Papers › CAST: Contrastive Adaptation and Distillation for Semi-Supervised Instance Segmentation

CAST: Contrastive Adaptation and Distillation for Semi-Supervised Instance Segmentation

28 May 2025arXiv:2505.21904archive 2025-07-28

Pardis Taghavi, Tian Liu, Renjie Li, Reza Langari, Zhengzhong Tu

Instance segmentation demands costly per-pixel annotations and large models. We introduce CAST, a semi-supervised knowledge distillation (SSKD) framework that compresses pretrained vision foundation models (VFM) into compact experts using limited labeled and abundant unlabeled data. CAST unfolds in three stages: (1) domain adaptation of the VFM teacher(s) via self-training with contrastive pixel calibration, (2) distillation into a compact student via a unified multi-objective loss that couples standard supervision and pseudo-labels with our instance-aware pixel-wise contrastive term, and (3) fine-tuning on labeled data to remove residual pseudo-label bias. Central to CAST is an \emph{instance-aware pixel-wise contrastive loss} that fuses mask and class scores to mine informative negatives and enforce clear inter-instance margins. By maintaining this contrastive signal across both adaptation and distillation, we align teacher and student embeddings and fully leverage unlabeled images. On Cityscapes and ADE20K, our ~11X smaller student surpasses its adapted VFM teacher(s) by +3.4 AP (33.9 vs. 30.5) and +1.5 AP (16.7 vs. 15.2) and outperforms state-of-the-art semi-supervised approaches.

PaperPDF

Code

No code repository is listed for this paper in the archive or in Syntology's graph.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Domain AdaptationInstance SegmentationKnowledge DistillationPseudo LabelSemantic SegmentationSemi-Supervised Instance Segmentation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Instance Segmentation Cityscapes CAST AP 33.9 #1 of 1 Archive leaderboard report
Knowledge Distillation Cityscapes CAST AP 33.9 #1 of 1 Archive leaderboard report
Semi-Supervised Instance Segmentation ADE20K CAST AP 16.7 #1 of 1 Archive leaderboard report
Semi-Supervised Instance Segmentation Cityscapes CAST AP 33.9 #1 of 1 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

ALIGNKnowledge Distillation

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections