mlsanityData to 13 Oct 2026

DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs

arXiv 1606.00915 ↗First posted 2 Jun 2016cs.CVcited by 3,240

Not on the map. Why?

Cited by 54 in Multimodal LLMs / vision-language models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

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% 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.

Key facts. Cited by 3,240 papers in the map (data through 13 Oct 2026). First posted on arXiv 2 Jun 2016.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 13 Oct)

Citing papers per year: 2018: 1; 2019: 1; 2020: 0; 2021: 827; 2022: 744; 2023: 669; 2024: 485; 2025: 364; 2026: 149.

3,240 papers.

Sort:

By area:

  1. 2021SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformerscited by 2,930
  2. 2021Masked-attention Mask Transformer for Universal Image Segmentationcited by 2,344
  3. 2021Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutionscited by 1,961
  4. 2021Vision Transformers for Dense Predictioncited by 1,795
  5. 2021Swin-Unet: Unet-like Pure Transformer for Medical Image Segmentationcited by 1,219
  6. 2021Grounded Language-Image Pre-trainingcited by 1,152
  7. 2021Per-Pixel Classification is Not All You Need for Semantic Segmentationcited by 1,150
  8. 2021UNETR: Transformers for 3D Medical Image Segmentationcited by 957
  9. 2021Segmenter: Transformer for Semantic Segmentationcited by 855
  10. 2023Vision-Language Models for Vision Tasks: A Surveycited by 837
  11. 2023LISA: Reasoning Segmentation via Large Language Modelcited by 773
  12. 2021PVT v2: Improved Baselines with Pyramid Vision Transformercited by 750
38 more
  1. 2024SpatialVLM: Endowing Vision-Language Models with Spatial Reasoning Capabilitiescited by 687
  2. 2021Twins: Revisiting the Design of Spatial Attention in Vision Transformerscited by 565
  3. 2022Open-Vocabulary Semantic Segmentation with Mask-adapted CLIPcited by 563
  4. 2023Segment Everything Everywhere All at Oncecited by 547
  5. 2021DenseCLIP: Language-Guided Dense Prediction with Context-Aware Promptingcited by 532
  6. 2022GroupViT: Semantic Segmentation Emerges from Text Supervisioncited by 531
  7. 2021MetaFormer Is Actually What You Need for Visioncited by 524
  8. 2021Image Segmentation Using Text and Image Promptscited by 511
  9. 2022InternImage: Exploring Large-Scale Vision Foundation Models with Deformable Convolutionscited by 482
  10. 2022MaxViT: Multi-Axis Vision Transformercited by 476
  11. 2021PointCLIP: Point Cloud Understanding by CLIPcited by 463
  12. 2021Semi-Supervised Semantic Segmentation with Cross Pseudo Supervisioncited by 462
  13. 2022Kubric: A scalable dataset generatorcited by 375
  14. 2021MonoScene: Monocular 3D Semantic Scene Completioncited by 359
  15. 2021Deep ViT Features as Dense Visual Descriptorscited by 329
  16. 2022OneFormer: One Transformer to Rule Universal Image Segmentationcited by 327
  17. 2021Categorical Depth Distribution Network for Monocular 3D Object Detectioncited by 326
  18. 2021DAFormer: Improving Network Architectures and Training Strategies for Domain-Adaptive Semantic Segmentationcited by 299
  19. 2023Side Adapter Network for Open-Vocabulary Semantic Segmentationcited by 298
  20. 2023OccFormer: Dual-path Transformer for Vision-based 3D Semantic Occupancy Predictioncited by 290
  21. 2021SegDiff: Image Segmentation with Diffusion Probabilistic Modelscited by 280
  22. 2021Prototypical Pseudo Label Denoising and Target Structure Learning for Domain Adaptive Semantic Segmentationcited by 268
  23. 2021DatasetGAN: Efficient Labeled Data Factory with Minimal Human Effortcited by 264
  24. 2021LoveDA: A Remote Sensing Land-Cover Dataset for Domain Adaptive Semantic Segmentationcited by 260
  25. 2022SegNeXt: Rethinking Convolutional Attention Design for Semantic Segmentationcited by 252
  26. 2023Personalize Segment Anything Model with One Shotcited by 250
  27. 2022Transformers in Medical Imaging: A Surveycited by 245
  28. 2021Exploring Cross-Image Pixel Contrast for Semantic Segmentationcited by 242
  29. 2025Seg-Zero: Reasoning-Chain Guided Segmentation via Cognitive Reinforcementcited by 237
  30. 2023MOSE: A New Dataset for Video Object Segmentation in Complex Scenescited by 233
  31. 2022CMX: Cross-Modal Fusion for RGB-X Semantic Segmentation with Transformerscited by 230
  32. 2021A Simple Baseline for Open-Vocabulary Semantic Segmentation with Pre-trained Vision-language Modelcited by 223
  33. 2022Semi-Supervised Semantic Segmentation Using Unreliable Pseudo-Labelscited by 218
  34. 2023CAT-Seg: Cost Aggregation for Open-Vocabulary Semantic Segmentationcited by 217
  35. 2021K-Net: Towards Unified Image Segmentationcited by 211
  36. 2021Multi-Scale Vision Longformer: A New Vision Transformer for High-Resolution Image Encodingcited by 207
  37. 2023Convolutions Die Hard: Open-Vocabulary Segmentation with Single Frozen Convolutional CLIPcited by 200
  38. 2021Decoupling Zero-Shot Semantic Segmentationcited by 199

50 most cited of 3,240 All 3,240 (JSON)