Weakly Supervised Semantic Segmentation via Alternative Self-Dual Teaching
Current weakly supervised semantic segmentation (WSSS) frameworks usually contain the separated mask-refinement model and the main semantic region mining model. These approaches would contain redundant feature extraction backbones and biased learning objectives, making them computational complex yet sub-optimal to addressing the WSSS task. To solve this problem, this paper establishes a compact learning framework that embeds the classification and mask-refinement components into a unified deep model. With the shared feature extraction backbone, our model is able to facilitate knowledge sharing between the two components while preserving a low computational complexity. To encourage high-quality knowledge interaction, we propose a novel alternative self-dual teaching (ASDT) mechanism. Unlike the conventional distillation strategy, the knowledge of the two teacher branches in our model is alternatively distilled to the student branch by a Pulse Width Modulation (PWM), which generates PW wave-like selection signal to guide the knowledge distillation process. In this way, the student branch can help prevent the model from falling into local minimum solutions caused by the imperfect knowledge provided of either teacher branch. Comprehensive experiments on the PASCAL VOC 2012 and COCO-Stuff 10K demonstrate the effectiveness of the proposed alternative self-dual teaching mechanism as well as the new state-of-the-art performance of our approach.
Code (0)
등록된 구현이 없습니다.
Tasks
Knowledge DistillationSemantic SegmentationWeakly supervised Semantic SegmentationWeakly-Supervised Semantic SegmentationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Generating Self-Guided Dense Annotations for Weakly Supervised Semantic Segmentation
Learning semantic segmentation models under image-level supervision is far more challenging than under fully supervised setting. Without knowing the exact pixel-label correspondence, most weakly-supervised methods rely o…
SegmentationSemantic SegmentationWeakly supervised Semantic SegmentationWeakly-Supervised Semantic SegmentationSelf-supervised Scale Equivariant Network for Weakly Supervised Semantic Segmentation
Weakly supervised semantic segmentation has attracted much research interest in recent years considering its advantage of low labeling cost. Most of the advanced algorithms follow the design principle that expands and co…
SegmentationSemantic SegmentationWeakly-supervised LearningWeakly supervised Semantic Segmentation+1Perturbed Self-Distillation: Weakly Supervised Large-Scale Point Cloud Semantic Segmentation
Large-scale point cloud semantic segmentation has wide applications. Current popular researches mainly focus on fully supervised learning which demands expensive and tedious manual point-wise annotation. Weakly super…
Self-Supervised LearningSemantic SegmentationWeakly-supervised LearningDBGroup: Dual-Branch Point Grouping for Weakly Supervised 3D Semantic Instance Segmentation
Weakly supervised 3D instance segmentation is essential for 3D scene understanding, especially as the growing scale of data and high annotation costs associated with fully supervised approaches. Existing methods primaril…
3D Semantic Instance Segmentation3D Semantic Segmentation3D Instance SegmentationScene UnderstandingSelf-Supervised Difference Detection for Weakly-Supervised Semantic Segmentation
To minimize the annotation costs associated with the training of semantic segmentation models, researchers have extensively investigated weakly-supervised segmentation approaches. In the current weakly-supervised segment…
SegmentationSemantic SegmentationWeakly supervised segmentationWeakly supervised Semantic Segmentation+1