用少量标注数据让小模型超越大模型，实现高效实例分割。
CAST: Contrastive Adaptation and Distillation for Semi-Supervised Instance Segmentation
- 通过对比学习融合掩码与类别得分，增强负样本信息。
- 在城市场景和室内场景数据集上，小模型性能超教师模型8.5和7.1点AP。
- 适合资源受限场景下部署高精度实例分割模型的开发者。
实例分割需要昂贵的像素级标注和计算开销大的模型。我们提出CAST，一种半监督知识蒸馏框架，利用少量标注数据和大量未标注数据，将预训练视觉基础模型（VFM）压缩为轻量级专家模型。CAST分为三个阶段：(1) 通过带有对比校准的自训练对VFM进行领域适应；(2) 通过统一多目标损失实现知识迁移；(3) 学生模型优化以缓解残留伪标签偏差。核心是实例感知的像素级对比损失，融合掩码与类别分数，提取有信息量的负样本并强化实例间边界。通过在适应与蒸馏中保持对比信号，实现师生嵌入对齐，并充分挖掘未标注图像。在Cityscapes和ADE20K数据集上，我们的约11倍更小的学生模型相比零样本教师模型分别提升+8.5和+7.1 AP，超过适配后的教师模型+3.4和+1.5 AP，且优于当前最优半监督知识蒸馏方法。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。