DHR: Dual Features-Driven Hierarchical Rebalancing in Inter- and Intra-Class Regions for Weakly-Supervised Semantic Segmentation
Not on the map. Why?
Abstract (arXiv)
Weakly-supervised semantic segmentation (WSS) ensures high-quality segmentation with limited data and excels when employed as input seed masks for large-scale vision models such as Segment Anything. However, WSS faces challenges related to minor classes since those are overlooked in images with adjacent multiple classes, a limitation originating from the overfitting of traditional expansion methods like Random Walk. We first address this by employing unsupervised and weakly-supervised feature maps instead of conventional methodologies, allowing for hierarchical mask enhancement. This method distinctly categorizes higher-level classes and subsequently separates their associated lower-level classes, ensuring all classes are correctly restored in the mask without losing minor ones. Our approach, validated through extensive experimentation, significantly improves WSS across five benchmarks (VOC: 79.8%, COCO: 53.9%, Context: 49.0%, ADE: 32.9%, Stuff: 37.4%), reducing the gap with fully supervised methods by over 84% on the VOC validation set. Code is available at https://github.com/shjo-april/DHR.
Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Builds on 69 of its 85 references that are in the map. First posted on arXiv 30 Mar 2024.
Builds on
69 of 85 references.
References · 69
- 2015Deep Residual Learning for Image Recognitioncited by 52,096
- 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
- 2014Microsoft COCO: Common Objects in Contextcited by 17,608
- 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,139
- 2023Segment Anythingcited by 8,234
- 2023DINOv2: Learning Robust Visual Features without Supervisioncited by 7,974
- 2021Emerging Properties in Self-Supervised Vision Transformerscited by 6,968
- 2023Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detectioncited by 3,332
- 2016DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFscited by 3,241
- 2018Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentationcited by 3,223
- 2021Masked-attention Mask Transformer for Universal Image Segmentationcited by 2,351
- 2016Semantic Understanding of Scenes through the ADE20K Datasetcited by 1,069
38 more
- 2024Grounded SAM: Assembling Open-World Models for Diverse Visual Taskscited by 929
- 2016COCO-Stuff: Thing and Stuff Classes in Contextcited by 864
- 2021Extract Free Dense Labels from CLIPcited by 583
- 2023Ferret: Refer and Ground Anything Anywhere at Any Granularitycited by 509
- 2018Invariant Information Clustering for Unsupervised Image Classification and Segmentationcited by 455
- 2023Segment Anything in High Qualitycited by 376
- 2018Learning Pixel-level Semantic Affinity with Image-level Supervision for Weakly Supervised Semantic Segmentationcited by 321
- 2020Self-supervised Equivariant Attention Mechanism for Weakly Supervised Semantic Segmentationcited by 300
- 2020Contrastive Clusteringcited by 265
- 2019Weakly Supervised Learning of Instance Segmentation with Inter-pixel Relationscited by 247
- 2022Unsupervised Semantic Segmentation by Distilling Feature Correspondencescited by 241
- 2016Seed, Expand and Constrain: Three Principles for Weakly-Supervised Image Segmentationcited by 198
- 2016Deeply supervised salient object detection with short connectionscited by 196
- 2015Weakly- and Semi-Supervised Learning of a DCNN for Semantic Image Segmentationcited by 189
- 2020Single-Stage Semantic Segmentation from Image Labelscited by 167
- 2021PiCIE: Unsupervised Semantic Segmentation using Invariance and Equivariance in Clusteringcited by 163
- 2019FickleNet: Weakly and Semi-supervised Semantic Image Segmentation using Stochastic Inferencecited by 162
- 2020Mining Cross-Image Semantics for Weakly Supervised Semantic Segmentationcited by 144
- 2022Multi-class Token Transformer for Weakly Supervised Semantic Segmentationcited by 138
- 2021Anti-Adversarially Manipulated Attributions for Weakly and Semi-Supervised Semantic Segmentationcited by 134
- 2022Learning to Generate Text-grounded Mask for Open-world Semantic Segmentation from Only Image-Text Pairscited by 130
- 2021Railroad is not a Train: Saliency as Pseudo-pixel Supervision for Weakly Supervised Semantic Segmentationcited by 127
- 2022Learning Affinity from Attention: End-to-End Weakly-Supervised Semantic Segmentation with Transformerscited by 118
- 2022CLIP is Also an Efficient Segmenter: A Text-Driven Approach for Weakly Supervised Semantic Segmentationcited by 118
- 2022Self-Supervised Learning of Object Parts for Semantic Segmentationcited by 90
- 2019Reliability Does Matter: An End-to-End Weakly Supervised Semantic Segmentation Approachcited by 88
- 2022Self-supervised Image-specific Prototype Exploration for Weakly Supervised Semantic Segmentationcited by 87
- 2021Weakly Supervised Semantic Segmentation by Pixel-to-Prototype Contrastcited by 85
- 2018CIAN: Cross-Image Affinity Net for Weakly Supervised Semantic Segmentationcited by 80
- 2021Complementary Patch for Weakly Supervised Semantic Segmentationcited by 75
- 2022Class Re-Activation Maps for Weakly-Supervised Semantic Segmentationcited by 75
- 2021Reducing Information Bottleneck for Weakly Supervised Semantic Segmentationcited by 65
- 2023Token Contrast for Weakly-Supervised Semantic Segmentationcited by 65
- 2022Regional Semantic Contrast and Aggregation for Weakly Supervised Semantic Segmentationcited by 64
- 2021Adaptive Early-Learning Correction for Segmentation from Noisy Annotationscited by 62
- 2020Autoregressive Unsupervised Image Segmentationcited by 60
- 2019Self-Supervised Difference Detection for Weakly-Supervised Semantic Segmentationcited by 58
- 2022Weakly Supervised Semantic Segmentation using Out-of-Distribution Datacited by 58
50 most cited of 69 All 69 (JSON)
Built on by
Citing papers per year: 2025: 2; 2026: 1.
3 papers.