DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs
Open accessThe DOI matches its Crossref record; 128 of the 128 references it cites were found in a registry or an index.
Abstract
In this work we address the task of semantic image segmentation with Deep Learning and make three main contributions that are experimentally shown to have substantial practical merit. First, we highlight convolution with upsampled filters, or 'atrous convolution', as a powerful tool in dense prediction tasks. Atrous convolution allows us to explicitly control the resolution at which feature responses are computed within Deep Convolutional Neural Networks. It also allows us to effectively enlarge the field of view of filters to incorporate larger context without increasing the number of parameters or the amount of computation. Second, we propose atrous spatial pyramid pooling (ASPP) to robustly segment objects at multiple scales. ASPP probes an incoming convolutional feature layer with filters at multiple sampling rates and effective fields-of-views, thus capturing objects as well as image context at multiple scales. Third, we improve the localization of object boundaries by combining methods from DCNNs and probabilistic graphical models. The commonly deployed combination of max-pooling and downsampling in DCNNs achieves invariance but has a toll on localization accuracy. We overcome this by combining the responses at the final DCNN layer with a fully connected Conditional Random Field (CRF), which is shown both qualitatively and quantitatively to improve localization performance. Our proposed "DeepLab" system sets the new state-of-art at the PASCAL VOC-2012 semantic image segmentation task, reaching 79.7 percent mIOU in the test set, and advances the results on three other datasets: PASCAL-Context, PASCAL-Person-Part, and Cityscapes. All of our code is made publicly available online.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
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
“According to the authors, dilated convolutions allow for an exponential increase in the receptive field without a decrease in resolution or increase in parameters, as may happen in the traditional pooling or stride-based approaches.”
From Multimodal semantic segmentation in autonomous driving: A review of current approaches and future perspectives (2022) · cites this paper as [21]
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“Nevertheless, CRFs are still the most commonly adopted and recognized approach to refine segmentation masks of both natural images (Schwing and Urtasun (2015), Chen et al. (2017) and Zheng et al. (2015)) and medical images (Roth et al. (2015), Chen and de Bruijne (2018) and Wachinger et al. (2018)).”
From Embracing imperfect datasets: A review of deep learning solutions for medical image segmentation (2020) · cites this paper as Chen et al. (2017)
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“Nonetheless, none of these can fully eliminate the limitation of FCN architecture in receptive field.”
From Vision Transformers: From Semantic Segmentation to Dense Prediction (2024) · cites this paper as Chen et al. (2017)
Experimental — accuracy not yet measuredThe cited source says what the claim attributes to it.
In the citing paper
“In the PASCAL VOC-2012 image segmentation, their model obtained an excellent performance.”
From Review of deep learning: concepts, CNN architectures, challenges, applications, future directions (2021) · cites this paper as [308]
The cited source says what the claim attributes to it.
In the citing paper
“Employing FC Conditional Random Fields (CRFs), atrous spatial pyramid pooling, and up-sampled filters were techniques introduced by Chen et al. [308]. These authors aimed to enhance the accuracy of localization and enlarge the field of view of every filter at a multi-scale. Their model, DeepLab, attained 79.7% mIOU (mean Intersection Over Union).”
From Review of deep learning: concepts, CNN architectures, challenges, applications, future directions (2021) · cites this paper as [308]
12 more claims about this paper
Create a free account to see every claim other papers make about this one.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
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
Very Deep Convolutional Networks for Large-Scale Image Recognition
Simonyan, K., & Zisserman, A. (2014) · arXiv · doi:10.48550/arxiv.1409.1556 · Cited by 114,148
ImageNet classification with deep convolutional neural networks
Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2017) · Communications of the ACM · doi:10.1145/3065386 · Cited by 112,155
U-Net: Convolutional Networks for Biomedical Image Segmentation
Ronneberger, O., Fischer, P., & Brox, T. (2015) · Lecture notes in computer science · doi:10.1007/978-3-319-24574-4_28 · Cited by 99,404
Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
Ren, S., He, K., Girshick, R., & Sun, J. (2017) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2016.2577031 · Cited by 73,472
Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
Ren, S., He, K., Girshick, R., & Sun, J. (2015) · arXiv · doi:10.48550/arxiv.1506.01497 · Cited by 70,812
Gradient-based learning applied to document recognition
Lecun, Y., Bottou, L., Bengio, Y., & Haffner, P. (1998) · Proceedings of the IEEE · doi:10.1109/5.726791 · Cited by 58,805 · cited 1×
“DEEP Convolutional Neural Networks (DCNNs) [1] have pushed the performance of computer vision systems to soaring heights on a broad array of high-level problems, including image classification [2], [3], [4], [5], [6] and object detection [7], [8], [9], [10], [11], [12], where DCNNs trained in an end-to-end manner have…”
BackgroundGoing 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
Microsoft COCO: Common Objects in Context
Lin, T.-Y., Maire, M., Belongie, S., Hays, J., Perona, P., Ramanan, D., Dollár, P., & Zitnick, C. L. (2014) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-10602-1_48 · Cited by 45,460
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
Cited by
Items 1,101–1,168 of 1,168
Learning From Synthetic Photorealistic Raindrop for Single Image Raindrop Removal
Hao, Z., You, S., Li, Y., Li, K., & Lu, F. (2019) · 2019 IEEE/CVF International Conference on Computer Vision Workshop (ICCVW) · doi:10.1109/iccvw.2019.00534 · Cited by 54
Multi-Modal Sensor Fusion-Based Semantic Segmentation for Snow Driving Scenarios
Vachmanus, S., Ravankar, A. A., Emaru, T., & Kobayashi, Y. (2021) · IEEE Sensors Journal · doi:10.1109/jsen.2021.3077029 · Cited by 53
“The ASPP module of DeeplabV3 [37] was developed from a previous version [50] by including batch normalization [51] into the model and adopting an image-level feature to incorporate the global context information.”
MethodLi, G., Jiang, S., Yun, I., Kim, J., & Kim, J. (2020) · IEEE Access · doi:10.1109/access.2020.2971760 · Cited by 53
Make RepVGG Greater Again: A Quantization-aware Approach
Chu, X., Li, L., & Zhang, B. (2022) · arXiv · doi:10.48550/arxiv.2212.01593 · Cited by 53
Robust Semantic Segmentation in Adverse Weather Conditions by means of Sensor Data Fusion
Pfeuffer, A., & Dietmayer, K. (2019) · 2019 22th International Conference on Information Fusion (FUSION) · doi:10.23919/fusion43075.2019.9011192 · Cited by 51
Let’s Get Dirty: GAN Based Data Augmentation for Camera Lens Soiling Detection in Autonomous Driving
Uricar, M., Sistu, G., Rashed, H., Vobecky, A., Kumar, V. R., Krizek, P., Burger, F., & Yogamani, S. (2021) · 2021 IEEE Winter Conference on Applications of Computer Vision (WACV) · doi:10.1109/wacv48630.2021.00081 · Cited by 66
NNWarp: Neural Network-based Nonlinear Deformation
Luo, R., Shao, T., Wang, H., Xu, W., Chen, X., Zhou, K., & Yang, Y. (2018) · IEEE Transactions on Visualization and Computer Graphics · doi:10.1109/tvcg.2018.2881451 · Cited by 50
Complementary Random Masking for RGB-Thermal Semantic Segmentation
Shin, U., Lee, K., Kweon, I. S., & Oh, J. (2024) · 2024 IEEE International Conference on Robotics and Automation (ICRA) · doi:10.1109/icra57147.2024.10611200 · Cited by 49
“RGB-thermal semantic segmentation networks have also been proposed to overcome the limitation of RGB semantic segmentation networks [4], [13], [40], [6], [5] that are often vulnerable to extreme conditions, such as low-light, rainy, snowy, and sandy conditions.”
BackgroundMethodDeep Learning of High-Order Interactions for Protein Interface Prediction
Liu, Y., Yuan, H., Cai, L., & Ji, S. (2020) · Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining · doi:10.1145/3394486.3403110 · Cited by 48
“Note that any modern CNN architecture such as ResNet [14], UNet [29] or DeepLab [6] can be flexibly integrated into our framework to perform dense prediction and the whole system can be trained end-to-end.”
BackgroundAdvisable Learning for Self-Driving Vehicles by Internalizing Observation-to-Action Rules
Kim, J., Moon, S., Rohrbach, A., Darrell, T., & Canny, J. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.00968 · Cited by 45
GCA-Net : Utilizing Gated Context Attention for Improving Image Forgery Localization and Detection
Das, S., Islam, M. S., & Amin, M. R. (2022) · 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw56347.2022.00018 · Cited by 45
Automated ultrasound assessment of amniotic fluid index using deep learning
Cho, H. C., Sun, S., Min Hyun, C., Kwon, J.-Y., Kim, B., Park, Y., & Seo, J. K. (2021) · Medical Image Analysis · doi:10.1016/j.media.2020.101951 · Cited by 43
Recaptured screen image demoiréing
Yue, H., Mao, Y., Liang, L., Xu, H., Hou, C., & Yang, J. (2021) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2020.2969984 · Cited by 42
A Layer-Based Sequential Framework for Scene Generation with GANs
Turkoglu, M. O., Thong, W., Spreeuwers, L., & Kicanaoglu, B. (2019) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v33i01.33018901 · Cited by 41
AuxNet: Auxiliary Tasks Enhanced Semantic Segmentation for Automated Driving
Chennupati, S., Sistu, G., Yogamani, S., & Rawashdeh, S. (2019) · Proceedings of the 14th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications · doi:10.5220/0007684106450652 · Cited by 42
“While these papers focus on architectures, Deeplab (Chen et al., 2018a) and EffNet (Freeman et al., 2018) focused on efficient convolutional layers by using dilated and separable convolutions.”
BackgroundMethodInfluentialTheodorou, L., Massiceti, D., Zintgraf, L., Stumpf, S., Morrison, C., Cutrell, E., Harris, M. T., & Hofmann, K. (2021) · Proceedings of the 23rd International ACM SIGACCESS Conference on Computers and Accessibility · doi:10.1145/3441852.3471225 · Cited by 42
“Enabling this application requires new machine learning (ML) techniques that work well when a small number of examples are available, termed “few-shot” learning [15, 51], and, crucially, appropriate user-centric datasets to drive ML innovation in this space.”
SELMA: SEmantic Large-Scale Multimodal Acquisitions in Variable Weather, Daytime and Viewpoints
Testolina, P., Barbato, F., Michieli, U., Giordani, M., Zanuttigh, P., & Zorzi, M. (2023) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2023.3257086 · Cited by 41
“We trained a DeepLab-V2 architecture (with ResNet-101 as backbone) on each dataset, and performed the testing on all the domains.”
BackgroundMethodInfluentialUNCERTAINTY MODELING AND INTERPRETABILITY IN CONVOLUTIONAL NEURAL NETWORKS FOR POLYP SEGMENTATION
Wickstrom, K., Kampffmeyer, M., & Jenssen, R. (2018) · 2018 IEEE 28th International Workshop on Machine Learning for Signal Processing (MLSP) · doi:10.1109/mlsp.2018.8516998 · Cited by 41
Hard pixel mining for depth privileged semantic segmentation
Gu, Z., Niu, L., Zhao, H., & Zhang, L. (2021) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2020.3035231 · Cited by 41
“Recently, abundant RGB based semantic segmentation meth-ods [1], [2], [3], [4], [5], [6], [7], [8], [9], [10], [11] have been developed and achieved excellent performances in given datasets.”
BackgroundAssessment of a new GeoAI foundation model for flood inundation mapping
Li, W., Lee, H., Wang, S., Hsu, C.-Y., & Arundel, S. T. (2023) · arXiv · doi:10.48550/arxiv.2309.14500 · Cited by 40
Visual Semantic Information Pursuit: A Survey
Liu, D., Bober, M., & Kittler, J. (2021) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2019.2950025 · Cited by 39
Assessment of a new GeoAI foundation model for flood inundation mapping
Li, W., Lee, H., Wang, S., Hsu, C.-Y., & Arundel, S. T. (2023) · Proceedings of the 6th ACM SIGSPATIAL International Workshop on AI for Geographic Knowledge Discovery · doi:10.1145/3615886.3627747 · Cited by 39
“Another family of convolutional semantic segmentation models include the DeepLab family developed by Google [7].”
MethodModel-Agnostic Method for Thoracic Wall Segmentation in Fetal Ultrasound Videos
Shozu, K., Komatsu, M., Sakai, A., Komatsu, R., Dozen, A., Machino, H., Yasutomi, S., Arakaki, T., Asada, K., Kaneko, S., et al. (2020) · Biomolecules · doi:10.3390/biom10121691 · Cited by 38
Endometrium segmentation on transvaginal ultrasound image using key-point discriminator
Park, H., Lee, H. J., Kim, H. G., Ro, Y. M., Shin, D., Lee, S. R., Kim, S. H., & Kong, M. (2019) · Medical Physics · doi:10.1002/mp.13677 · Cited by 37
Retrieval-based Spatially Adaptive Normalization for Semantic Image Synthesis
Shi, Y., Liu, X., Wei, Y., Wu, Z., & Zuo, W. (2022) · 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52688.2022.01094 · Cited by 36
“They both require a pretrained segmentation model to compute segmentation accuracy [2, 30, 31].”
MethodAttention Weighted Local Descriptors
Wang, C., Xu, R., Lu, K., Xu, S., Meng, W., Zhang, Y., Fan, B., & Zhang, X. (2023) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2023.3266728 · Cited by 36
Mapping oil palm density at country scale: An active learning approach
Rodríguez, A. C., D'Aronco, S., Schindler, K., & Wegner, J. D. (2021) · Remote Sensing of Environment · doi:10.1016/j.rse.2021.112479 · Cited by 36
Neural Batch Sampling with Reinforcement Learning for Semi-supervised Anomaly Detection
Chu, W.-H., & Kitani, K. M. (2020) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-58574-7_45 · Cited by 34
“Although supervised segmentation algorithms have seen significant advances in recent years [7,24,29], they are difficult to apply directly to such tasks due to the rare occurrence of anomalies during data collection.”
BackgroundInfluentialMake RepVGG Greater Again: A Quantization-Aware Approach
Chu, X., Li, L., & Zhang, B. (2024) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v38i10.29045 · Cited by 53
The Smart Black Box: A Value-Driven High-Bandwidth Automotive Event Data Recorder
Yao, Y., & Atkins, E. (2021) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2020.2971385 · Cited by 33
“For semantic segmentation tasks, we use DeepLabV2 [13] pre-trained on the crowdflower dataset.”
BackgroundMethodInfluentialISDNet: AI-enabled Instance Segmentation of Aerial Scenes for Smart Cities
Garg, P., Chakravarthy, A. S., Mandal, M., Narang, P., Chamola, V., & Guizani, M. (2021) · ACM Transactions on Internet Technology · doi:10.1145/3418205 · Cited by 32
MTLDesc: Looking Wider to Describe Better
Wang, C., Xu, R., Zhang, Y., Xu, S., Meng, W., Fan, B., & Zhang, X. (2022) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v36i2.20138 · Cited by 33
DooDLeNet: Double DeepLab Enhanced Feature Fusion for Thermal-color Semantic Segmentation
Frigo, O., Martin-Gaffe, L., & Wacongne, C. (2022) · 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw56347.2022.00341 · Cited by 32
Optical Flow Estimation with Deep Learning, a Survey on Recent Advances
Savian, S., Elahi, M., & Tillo, T. (2020) · Unsupervised and Semi-Supervised Learning · doi:10.1007/978-3-030-32583-1_12 · Cited by 29
An Adaptive Supervision Framework for Active Learning in Object Detection
Desai, S. V., Chandra, A. L., Guo, W., Ninomiya, S., & Balasubramanian, V. N. (2019) · arXiv · doi:10.48550/arxiv.1908.02454 · Cited by 29
AQD: Towards Accurate Quantized Object Detection
Chen, P., Liu, J., Zhuang, B., Tan, M., & Shen, C. (2021) · 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr46437.2021.00017 · Cited by 29
“Deep neural networks (DNNs) have achieved great success in many computer vision tasks, such as image classification [11, 21, 12], semantic segmentation [31, 10, 5], object detection [37, 27, 26], etc.”
Deep-recursive residual network for image semantic segmentation
Zhang, Y., Li, X., Lin, M., Chiu, B., & Zhao, M. (2020) · Neural Computing and Applications · doi:10.1007/s00521-020-04738-5 · Cited by 27
Collaborative Multi-Robot Systems for Search and Rescue: Coordination and Perception
Queralta, J. P., Taipalmaa, J., Pullinen, B. C., Sarker, V. K., Gia, T. N., Tenhunen, H., Gabbouj, M., Raitoharju, J., & Westerlund, T. (2020) · arXiv · doi:10.48550/arxiv.2008.12610 · Cited by 27
“In [183], three commonly used state-of-the-art deep learning semantic segmentation methods (U-Net [184], PSP-Net [185] and DeepLabv2 [186]) are bench-marked on a maritime environment.”
BackgroundMethodGlobal mapping of river sediment bars
Carbonneau, P. E., & Bizzi, S. (2024) · Earth Surface Processes and Landforms · doi:10.1002/esp.5739 · Cited by 27
Perspective-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
Barrientos-Espillco, F., Gascó, E., López-González, C. I., Gómez-Silva, M. J., & Pajares, G. (2023) · Applied Soft Computing · doi:10.1016/j.asoc.2023.110315 · Cited by 26
A Survey on Deep Learning for Precision Oncology
Wang, C.-W., Khalil, M.-A., & Firdi, N. (2022) · Diagnostics · doi:10.3390/diagnostics12061489 · Cited by 23
Pancreatic Adenocarcinoma: Imaging Modalities and the Role of Artificial Intelligence
Anghel, C., Mugur, G. C., Anghel, D. A., Rusu-Munteanu, G. I., Dumitru, R. L., & Lupescu, I. G. (2024) · doi:10.20944/preprints202401.0904.v1 · Cited by 23
Dimitri, G. M. (2022) · Computers · doi:10.3390/computers11110163 · Cited by 22
Vision Transformers: From Semantic Segmentation to Dense Prediction
Zhang, L., Lu, J., Zheng, S., Zhao, X., Zhu, X., Fu, Y., Xiang, T., Feng, J., & Torr, P. H. S. (2024) · International Journal of Computer Vision · doi:10.1007/s11263-024-02173-w · Cited by 23
“Recently, ViT [1] is the first work to show that a pure Transformer based image classification model can achieve the state-of-the-art.”
A simulation-based few samples learning method for surface defect segmentation
Wei, T., Cao, D., Zheng, C., & Yang, Q. (2020) · Neurocomputing · doi:10.1016/j.neucom.2020.06.090 · Cited by 21
Outdoor RGBD Instance Segmentation With Residual Regretting Learning
Xu, Z., Liu, S., Shi, J., & Lu, C. (2020) · IEEE Transactions on Image Processing · doi:10.1109/tip.2020.2975711 · Cited by 20
“By combining the benefits in both object detection [5]–[7] and semantic segmentation [8]–[10], it not only requires accurate object localization but also precise instance mask prediction.”
BackgroundAttendNets: Tiny Deep Image Recognition Neural Networks for the Edge via Visual Attention Condensers
Wong, A., Famouri, M., & Shafiee, M. J. (2020) · arXiv · doi:10.48550/arxiv.2009.14385 · Cited by 20
“Deep learning [11] has resulted in significant breakthroughs in the area of computer vision, with stateof-the-art performance in a wide range of visual perception tasks such as image recognition [6, 9], object detection [4], and segmentation [1, 7].”
BackgroundBouget, D., Eijgelaar, R. S., Pedersen, A., Kommers, I., Ardon, H., Barkhof, F., Bello, L., Berger, M. S., Nibali, M. C., Furtner, J., et al. (2021) · Cancers · doi:10.3390/cancers13184674 · Cited by 19
Sketch2code: Generating a website from a paper mockup
Robinson, A. (2019) · arXiv · doi:10.48550/arxiv.1905.13750 · Cited by 18
Multiscale ensemble of convolutional neural networks for skin lesion classification
Liu, Y., Wang, Z., Li, Z., Li, J., Li, T., Chen, P., & Liang, R. (2021) · IET Image Processing · doi:10.1049/ipr2.12214 · Cited by 18
Automatic Fetal Middle Sagittal Plane Detection in Ultrasound Using Generative Adversarial Network
Tsai, P.-Y., Hung, C.-H., Chen, C.-Y., & Sun, Y.-N. (2020) · Diagnostics · doi:10.3390/diagnostics11010021 · Cited by 18
“The atrous spatial pyramid pooling (ASPP) probes an incoming convolutional feature layer with filters at multiple sampling rates and effective fields-of-views, thus capturing objects as well as image context at multipl scales [21].”
BackgroundKuang, B., Gu, C., Rana, Z. A., Zhao, Y., Sun, S., & Nnabuife, S. G. (2022) · Sensors · doi:10.3390/s22218393 · Cited by 15
van Rijthoven, M., Balkenhol, M., Siliņa, K., van der Laak, J., & Ciompi, F. (2021) · Medical Image Analysis · doi:10.1016/j.media.2020.101890 · Cited by 16
Print Defect Mapping with Semantic Segmentation
Valente, A. C., Wada, C., Neves, D., Neves, D., Perez, F. V. M., Megeto, G. A. S., Cascone, M. H., Gomes, O., & Lin, Q. (2020) · 2020 IEEE Winter Conference on Applications of Computer Vision (WACV) · doi:10.1109/wacv45572.2020.9093470 · Cited by 21
“Results on public benchmarks have considerably improved with the use of fully-convolutional DCNNs, such as FCN [11], U-Net [14], and DeepLab [4].”
BackgroundMethodABYOLOv4: improved YOLOv4 human object detection based on enhanced multi-scale feature fusion
Li, R., Zeng, X., Yang, S., Li, Q., Yan, A., & Li, D. (2024) · EURASIP Journal on Advances in Signal Processing · doi:10.1186/s13634-023-01105-z · Cited by 15
“…work can be summarized as follows: (1) To enhance the perception of multi-scale targets, this paper intends to replace the original SPP (spatial pyramid pooling) [21] module with the ASPP (Atrous Spatial Pyramid Pooling) [22] module, which increases the receptive field hierarchy of the network.”
BackgroundISP Meets Deep Learning: A Survey on Deep Learning Methods for Image Signal Processing
Santos, C. F. G. D., Arrais, R. R., Silva, J. V. S. D., Silva, M. H. M. D., Neto, W. B. G. D. A., Lopes, L. T., Bileki, G. A., Lima, I. O., Rondon, L. B., Souza, B. M. D., et al. (2025) · ACM Computing Surveys · doi:10.1145/3708516 · Cited by 15
Helping Visually Impaired People Take Better Quality Pictures
Mandal, M., Ghadiyaram, D., Gurari, D., & Bovik, A. C. (2023) · IEEE Transactions on Image Processing · doi:10.1109/tip.2023.3282067 · Cited by 14
“Atrous VGG-16 [25] performed the worst, while ResNet-50V2 [53] and ResNeXt-50 [55] models consistently performed best on most distortion classes.”
BackgroundInfluentialC3net: demoiréing network attentive in channel, color, and concatenation
Kim, S., Nam, H., Kim, J., & Jeong, J. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw50498.2020.00221 · Cited by 9
Antony, B. J., Maetschke, S., & Garnavi, R. (2019) · PLOS ONE · doi:10.1371/journal.pone.0203726 · Cited by 8
Defective samples simulation through neural style transfer for automatic surface defect segment
Wei, T., Cao, D., Jiang, X., Zheng, C., & Liu, L. (2020) · 2019 International Conference on Optical Instruments and Technology: Optoelectronic Measurement Technology and Systems · doi:10.1117/12.2540464 · Cited by 10
“Chen et al.18 proposed Encoder-Decoder structure segmentation net Deeplab V3+, which is mainly composed of Deeplab v316 as the encoder, while the decoder uses a simple but effective module.”
MethodResidual Grounding Transformer Network for Terrain Recognition on the Lunar Surface
Qiu, L., Li, H., Li, Z., & Wang, C. (2021) · Applied Optics · doi:10.1364/ao.428232 · Cited by 7
Bao, Y., Zhang, J., Zhang, Q., Chang, J., Lu, D., & Fu, Y. (2021) · Frontiers in Medicine · doi:10.3389/fmed.2021.696305 · Cited by 5
“The model reached an intersection over union (IoU) of 0.863, a specificity of 0.969, and a sensitivity of 0.939, respectively, which were significantly better than the previous IoU (0.764) (5). specificity (0.927), and sensitivity (0.869) (6).”
BackgroundInfluentialQiu, Y., Lu, H., Mei, J., Bao, S., & Xu, J. (2024) · Expert Systems with Applications · doi:10.1016/j.eswa.2024.124734 · Cited by 5
(2023) · doi:10.1109/iros55552.2023.10341959 · Cited by 4
“We follow the same protocols of [3] and [2] (e.”
MethodInfluentialRoVi-Aug: Robot and Viewpoint Augmentation for Cross-Embodiment Robot Learning
Chen, L. Y., Xu, C., Dharmarajan, K., Irshad, M. Z., Cheng, R., Keutzer, K., Tomizuka, M., Vuong, Q., & Goldberg, K. (2024) · arXiv · doi:10.48550/arxiv.2409.03403 · Cited by 1
Self-citationSeg-Zero: Reasoning-Chain Guided Segmentation via Cognitive Reinforcement
Liu, Y., Peng, B., Zhong, Z., Yue, Z., Lu, F., Yu, B., & Jia, J. (2025) · arXiv · doi:10.48550/arxiv.2503.06520
Deep ViT Features as Dense Visual Descriptors
Amir, S., Gandelsman, Y., Bagon, S., & Dekel, T. (2021) · arXiv · doi:10.48550/arxiv.2112.05814
Metadata
- Authors
- Chen, L.-C., Papandreou, G., Kokkinos, I., Murphy, K., & Yuille, A. L.
- Affiliations
- Google (United States) (US)
- University College London (GB)
- Johns Hopkins University (US)
- Venue
- IEEE Transactions on Pattern Analysis and Machine Intelligence
- Published
- 2018-04-01
- Volume
- 40
- Issue
- 4
- Pages
- 834-848
- ISSN
- 0162-8828 (ISSN-L)
- 2160-9292
- OpenAlex
- W2412782625
- Cited by
- 22,392
- References
- 108
- Citations by year
- 2026: 1655 · 2025: 2789 · 2024: 3153 · 2023: 3262 · 2022: 3039 · 2021: 2885 · 2020: 2282 · 2019: 1914 · 2018: 1035
- FWCI
- 631.17
- Type
- journal article
- Language
- en
- Open access
- green
- arxiv.org
- Locations
- IEEE Transactions on Pattern Analysis and Machine Intelligence (publishedVersion)
- PubMed (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- UCL Discovery (University College London) (submittedVersion)
- arXiv (Cornell University)
- Funders
- ARO 62250-CS
- FP7-RECONFIG
- FP7-MOBOT
- H2020-ISUPPORT EU
- NVIDIA Corporation
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Medical Image Segmentation Techniques
- Physical Sciences › Computer Science › Artificial Intelligence › Domain Adaptation and Few-Shot Learning
- Keywords
- semantic segmentation, dilated convolution, atrous spatial pyramid pooling, conditional random fields, dense prediction, boundary localization, Pascal VOC 2012, Pascal Context, cityscape, probabilistic graphical models
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.
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.