Region Rebalance for Long-Tailed Semantic Segmentation
Not on the map. Why?
Abstract (arXiv)
In this paper, we study the problem of class imbalance in semantic segmentation. We first investigate and identify the main challenges of addressing this issue through pixel rebalance. Then a simple and yet effective region rebalance scheme is derived based on our analysis. In our solution, pixel features belonging to the same class are grouped into region features, and a rebalanced region classifier is applied via an auxiliary region rebalance branch during training. To verify the flexibility and effectiveness of our method, we apply the region rebalance module into various semantic segmentation methods, such as Deeplabv3+, OCRNet, and Swin. Our strategy achieves consistent improvement on the challenging ADE20K and COCO-Stuff benchmark. In particular, with the proposed region rebalance scheme, state-of-the-art BEiT receives +0.7% gain in terms of mIoU on the ADE20K val set.
Key facts. Cited by 17 papers in the map (data through 7 Oct 2026). Builds on 48 of its 63 references that are in the map. First posted on arXiv 5 Apr 2022.
Builds on
48 of 63 references.
References · 48
- 2015Deep Residual Learning for Image Recognitioncited by 51,809
- 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
- 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
- 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
- 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
- 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
- 2017Mask R-CNNcited by 7,259
- 2016Feature Pyramid Networks for Object Detectioncited by 5,021
- 2014Fully Convolutional Networks for Semantic Segmentationcited by 4,845
- 2020Training data-efficient image transformers & distillation through attentioncited by 4,560
- 2014Going Deeper with Convolutionscited by 4,231
- 2016DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFscited by 3,239
36 more
- 2018Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentationcited by 3,210
- 2016Pyramid Scene Parsing Networkcited by 2,472
- 2021BEiT: BERT Pre-Training of Image Transformerscited by 2,360
- 2016V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentationcited by 2,284
- 2017Rethinking Atrous Convolution for Semantic Image Segmentationcited by 2,154
- 2015SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentationcited by 1,483
- 2019Deep High-Resolution Representation Learning for Visual Recognitioncited by 1,417
- 2018Unified Perceptual Parsing for Scene Understandingcited by 1,265
- 2019Class-Balanced Loss Based on Effective Number of Samplescited by 1,239
- 2019LVIS: A Dataset for Large Vocabulary Instance Segmentationcited by 1,215
- 2015Multi-Scale Context Aggregation by Dilated Convolutionscited by 1,128
- 2019Learning Imbalanced Datasets with Label-Distribution-Aware Margin Losscited by 987
- 2016COCO-Stuff: Thing and Stuff Classes in Contextcited by 858
- 2019Decoupling Representation and Classifier for Long-Tailed Recognitioncited by 806
- 2018Path Aggregation Network for Instance Segmentationcited by 796
- 2019Large-Scale Long-Tailed Recognition in an Open Worldcited by 704
- 2018Learning to Reweight Examples for Robust Deep Learningcited by 670
- 2019Segmentation Transformer: Object-Contextual Representations for Semantic Segmentationcited by 573
- 2014Semantic Image Segmentation with Deep Convolutional Nets and Fully Connected CRFscited by 552
- 2017A systematic study of the class imbalance problem in convolutional neural networkscited by 510
- 2016RefineNet: Multi-Path Refinement Networks for High-Resolution Semantic Segmentationcited by 463
- 2019BBN: Bilateral-Branch Network with Cumulative Learning for Long-Tailed Visual Recognitioncited by 403
- 2020Balanced Meta-Softmax for Long-Tailed Visual Recognitioncited by 397
- 2020Equalization Loss for Long-Tailed Object Recognitioncited by 285
- 2020Long-tailed Recognition by Routing Diverse Distribution-Aware Expertscited by 270
- 2020Long-Tailed Classification by Keeping the Good and Removing the Bad Momentum Causal Effectcited by 256
- 2018What is the Effect of Importance Weighting in Deep Learning?cited by 250
- 2021Parametric Contrastive Learningcited by 217
- 2021Improving Calibration for Long-Tailed Recognitioncited by 212
- 2020Overcoming Classifier Imbalance for Long-tail Object Detection with Balanced Group Softmaxcited by 152
- 2020Seesaw Loss for Long-Tailed Instance Segmentationcited by 146
- 2020Rethinking Class-Balanced Methods for Long-Tailed Visual Recognition from a Domain Adaptation Perspectivecited by 143
- 2015Relay Backpropagation for Effective Learning of Deep Convolutional Neural Networkscited by 115
- 2021ResLT: Residual Learning for Long-tailed Recognitioncited by 96
- 2018Deep Imbalanced Learning for Face Recognition and Attribute Predictioncited by 90
- 2016Full-Resolution Residual Networks for Semantic Segmentation in Street Scenescited by 71
Built on by
Citing papers per year: 2022: 3; 2023: 8; 2024: 1; 2025: 4; 2026: 1.
17 papers.
Sort:
By area:
- 2022Vision Transformer Adapter for Dense Predictionscited by 564
- 2023DDP: Diffusion Model for Dense Visual Predictioncited by 148
- 2023Hierarchical Dense Correlation Distillation for Few-Shot Segmentationcited by 84
- 2023Decoupled Kullback-Leibler Divergence Losscited by 58
- 2022Generalized Parametric Contrastive Learningcited by 45
- 2023Learning Context-aware Classifier for Semantic Segmentationcited by 23
- 2023HiLo: Exploiting High Low Frequency Relations for Unbiased Panoptic Scene Graph Generationcited by 19
- 2023Boosting Few-shot 3D Point Cloud Segmentation via Query-Guided Enhancementcited by 19
- 2025Generalized Kullback-Leibler Divergence Losscited by 6
- 2022Representation Separation for Semantic Segmentation with Vision Transformerscited by 4
- 2024Frequency-based Matcher for Long-tailed Semantic Segmentationcited by 3
- 2025Differentiable Hierarchical Visual Tokenizationcited by 3
5 more
- 2025SRMF: A Data Augmentation and Multimodal Fusion Approach for Long-Tail UHR Satellite Image Segmentationcited by 2
- 2023Hierarchical Dense Correlation Distillation for Few-Shot Segmentation-Extended Abstractcited by 0
- 2023MEDOE: A Multi-Expert Decoder and Output Ensemble Framework for Long-tailed Semantic Segmentationcited by 0
- 2025Diffusion-Based Image Augmentation for Semantic Segmentation in Outdoor Roboticscited by 0
- 2026Class-frequency Guided Noise Schedule for Diffusion Modelscited by 0
- 2026Class-frequency Guided Noise Schedule for Diffusion Models26 Jun 2026
- 2025Differentiable Hierarchical Visual Tokenization4 Nov 2025
- 2025Diffusion-Based Image Augmentation for Semantic Segmentation in Outdoor Robotics30 Jun 2025
- 2025SRMF: A Data Augmentation and Multimodal Fusion Approach for Long-Tail UHR Satellite Image Segmentation28 Apr 2025
- 2025Generalized Kullback-Leibler Divergence Loss11 Mar 2025
- 2024Frequency-based Matcher for Long-tailed Semantic Segmentation6 Jun 2024
- 2023MEDOE: A Multi-Expert Decoder and Output Ensemble Framework for Long-tailed Semantic Segmentation16 Aug 2023
- 2023Boosting Few-shot 3D Point Cloud Segmentation via Query-Guided Enhancement6 Aug 2023
- 2023Hierarchical Dense Correlation Distillation for Few-Shot Segmentation-Extended Abstract27 Jun 2023
- 2023Decoupled Kullback-Leibler Divergence Loss23 May 2023
- 2023DDP: Diffusion Model for Dense Visual Prediction30 Mar 2023
- 2023HiLo: Exploiting High Low Frequency Relations for Unbiased Panoptic Scene Graph Generation28 Mar 2023
5 more
- 2023Hierarchical Dense Correlation Distillation for Few-Shot Segmentation26 Mar 2023
- 2023Learning Context-aware Classifier for Semantic Segmentation21 Mar 2023
- 2022Representation Separation for Semantic Segmentation with Vision Transformers28 Dec 2022
- 2022Generalized Parametric Contrastive Learning26 Sep 2022
- 2022Vision Transformer Adapter for Dense Predictions17 May 2022
- 2022Vision Transformer Adapter for Dense Predictionscited by 564
- 2023Hierarchical Dense Correlation Distillation for Few-Shot Segmentationcited by 84
- 2023Decoupled Kullback-Leibler Divergence Losscited by 58
- 2022Generalized Parametric Contrastive Learningcited by 45
- 2023Learning Context-aware Classifier for Semantic Segmentationcited by 23
- 2023HiLo: Exploiting High Low Frequency Relations for Unbiased Panoptic Scene Graph Generationcited by 19
- 2023Boosting Few-shot 3D Point Cloud Segmentation via Query-Guided Enhancementcited by 19
- 2025Generalized Kullback-Leibler Divergence Losscited by 6
- 2022Representation Separation for Semantic Segmentation with Vision Transformerscited by 4
- 2024Frequency-based Matcher for Long-tailed Semantic Segmentationcited by 3
- 2025Differentiable Hierarchical Visual Tokenizationcited by 3
- 2025SRMF: A Data Augmentation and Multimodal Fusion Approach for Long-Tail UHR Satellite Image Segmentationcited by 2
12 most cited of 13 All 13 (JSON)
- 2025Differentiable Hierarchical Visual Tokenization4 Nov 2025
- 2025SRMF: A Data Augmentation and Multimodal Fusion Approach for Long-Tail UHR Satellite Image Segmentation28 Apr 2025
- 2025Generalized Kullback-Leibler Divergence Loss11 Mar 2025
- 2024Frequency-based Matcher for Long-tailed Semantic Segmentation6 Jun 2024
- 2023Boosting Few-shot 3D Point Cloud Segmentation via Query-Guided Enhancement6 Aug 2023
- 2023Hierarchical Dense Correlation Distillation for Few-Shot Segmentation-Extended Abstract27 Jun 2023
- 2023Decoupled Kullback-Leibler Divergence Loss23 May 2023
- 2023HiLo: Exploiting High Low Frequency Relations for Unbiased Panoptic Scene Graph Generation28 Mar 2023
- 2023Hierarchical Dense Correlation Distillation for Few-Shot Segmentation26 Mar 2023
- 2023Learning Context-aware Classifier for Semantic Segmentation21 Mar 2023
- 2022Representation Separation for Semantic Segmentation with Vision Transformers28 Dec 2022
- 2022Generalized Parametric Contrastive Learning26 Sep 2022
12 newest of 13 All 13 (JSON)