S^4M: Boosting Semi-Supervised Instance Segmentation with SAM
Semi-supervised instance segmentation poses challenges due to limited labeled data, causing difficulties in accurately localizing distinct object instances. Current teacher-student frameworks still suffer from performance constraints due to unreliable pseudo-label quality stemming from limited labeled data. While the Segment Anything Model (SAM) offers robust segmentation capabilities at various granularities, directly applying SAM to this task introduces challenges such as class-agnostic predictions and potential over-segmentation. To address these complexities, we carefully integrate SAM into the semi-supervised instance segmentation framework, developing a novel distillation method that effectively captures the precise localization capabilities of SAM without compromising semantic recognition. Furthermore, we incorporate pseudo-label refinement as well as a specialized data augmentation with the refined pseudo-labels, resulting in superior performance. We establish state-of-the-art performance, and provide comprehensive experiments and ablation studies to validate the effectiveness of our proposed approach.
Code (0)
등록된 구현이 없습니다.
Tasks
Data AugmentationInstance SegmentationPseudo LabelSegmentationSemantic SegmentationSemi-Supervised Instance SegmentationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Semi-supervised Semantic Segmentation via Boosting Uncertainty on Unlabeled Data
We bring a new perspective to semi-supervised semantic segmentation by providing an analysis on the labeled and unlabeled distributions in training datasets. We first figure out that the distribution gap between labeled …
SegmentationSemantic SegmentationSemi-Supervised Semantic SegmentationBoosting Overlapping Organoid Instance Segmentation Using Pseudo-Label Unmixing and Synthesis-Assisted Learning
Organoids, sophisticated in vitro models of human tissues, are crucial for medical research due to their ability to simulate organ functions and assess drug responses accurately. Accurate organoid instance segmentation i…
Semi-Supervised Semantic SegmentationInstance SegmentationConsInstancy: Learning Instance Representations for Semi-Supervised Panoptic Segmentation of Concrete Aggregate Particles
We present a semi-supervised method for panoptic segmentation based on ConsInstancy regularisation, a novel strategy for semi-supervised learning. It leverages completely unlabelled data by enforcing consistency between …
Panoptic SegmentationSegmentationInstance Consistency Regularization for Semi-Supervised 3D Instance Segmentation
Large-scale datasets with point-wise semantic and instance labels are crucial to 3D instance segmentation but also expensive. To leverage unlabeled data, previous semi-supervised 3D instance segmentation approaches have …
3D Instance SegmentationInstance SegmentationSegmentationSemantic SegmentationPseudo-label Alignment for Semi-supervised Instance Segmentation
Pseudo-labeling is significant for semi-supervised instance segmentation, which generates instance masks and classes from unannotated images for subsequent training. However, in existing pipelines, pseudo-labels that con…
Instance SegmentationPseudo LabelSegmentationSemantic Segmentation+1