English

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

Computer Vision and Pattern Recognition 2025-10-10 v4 Artificial Intelligence

Abstract

Instance segmentation demands costly per-pixel annotations and computationally expensive models. We introduce CAST, a semi-supervised knowledge distillation (SSKD) framework that compresses pre-trained 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(s) via self-training with contrastive calibration, (2) knowledge transfer through a unified multi-objective loss, and (3) student refinement to mitigate residual pseudo-label bias. Central to CAST is an \emph{instance-aware pixel-wise contrastive loss} that fuses mask and class scores to extract 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 improves over its zero-shot VFM teacher(s) by +8.5 and +7.1 AP, surpasses adapted teacher(s) by +3.4 and +1.5 AP, and further outperforms state-of-the-art SSKD methods on both benchmarks.

Keywords

Cite

@article{arxiv.2505.21904,
  title  = {CAST: Contrastive Adaptation and Distillation for Semi-Supervised Instance Segmentation},
  author = {Pardis Taghavi and Tian Liu and Renjie Li and Reza Langari and Zhengzhong Tu},
  journal= {arXiv preprint arXiv:2505.21904},
  year   = {2025}
}
R2 v1 2026-07-01T02:45:05.058Z