mlsanityData to 7 Oct 2026

InverseForm: A Loss Function for Structured Boundary-Aware Segmentation

arXiv 2104.02745 ↗First posted 6 Apr 2021cs.CV cs.LGcited by 65

Not on the map. Why?

Abstract (arXiv)

We present a novel boundary-aware loss term for semantic segmentation using an inverse-transformation network, which efficiently learns the degree of parametric transformations between estimated and target boundaries. This plug-in loss term complements the cross-entropy loss in capturing boundary transformations and allows consistent and significant performance improvement on segmentation backbone models without increasing their size and computational complexity. We analyze the quantitative and qualitative effects of our loss function on three indoor and outdoor segmentation benchmarks, including Cityscapes, NYU-Depth-v2, and PASCAL, integrating it into the training phase of several backbone networks in both single-task and multi-task settings. Our extensive experiments show that the proposed method consistently outperforms baselines, and even sets the new state-of-the-art on two datasets.

Key facts. Cited by 65 papers in the map (data through 7 Oct 2026). Builds on 38 of its 54 references that are in the map. First posted on arXiv 6 Apr 2021.

Builds on

38 of 54 references.

References · 38

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Fully Convolutional Networks for Semantic Segmentationcited by 4,845
  3. 2017Squeeze-and-Excitation Networkscited by 4,763
  4. 2016The Cityscapes Dataset for Semantic Urban Scene Understandingcited by 4,427
  5. 2016DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFscited by 3,239
  6. 2018Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentationcited by 3,210
  7. 2016Wide Residual Networkscited by 3,057
  8. 2016Pyramid Scene Parsing Networkcited by 2,472
  9. 2015Spatial Transformer Networkscited by 1,423
  10. 2019Deep High-Resolution Representation Learning for Visual Recognitioncited by 1,417
  11. 2019Segmentation Transformer: Object-Contextual Representations for Semantic Segmentationcited by 573
  12. 2016RefineNet: Multi-Path Refinement Networks for High-Resolution Semantic Segmentationcited by 463
26 more
  1. 2019PointRend: Image Segmentation as Renderingcited by 439
  2. 2018PAD-Net: Multi-Tasks Guided Prediction-and-Distillation Network for Simultaneous Depth Estimation and Scene Parsingcited by 224
  3. 2019High-Resolution Representations for Labeling Pixels and Regionscited by 211
  4. 2017Large Kernel Matters -- Improve Semantic Segmentation by Global Convolutional Networkcited by 208
  5. 2016UberNet: Training a `Universal' Convolutional Neural Network for Low-, Mid-, and High-Level Vision using Diverse Datasets and Limited Memorycited by 200
  6. 2020Hierarchical Multi-Scale Attention for Semantic Segmentationcited by 183
  7. 2019Gated-SCNN: Gated Shape CNNs for Semantic Segmentationcited by 165
  8. 2020MTI-Net: Multi-Scale Task Interaction Networks for Multi-Task Learningcited by 157
  9. 2019Attentive Single-Tasking of Multiple Taskscited by 148
  10. 2019Pattern-Affinitive Propagation across Depth, Surface Normal and Semantic Segmentationcited by 141
  11. 2020Bi-directional Cross-Modality Feature Propagation with Separation-and-Aggregation Gate for RGB-D Semantic Segmentationcited by 120
  12. 2020CascadePSP: Toward Class-Agnostic and Very High-Resolution Segmentation via Global and Local Refinementcited by 113
  13. 2019Boundary-Aware Feature Propagation for Scene Segmentationcited by 107
  14. 2019ACNet: Attention Based Network to Exploit Complementary Features for RGBD Semantic Segmentationcited by 105
  15. 2020SegFix: Model-Agnostic Boundary Refinement for Segmentationcited by 97
  16. 2017Learning Affinity via Spatial Propagation Networkscited by 79
  17. 2019AET vs. AED: Unsupervised Representation Learning by Auto-Encoding Transformations rather than Datacited by 77
  18. 2020Temporally Distributed Networks for Fast Video Semantic Segmentationcited by 77
  19. 2019Semantic Correlation Promoted Shape-Variant Context for Segmentationcited by 61
  20. 2015Semantic Image Segmentation with Task-Specific Edge Detection Using CNNs and a Discriminatively Trained Domain Transformcited by 46
  21. 2015Semantic Segmentation with Boundary Neural Fieldscited by 37
  22. 2015Pushing the Boundaries of Boundary Detection using Deep Learningcited by 35
  23. 2017BlitzNet: A Real-Time Deep Network for Scene Understandingcited by 29
  24. 2020Malleable 2.5D Convolution: Learning Receptive Fields along the Depth-axis for RGB-D Scene Parsingcited by 24
  25. 2017Recurrent Scene Parsing with Perspective Understanding in the Loopcited by 16
  26. 2019AETv2: AutoEncoding Transformations for Self-Supervised Representation Learning by Minimizing Geodesic Distances in Lie Groupscited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 5; 2022: 7; 2023: 29; 2024: 14; 2025: 7; 2026: 3.

65 papers.

Sort:

By area:

  1. 2024HUGS: Holistic Urban 3D Scene Understanding via Gaussian Splattingcited by 141
  2. 2023Delivering Arbitrary-Modal Semantic Segmentationcited by 115
  3. 2024HUGSIM: A Real-Time, Photo-Realistic and Closed-Loop Simulator for Autonomous Drivingcited by 84
  4. 2024Vivim: a Video Vision Mamba for Medical Video Segmentationcited by 51
  5. 2022X-Align: Cross-Modal Cross-View Alignment for Bird's-Eye-View Segmentationcited by 38
  6. 2023Loss Functions in the Era of Semantic Segmentation: A Survey and Outlookcited by 33
  7. 2023Semantic Diffusion Network for Semantic Segmentationcited by 30
  8. 2023X3KD: Knowledge Distillation Across Modalities, Tasks and Stages for Multi-Camera 3D Object Detectioncited by 28
  9. 2023Semantic Image Segmentation: Two Decades of Researchcited by 26
  10. 2021Fully Transformer Networks for Semantic Image Segmentationcited by 24
  11. 2021Semi-supervised Multi-task Learning for Semantics and Depthcited by 22
  12. 2024Open-World Semantic Segmentation Including Class Similaritycited by 22
38 more
  1. 2024Centering the Value of Every Modality: Towards Efficient and Resilient Modality-agnostic Semantic Segmentationcited by 21
  2. 2023Strong but simple: A Baseline for Domain Generalized Dense Perception by CLIP-based Transfer Learningcited by 20
  3. 20234D Panoptic Segmentation as Invariant and Equivariant Field Predictioncited by 19
  4. 2023Delving into Shape-aware Zero-shot Semantic Segmentationcited by 16
  5. 2023DistractFlow: Improving Optical Flow Estimation via Realistic Distractions and Pseudo-Labelingcited by 14
  6. 2023Pixel Difference Convolutional Network for RGB-D Semantic Segmentationcited by 13
  7. 2021X-Distill: Improving Self-Supervised Monocular Depth via Cross-Task Distillationcited by 12
  8. 2021HS3: Learning with Proper Task Complexity in Hierarchically Supervised Semantic Segmentationcited by 12
  9. 2024U3M: Unbiased Multiscale Modal Fusion Model for Multimodal Semantic Segmentationcited by 12
  10. 2024MAGIC++: Efficient and Resilient Modality-Agnostic Semantic Segmentation via Hierarchical Modality Selectioncited by 12
  11. 2025RealEngine: Simulating Autonomous Driving in Realistic Contextcited by 10
  12. 2022Panoptic, Instance and Semantic Relations: A Relational Context Encoder to Enhance Panoptic Segmentationcited by 9
  13. 2022Boosting Night-time Scene Parsing with Learnable Frequencycited by 9
  14. 2022DCANet: Differential Convolution Attention Network for RGB-D Semantic Segmentationcited by 9
  15. 2023DejaVu: Conditional Regenerative Learning to Enhance Dense Predictioncited by 9
  16. 2023SemARFlow: Injecting Semantics into Unsupervised Optical Flow Estimation for Autonomous Drivingcited by 9
  17. 2023Milestones in Autonomous Driving and Intelligent Vehicles Part II: Perception and Planningcited by 9
  18. 2024PosSAM: Panoptic Open-vocabulary Segment Anythingcited by 9
  19. 2024UrbanCAD: Towards Highly Controllable and Photorealistic 3D Vehicles for Urban Scene Simulationcited by 7
  20. 2025Training-Free Dataset Pruning for Instance Segmentationcited by 7
  21. 2022Multi-Task Learning for Visual Scene Understandingcited by 6
  22. 2022Contour-Aware Equipotential Learning for Semantic Segmentationcited by 6
  23. 2023When Multi-Task Learning Meets Partial Supervision: A Computer Vision Reviewcited by 6
  24. 2023ShareCMP: Polarization-Aware RGB-P Semantic Segmentationcited by 6
  25. 2024Part-Whole Relational Fusion Towards Multi-Modal Scene Understandingcited by 6
  26. 2023Soft labelling for semantic segmentation: Bringing coherence to label down-samplingcited by 5
  27. 2023Compensation Learning in Semantic Segmentationcited by 5
  28. 20243D-AVS: LiDAR-based 3D Auto-Vocabulary Segmentationcited by 5
  29. 2023Shape-Sensitive Loss for Catheter and Guidewire Segmentationcited by 4
  30. 2021Distribution Estimation to Automate Transformation Policies for Self-Supervisioncited by 3
  31. 2023ComPtr: Towards Diverse Bi-source Dense Prediction Tasks via A Simple yet General Complementary Transformercited by 3
  32. 2023Boosting Semantic Segmentation with Semantic Boundariescited by 2
  33. 2023Not All Pixels Are Equal: Learning Pixel Hardness for Semantic Segmentationcited by 2
  34. 2024Open-World Panoptic Segmentationcited by 2
  35. 2023OVeNet: Offset Vector Network for Semantic Segmentationcited by 1
  36. 2023Streaming Anchor Loss: Augmenting Supervision with Temporal Significancecited by 1
  37. 2025Steerable Pyramid Weighted Loss: Multi-Scale Adaptive Weighting for Semantic Segmentationcited by 1
  38. 2025EGFormer: Towards Efficient and Generalizable Multimodal Semantic Segmentationcited by 1

50 most cited of 65 All 65 (JSON)