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
Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation
Chen, L.-C., Zhu, Y., Papandreou, G., Schroff, F., & Adam, H. (2018) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-01234-2_49 · Cited by 20,054
SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation
Badrinarayanan, V., Kendall, A., & Cipolla, R. (2017) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2016.2644615 · Cited by 19,631
MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications
Howard, A. G., Zhu, M., Chen, B., Kalenichenko, D., Wang, W., Weyand, T., Andreetto, M., & Adam, H. (2017) · arXiv · doi:10.48550/arxiv.1704.04861 · Cited by 19,015
Zhao, H., Shi, J., Qi, X., Wang, X., & Jia, J. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.660 · Cited by 16,438
Neural Machine Translation by Jointly Learning to Align and Translate
Bahdanau, D., Cho, K., & Bengio, Y. (2014) · arXiv · doi:10.48550/arxiv.1409.0473 · Cited by 16,213
The Cityscapes Dataset for Semantic Urban Scene Understanding
Cordts, M., Omran, M., Ramos, S., Rehfeld, T., Enzweiler, M., Benenson, R., Franke, U., Roth, S., & Schiele, B. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.350 · Cited by 12,433 · cited 4×
“Accuracy vs. the number of parameters on Cityscapes [10] 2 .”
BackgroundMethodInfluentialSqueeze-and-Excitation Networks
Hu, J., Shen, L., Albanie, S., Sun, G., & Wu, E. (2020) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2019.2913372 · Cited by 12,157
Wang, X., Girshick, R., Gupta, A., & He, K. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00813 · Cited by 11,596 · cited 1×
“More recently, NL [29] proposes to compute the response at a position as a weighted sum of the features at all positions for video classification.”
MethodAzuma, R. T. (1997) · Presence: Teleoperators and Virtual Environments · doi:10.1162/pres.1997.6.4.355 · Cited by 10,121
Multi-scale context aggregation by dilated convolutions
Yu, F., & Koltun, V. (2015) · arXiv · doi:10.48550/arxiv.1511.07122 · Cited by 7,738 · cited 1×
“Dilation8 [33] employs multiple dilated convolutional layers after class likelihood maps to exercise multi-scale context aggregation.”
BackgroundRethinking Atrous Convolution for Semantic Image Segmentation
Chen, L.-C., Papandreou, G., Schroff, F., & Adam, H. (2017) · arXiv · doi:10.48550/arxiv.1706.05587 · Cited by 7,517
Dual Attention Network for Scene Segmentation
Fu, J., Liu, J., Tian, H., Li, Y., Bao, Y., Fang, Z., & Lu, H. (2019) · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2019.00326 · Cited by 7,351
RefineNet: Multi-path Refinement Networks for High-Resolution Semantic Segmentation
Lin, G., Milan, A., Shen, C., & Reid, I. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.549 · Cited by 3,287
BiSeNet: Bilateral Segmentation Network for Real-Time Semantic Segmentation
Yu, C., Wang, J., Peng, C., Gao, C., Yu, G., & Sang, N. (2018) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-01261-8_20 · Cited by 2,968
Efficient Inference in Fully Connected CRFs with Gaussian Edge Potentials
Krähenbühl, P., & Koltun, V. (2012) · arXiv · doi:10.48550/arxiv.1210.5644 · Cited by 2,908
Conditional Random Fields as Recurrent Neural Networks
Zheng, S., Jayasumana, S., Romera-Paredes, B., Vineet, V., Su, Z., Du, D., Huang, C., & Torr, P. H. S. (2015) · 2015 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2015.179 · Cited by 2,386 · cited 1×
“CRFasRNN [46] reformulates DenseCRF with pairwise potential functions and unrolls the mean-field steps as recurrent neural networks, which composes a uniform framework and can be learned end-to-end.”
MethodSqueeze-and-Excitation Networks
Hu, J., Shen, L., Albanie, S., Sun, G. Z., & Wu, E. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1709.01507 · Cited by 1,908
ENet: A Deep Neural Network Architecture for Real-Time Semantic Segmentation
Paszke, A., Chaurasia, A., Kim, S., & Culurciello, E. (2016) · arXiv · doi:10.48550/arxiv.1606.02147 · Cited by 1,826 · cited 4×
“The number of parameters of CGNet M3N21 is close to ENet [23], and our method is 6.5% higher than it in mean IoU.”
BackgroundMethodInfluentialICNet for Real-Time Semantic Segmentation on High-Resolution Images
Zhao, H., Qi, X., Shen, X., Shi, J., & Jia, J. (2018) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-01219-9_25 · Cited by 1,709
DenseASPP for Semantic Segmentation in Street Scenes
Yang, M., Yu, K., Zhang, C., Li, Z., & Yang, K. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00388 · Cited by 1,674
ERFNet: Efficient Residual Factorized ConvNet for Real-Time Semantic Segmentation
Romera, E., Alvarez, J. M., Bergasa, L. M., & Arroyo, R. (2018) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2017.2750080 · Cited by 1,484
Context Encoding for Semantic Segmentation
Zhang, H., Dana, K., Shi, J., Zhang, Z., Wang, X., Tyagi, A., & Agrawal, A. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00747 · Cited by 1,464
Attention to Scale: Scale-Aware Semantic Image Segmentation
Chen, L.-C., Yang, Y., Wang, J., Xu, W., & Yuille, A. L. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.396 · Cited by 1,377
PSANet: Point-wise Spatial Attention Network for Scene Parsing
Zhao, H., Zhang, Y., Liu, S., Shi, J., Loy, C. C., Lin, D., & Jia, J. (2018) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-01240-3_17 · Cited by 1,192
Segmentation and Recognition Using Structure from Motion Point Clouds
Brostow, G. J., Shotton, J., Fauqueur, J., & Cipolla, R. (2008) · Lecture Notes in Computer Science · doi:10.1007/978-3-540-88682-2_5 · Cited by 1,050
ESPNet: Efficient Spatial Pyramid of Dilated Convolutions for Semantic Segmentation
Mehta, S., Rastegari, M., Caspi, A., Shapiro, L., & Hajishirzi, H. (2018) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-01249-6_34 · Cited by 1,029
Learning a Discriminative Feature Network for Semantic Segmentation
Yu, C., Wang, J., Peng, C., Gao, C., Yu, G., & Sang, N. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00199 · Cited by 870
DFANet: Deep Feature Aggregation for Real-Time Semantic Segmentation
Li, H., Xiong, P., Fan, H., & Sun, J. (2019) · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2019.00975 · Cited by 718
A new performance measure and evaluation benchmark for road detection algorithms
Fritsch, J., Kuhnl, T., & Geiger, A. (2013) · 16th International IEEE Conference on Intelligent Transportation Systems (ITSC 2013) · doi:10.1109/itsc.2013.6728473 · Cited by 690
Full-Resolution Residual Networks for Semantic Segmentation in Street Scenes
Pohlen, T., Hermans, A., Mathias, M., & Leibe, B. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.353 · Cited by 584
Laplacian Pyramid Reconstruction and Refinement for Semantic Segmentation
Ghiasi, G., & Fowlkes, C. C. (2016) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-46487-9_32 · Cited by 502
OCNet: Object Context Network for Scene Parsing
Yuan, Y., Huang, L., Guo, J., Zhang, C., Chen, X., & Wang, J. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1809.00916 · Cited by 453
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
Context Contrasted Feature and Gated Multi-scale Aggregation for Scene Segmentation
Ding, H., Jiang, X., Shuai, B., Liu, A. Q., & Wang, G. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00254 · Cited by 394
Searching for Efficient Multi-Scale Architectures for Dense Image Prediction
Chen, L.-C., Collins, M. D., Zhu, Y., Papandreou, G., Zoph, B., Schroff, F., Adam, H., & Shlens, J. (2018) · arXiv · doi:10.48550/arxiv.1809.04184 · Cited by 347
(2016) · Cited by 271
FasterSeg: Searching for Faster Real-time Semantic SegmentationPreprint
Chen, W., Gong, X., Liu, X., Zhang, Q., Li, Y., & Wang, Z. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1912.10917 · Cited by 226
Gated Feedback Refinement Network for Dense Image Labeling
Islam, M. A., Rochan, M., Bruce, N. D. B., & Wang, Y. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.518 · Cited by 218
Scale-Adaptive Convolutions for Scene Parsing
Zhang, R., Tang, S., Zhang, Y., Li, J., & Yan, S. (2017) · 2017 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.224 · Cited by 195 · cited 2×
“SAC [37] proposes a scale-adaptive convolution to acquire flexiblesize receptive fields.”
BackgroundSelf-citationLearning Sparse High Dimensional Filters: Image Filtering, Dense CRFs and Bilateral Neural Networks
Jampani, V., Kiefel, M., & Gehler, P. V. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.482 · Cited by 188
Fast, Exact and Multi-scale Inference for Semantic Image Segmentation with Deep Gaussian CRFs
Chandra, S., & Kokkinos, I. (2016) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-46478-7_25 · Cited by 175
Efficient ConvNet for real-time semantic segmentation
Romera, E., Álvarez, J. M., Bergasa, L. M., & Arroyo, R. (2017) · IEEE Intelligent Vehicles Symposium · doi:10.1109/ivs.2017.7995966 · Cited by 140
Efficient inference for fully-connected CRFs with stationarity
Zhang, Y., & Chen, T. (2012) · 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/cvpr.2012.6247724 · Cited by 124
Self-citationNassar, A., Amer, K., ElHakim, R., & ElHelw, M. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw.2018.00201 · Cited by 94
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
GINet: Graph Interaction Network for Scene Parsing
Wu, T., Lu, Y., Zhu, Y. M., Zhang, C., Wu, M., Ma, Z., & Guo, G. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-58520-4_3 · Cited by 51
Self-citationTree-Structured Kronecker Convolutional Network for Semantic Segmentation
Wu, T., Tang, S., Zhang, R., Cao, J., & Li, J. (2019) · IEEE International Conference on Multimedia and Expo (ICME) · doi:10.1109/icme.2019.00166 · Cited by 44
Self-citationGlobal-residual and Local-boundary Refinement Networks for Rectifying Scene Parsing Predictions
Zhang, R., Tang, S., Lin, M., Li, J., & Yan, S. (2017) · International Joint Conference on Artificial Intelligence · doi:10.24963/ijcai.2017/479 · Cited by 37
Self-citationPerspective-Adaptive Convolutions for Scene Parsing
Zhang, R., Tang, S., Zhang, Y., Li, J., & Yan, S. (2020) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2018.2890637 · Cited by 25
Self-citationObject Localization Based on Proposal Fusion
Tang, S., Li, Y., Deng, L., & Zhang, Y. (2017) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2017.2729786 · Cited by 25
Self-citationHigh Resolution Feature Recovering for Accelerating Urban Scene Parsing
Zhang, R., Tang, S., Liu, L., Zhang, Y., Li, J., & Yan, S. (2018) · International Joint Conference on Artificial Intelligence · doi:10.24963/ijcai.2018/161 · Cited by 16
Self-citationTree-structured Kronecker Convolutional Network for Semantic SegmentationPreprint
Wu, T., Tang, S., Zhang, R., et al. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1812.04945 · Cited by 9
Self-citationConsensus Feature Network for Scene Parsing
Wu, T., Tang, S., Zhang, R., & Guo, G. (2021) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2021.3094333 · Cited by 7
Self-citationFDDWNet: A Lightweight Convolutional Neural Network for Real-time Sementic SegmentationPreprint
Liu, J., Zhou, Q., Qiang, Y., Kang, B., Wu, X., & Zheng, B. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1911.00632 · Cited by 3
Consensus Feature Network for Scene ParsingPreprint
Wu, T., Tang, S., Zhang, R., et al. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1907.12411 · Cited by 3
Self-citation
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
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.