by 64
Shim, S., Kim, J., Lee, S.-W., & Cho, G.-C. (2021) · Automation in Construction · doi:10.1016/j.autcon.2021.103833 · Cited by 69
Guo, B., Wang, Y., Zhen, S., Yu, R., & Su, Z. (2023) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2022.3233674 · Cited by 67
Pale Transformer: A General Vision Transformer Backbone with Pale-Shaped Attention
Wu, S., Wu, T., Tan, H., & Guo, G. (2022) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v36i3.20176 · Cited by 110
Self-citationZhu, M., Fan, J., Yang, Q., & Chen, T. (2021) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2021.3131152 · Cited by 61
LAANet: lightweight attention-guided asymmetric network for real-time semantic segmentation
Zhang, X., Du, B., Wu, Z., & Wan, T. (2022) · Neural Computing and Applications · doi:10.1007/s00521-022-06932-z · Cited by 60
Is Context-Aware CNN Ready for the Surroundings? Panoramic Semantic Segmentation in the Wild
Yang, K., Hu, X., & Stiefelhagen, R. (2021) · IEEE Transactions on Image Processing · doi:10.1109/tip.2020.3048682 · Cited by 66
Shim, S. (2023) · Computer-Aided Civil and Infrastructure Engineering · doi:10.1111/mice.13119 · Cited by 66
Jiang, W., Xie, Z., Li, Y., Liu, C., & Lu, H. (2020) · IEEE International Conference on Multimedia & Expo Workshops (ICMEW) · doi:10.1109/icmew46912.2020.9106038 · Cited by 66
MiniNet: An Efficient Semantic Segmentation ConvNet for Real-Time Robotic Applications
Alonso, Í., Riazuelo, L., & Murillo, A. C. (2020) · IEEE Transactions on Robotics · doi:10.1109/tro.2020.2974099 · Cited by 69
LightCDNet: Lightweight Change Detection Network Based on VHR Images
Xing, Y., Jiang, J., Xiang, J., et al. (2023) · IEEE Geoscience and Remote Sensing Letters · doi:10.1109/lgrs.2023.3304309 · Cited by 56
Xu, C. X., Li, Q., Jiang, X., Yu, D., & Zhou, Y. (2022) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2022.3216313 · Cited by 62
Landslide extraction from aerial imagery considering context association characteristics
Xie, Y., Zhan, N., Zhu, J., Xu, B., Chen, H., Mao, W., Luo, X., & Hu, Y. (2024) · International Journal of Applied Earth Observation and Geoinformation · doi:10.1016/j.jag.2024.103950 · Cited by 104
Cloud/shadow segmentation based on multi-level feature enhanced network for remote sensing imagery
Miao, S., Xia, M., Qian, M., Zhang, Y., Liu, J., & Lin, H. (2022) · International Journal of Remote Sensing · doi:10.1080/01431161.2021.2014077 · Cited by 57
Self-citationLeViT-UNet: Make Faster Encoders with Transformer for Medical Image SegmentationPreprint
Xu, G., Wu, X., Zhang, X., et al. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2107.08623 · Cited by 55
Liu, J., Xu, X., Shi, Y., Deng, C. D., & Shi, M. (2021) · Neurocomputing · doi:10.1016/j.neucom.2021.12.003 · Cited by 59
Yang, K., Hu, X., Chen, H., Xiang, K., Wang, K., & Stiefelhagen, R. (2020) · IEEE Intelligent Vehicles Symposium · doi:10.1109/iv47402.2020.9304706 · Cited by 55
MLMSeg: A multi-view learning model for ultrasound thyroid nodule segmentation
Chen, G., Tan, G., Duan, M., Pu, B., Luo, H., Li, S., & Li, K. (2023) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2023.107898 · Cited by 57
TerraPN: Unstructured Terrain Navigation using Online Self-Supervised Learning
Sathyamoorthy, A. J., Weerakoon, K., Guan, T., Liang, J., & Manocha, D. (2022) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros47612.2022.9981942 · Cited by 88
Li, G., Jiang, S., Yun, I., Kim, J., & Kim, J. (2020) · IEEE Access · doi:10.1109/access.2020.2971760 · Cited by 53
Lightweight and efficient asymmetric network design for real-time semantic segmentation
Zhang, X., Du, B., Luo, Z.-C., & Ma, K. (2021) · Applied Intelligence · doi:10.1007/s10489-021-02437-9 · Cited by 50
Rose-Mamba-YOLO: an enhanced framework for efficient and accurate greenhouse rose monitoring
You, S., Li, B., Chen, Y., Ren, Z., Liu, Y., Wu, Q., Tao, J., Zhang, Z., Zhang, C., Xue, F., et al. (2025) · Frontiers in Plant Science · doi:10.3389/fpls.2025.1607582 · Cited by 65
Xiao, R., Xu, Y., Xu, F., Zhen, H., Zhang, H., & Chen, S. (2023) · IEEE Transactions on Industrial Electronics · doi:10.1109/tie.2023.3243265 · Cited by 50
MFNet: Multi-Feature Fusion Network for Real-Time Semantic Segmentation in Road Scenes
Lu, M., Chen, Z., Liu, C., Ma, S., Cai, L., & Qin, H. (2022) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2022.3182311 · Cited by 51
Sehar, U., & Naseem, M. L. (2022) · Multimedia Tools and Applications · doi:10.1007/s11042-022-12821-3 · Cited by 60
Qiu, Y., Liu, Y., Li, S., & Xu, J. (2022) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2022.3230821 · Cited by 56
Parallel Complement Network for Real-Time Semantic Segmentation of Road Scenes
Lv, Q., Sun, X., Chen, C., Dong, J., & Zhou, H. (2021) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2020.3044672 · Cited by 50
ARTHuS: Adaptive Real-Time Human Segmentation in Sports Through Online Distillation
Cioppa, A., Deliège, A., Istasse, M., Vleeschouwer, C. D., & Droogenbroeck, M. V. (2019) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw.2019.00306 · Cited by 55
A lightweight network for smoke semantic segmentation
Yuan, F., Li, K., Wang, C., & Fang, Z. (2023) · Pattern Recognition · doi:10.1016/j.patcog.2022.109289 · Cited by 49
Feature pyramid network with multi-scale prediction fusion for real-time semantic segmentation
Quyen, T. V., & Kim, M. Y. (2022) · Neurocomputing · doi:10.1016/j.neucom.2022.11.062 · Cited by 47
Gao, Z., Yang, G., Li, E., Liang, Z., & Guo, R. (2021) · IEEE Sensors Journal · doi:10.1109/jsen.2021.3062660 · Cited by 45
Singh, V. K., Abdel‐Nasser, M., Pandey, N., & Puig, D. (2021) · Diagnostics · doi:10.3390/diagnostics11020158 · Cited by 52
Lightweight deep learning methods for panoramic dental X-ray image segmentation
Lin, S., Hao, X., Liu, Y., Dong, Y., Liu, J.-W., & Zhong, M. (2022) · Neural Computing and Applications · doi:10.1007/s00521-022-08102-7 · Cited by 56
Mask-guided modality difference reduction network for RGB-T semantic segmentation
Liang, W., Yang, Y., Li, F., Long, X., & Shan, C. (2022) · Neurocomputing · doi:10.1016/j.neucom.2022.12.036 · Cited by 49
A Comprehensive Review of Modern Object Segmentation Approaches
Wang, Y., Ahsan, U., Li, H., & Hagen, M. (2022) · Foundations and Trends® in Computer Graphics and Vision · doi:10.1561/0600000097 · Cited by 65
EACNet: Enhanced Asymmetric Convolution for Real-Time Semantic Segmentation
Li, Y., Li, X., Xiao, C., Li, H., & Zhang, W. (2021) · IEEE Signal Processing Letters · doi:10.1109/lsp.2021.3051845 · Cited by 46
Deep Multi-Branch Aggregation Network for Real-Time Semantic Segmentation in Street Scenes
Weng, X., Yan, Y., Dong, G., Shu, C., Wang, B., Wang, H., & Zhang, J. (2022) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2022.3150350 · Cited by 44
Attention Guided Global Enhancement and Local Refinement Network for Semantic Segmentation
Li, J., Zha, S., Chen, C., Ding, M., Zhang, T., & Yu, H. (2022) · IEEE Transactions on Image Processing · doi:10.1109/tip.2022.3166673 · Cited by 48
Global contextually guided lightweight network for RGB-thermal urban scene understanding
Gong, T., Zhou, W., Qian, X., Lei, J., & Yu, L. (2022) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2022.105510 · Cited by 48
Zhuang, M., Zhong, X., Gu, D., Feng, L., Zhong, X., & Hu, H. (2021) · Neurocomputing · doi:10.1016/j.neucom.2021.07.019 · Cited by 45
Multi-Object Vehicle Detection and Tracking Algorithm Based on Improved YOLOv8 and ByteTrack
You, L., Chen, Y., Xiao, C., Sun, C., & Li, R. (2024) · Electronics · doi:10.3390/electronics13153033 · Cited by 42
Golden Cudgel Network for Real-Time Semantic Segmentation
Yang, G., Wang, Y., Shi, D., & Wang, Y. (2025) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52734.2025.02362 · Cited by 85
Context Attention Fusion Network for crowd counting
Wang, T., Zhang, T., Zhang, T., et al. (2023) · Knowledge-Based Systems · doi:10.1016/j.knosys.2023.110541 · Cited by 41
Multi-stage context refinement network for semantic segmentation
Liu, Q., Dong, Y., & Li, X. (2023) · Neurocomputing · doi:10.1016/j.neucom.2023.03.006 · Cited by 42
Jaus, A., Yang, K., & Stiefelhagen, R. (2021) · IEEE Intelligent Vehicles Symposium · doi:10.1109/iv48863.2021.9575904 · Cited by 41
Cai, Y., Dai, L., Wang, H., & Li, Z. (2021) · IEEE Transactions on Image Processing · doi:10.1109/tip.2021.3122293 · Cited by 46
Zhao, D., Zhou, H., Chen, P., Hu, Y., Ge, W., Dang, Y., & Liang, R. (2023) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2023.3341127 · Cited by 48
CoralSCOP: Segment any COral Image on this Planet
Zheng, Z., Liang, H., Hua, B., Wong, Y. H., Ang, P., Chui, A. P. Y., & Yeung, S.-K. (2024) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52733.2024.02661 · Cited by 75
Zhang, X., Li, Q., Li, W., Guo, Y., Zhang, J., Guo, C.-B., Chang, K., & Lovell, N. H. (2024) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2024.3350245 · Cited by 44
HAFormer: Unleashing the Power of Hierarchy-Aware Features for Lightweight Semantic Segmentation
Xu, G., Jia, W., Wu, T., Chen, L., & Gao, G. (2024) · IEEE Transactions on Image Processing · doi:10.1109/tip.2024.3425048 · Cited by 51
Self-citationLCDNet: Light-Weighted Cloud Detection Network for High-Resolution Remote Sensing Images
Hu, K., Zhang, D., Xia, M., Qian, M., & Chen, B. (2022) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2022.3181303 · Cited by 42
Chang, Y., & Wang, W. (2021) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2021.3124053 · Cited by 39
Real-time defect detection in underground sewage pipelines using an improved YOLOv5 model
Lu, J., Song, W., Zhang, Y., Yin, X., & Zhao, S. (2025) · Automation in Construction · doi:10.1016/j.autcon.2025.106068 · Cited by 42
Self-citationCross-supervised contrastive learning domain adaptation network for steel defect segmentation
Zhao, L., Zhang, Y., Duan, J., & Yu, J. (2024) · Advanced Engineering Informatics · doi:10.1016/j.aei.2024.102964 · Cited by 44
Self-citationLiu, X., Wang, J., & Li, J. (2023) · Control Engineering Practice · doi:10.1016/j.conengprac.2023.105560 · Cited by 41
Bilateral U‐Net semantic segmentation with spatial attention mechanism
Zhao, G., Zhang, Y., Ge, M., & Yu, M. (2022) · CAAI Transactions on Intelligence Technology · doi:10.1049/cit2.12118 · Cited by 38
Self-citation
Metadata
- Authors
- Wu, T., Tang, S., Zhang, R., Cao, J., & Zhang, Y.
- Affiliations
- Chinese Academy of Sciences (CN)
- Venue
- IEEE Transactions on Image Processing
- Published
- 2021
- Volume
- 30
- Pages
- 1169-1179
- ISSN
- 1057-7149 (ISSN-L)
- 1941-0042
- OpenAlex
- W3112503277
- Cited by
- 859
- References
- 84
- Citations by year
- 2026: 145 · 2025: 222 · 2024: 172 · 2023: 129 · 2022: 97 · 2021: 59
- FWCI
- 30.23
- Type
- journal article
- Language
- en
- Open access
- green
- arxiv.org
- Licence
- Locations
- IEEE Transactions on Image Processing (publishedVersion)
- PubMed (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- arXiv (Cornell University)
- Funders
- National Key Research and Development Program of China (2017YFC0820605)
- National Natural Science Foundation of China (61525206, U1703261, 61871004)
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
- Physical Sciences › Computer Science › Artificial Intelligence › Domain Adaptation and Few-Shot Learning
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Medical Image Segmentation Techniques
- Keywords
- semantic segmentation, global context, local features, memory footprint reduction, parameter reduction, mobile devices, cityscape, CamVid
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
The claim verdicts this report counts are experimental: their accuracy is not yet measured.
A language model drew the claims from the paper on 2026-10-04, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).
A second model labelled each claim on 2026-10-04 (model jev-1.13-20260917, definition revision gold-guideline-v0.2).
Cited sources are checked with a language model’s help (qwen3.8-omni-flash).
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.