Knowledge Consultation for Semi-Supervised Semantic Segmentation
Not on the map. Why?
Abstract (arXiv)
Semi-Supervised Semantic Segmentation reduces reliance on extensive annotations by using unlabeled data and state-of-the-art models to improve overall performance. Despite the success of deep co-training methods, their underlying mechanisms remain underexplored. This work revisits Cross Pseudo Supervision with dual heterogeneous backbones and introduces Knowledge Consultation (SegKC) to further enhance segmentation performance. The proposed SegKC achieves significant improvements on Pascal and Cityscapes benchmarks, with mIoU scores of 87.1%, 89.2%, and 89.8% on Pascal VOC with the 1/4, 1/2, and full split partition, respectively, while maintaining a compact model architecture.
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 45 of its 68 references that are in the map. First posted on arXiv 12 Mar 2025.
Builds on
45 of 68 references.
References · 45
- 2016The Cityscapes Dataset for Semantic Urban Scene Understandingcited by 4,444
- 2019CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Featurescited by 2,884
- 2020FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidencecited by 2,085
- 2021Vision Transformers for Dense Predictioncited by 1,803
- 2020Knowledge Distillation: A Surveycited by 1,603
- 2019MixMatch: A Holistic Approach to Semi-Supervised Learningcited by 1,391
- 2019Self-training with Noisy Student improves ImageNet classificationcited by 1,311
- 2021FlexMatch: Boosting Semi-Supervised Learning with Curriculum Pseudo Labelingcited by 540
- 2019On the Efficacy of Knowledge Distillationcited by 381
- 2020Semi-Supervised Semantic Segmentation with Cross-Consistency Trainingcited by 376
- 2020Meta Pseudo Labelscited by 374
- 2020Rethinking Pre-training and Self-trainingcited by 352
33 more
- 2019ReMixMatch: Semi-Supervised Learning with Distribution Alignment and Augmentation Anchoringcited by 349
- 2022FreeMatch: Self-adaptive Thresholding for Semi-supervised Learningcited by 232
- 2022Semi-Supervised Semantic Segmentation Using Unreliable Pseudo-Labelscited by 218
- 2020ClassMix: Segmentation-Based Data Augmentation for Semi-Supervised Learningcited by 209
- 2021ST++: Make Self-training Work Better for Semi-supervised Semantic Segmentationcited by 184
- 2022Revisiting Weak-to-Strong Consistency in Semi-Supervised Semantic Segmentationcited by 178
- 2022SimMatch: Semi-supervised Learning with Similarity Matchingcited by 118
- 2021Humble Teachers Teach Better Students for Semi-Supervised Object Detectioncited by 116
- 2019Dual Student: Breaking the Limits of the Teacher in Semi-supervised Learningcited by 104
- 2021SimCVD: Simple Contrastive Voxel-Wise Representation Distillation for Semi-Supervised Medical Image Segmentationcited by 86
- 2021Open-Vocabulary Instance Segmentation via Robust Cross-Modal Pseudo-Labelingcited by 84
- 2022Learning with Limited Annotations: A Survey on Deep Semi-Supervised Learning for Medical Image Segmentationcited by 76
- 2022Augmentation Matters: A Simple-yet-Effective Approach to Semi-supervised Semantic Segmentationcited by 64
- 2024UniMatch V2: Pushing the Limit of Semi-Supervised Semantic Segmentationcited by 54
- 2018Universal Semi-Supervised Semantic Segmentationcited by 50
- 2022Semi-supervised Semantic Segmentation with Prototype-based Consistency Regularizationcited by 50
- 2023CorrMatch: Label Propagation via Correlation Matching for Semi-Supervised Semantic Segmentationcited by 44
- 2023Active Teacher for Semi-Supervised Object Detectioncited by 43
- 2023SemiVL: Semi-Supervised Semantic Segmentation with Vision-Language Guidancecited by 41
- 2019Understanding Deep Learning Techniques for Image Segmentationcited by 38
- 2023Conflict-Based Cross-View Consistency for Semi-Supervised Semantic Segmentationcited by 35
- 2024AllSpark: Reborn Labeled Features from Unlabeled in Transformer for Semi-Supervised Semantic Segmentationcited by 35
- 2020Semi-supervised few-shot learning for medical image segmentationcited by 34
- 2023Semi-Supervised Semantic Segmentation via Gentle Teaching Assistantcited by 34
- 2023RCPS: Rectified Contrastive Pseudo Supervision for Semi-Supervised Medical Image Segmentationcited by 27
- 2023Diverse Cotraining Makes Strong Semi-Supervised Segmentorcited by 26
- 2024Towards the Uncharted: Density-Descending Feature Perturbation for Semi-supervised Semantic Segmentationcited by 16
- 2022Semi-supervised Semantic Segmentation with Mutual Knowledge Distillationcited by 12
- 2024Beyond Pixels: Semi-Supervised Semantic Segmentation with a Multi-scale Patch-based Multi-Label Classifiercited by 12
- 2023Semi-Supervised Semantic Segmentation via Marginal Contextual Informationcited by 8
- 2023SequenceMatch: Revisiting the design of weak-strong augmentations for Semi-supervised learningcited by 8
- 2023OTMatch: Improving Semi-Supervised Learning with Optimal Transportcited by 6
- 2022Dense FixMatch: a simple semi-supervised learning method for pixel-wise prediction taskscited by 4
Built on by
Citing papers per year: 2025: 1.
1 paper.