Semi-Supervised Confidence-Level-based Contrastive Discrimination for Class-Imbalanced Semantic Segmentation
To overcome the data-hungry challenge, we have proposed a semi-supervised contrastive learning framework for the task of class-imbalanced semantic segmentation. First and foremost, to make the model operate in a semi-supervised manner, we proposed the confidence-level-based contrastive learning to achieve instance discrimination in an explicit manner, and make the low-confidence low-quality features align with the high-confidence counterparts. Moreover, to tackle the problem of class imbalance in crack segmentation and road components extraction, we proposed the data imbalance loss to replace the traditional cross entropy loss in pixel-level semantic segmentation. Finally, we have also proposed an effective multi-stage fusion network architecture to improve semantic segmentation performance. Extensive experiments on the real industrial crack segmentation and the road segmentation demonstrate the superior effectiveness of the proposed framework. Our proposed method can provide satisfactory segmentation results with even merely 3.5% labeled data.
Code (1)
Tasks
Contrastive LearningRoad SegmentationSegmentationSemantic SegmentationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Low-confidence Samples Matter for Domain Adaptation
Domain adaptation (DA) aims to transfer knowledge from a label-rich source domain to a related but label-scarce target domain. The conventional DA strategy is to align the feature distributions of the two domains. Recent…
Contrastive LearningDomain AdaptationSemi-supervised Contrastive Outlier removal for Pseudo Expectation Maximization (SCOPE)
Semi-supervised learning is the problem of training an accurate predictive model by combining a small labeled dataset with a presumably much larger unlabeled dataset. Many methods for semi-supervised deep learning have b…
Contrastive LearningImproving Semi-Supervised Contrastive Learning via Entropy-Weighted Confidence Integration of Anchor-Positive Pairs
Conventional semi-supervised contrastive learning methods assign pseudo-labels only to samples whose highest predicted class probability exceeds a predefined threshold, and then perform supervised contrastive learning us…
Contrastive LearningTowards Semi-Supervised Deep Facial Expression Recognition with An Adaptive Confidence Margin
Only parts of unlabeled data are selected to train models for most semi-supervised learning methods, whose confidence scores are usually higher than the pre-defined threshold (i.e., the confidence margin). We argue that …
Facial Expression RecognitionFacial Expression Recognition (FER)Distribution-Aware Robust Learning from Long-Tailed Data with Noisy Labels
Deep neural networks have demonstrated remarkable advancements in various fields using large, well-annotated datasets. However, real-world data often exhibit long-tailed distributions and label noise, significantly degra…
Contrastive Learning