CAST: Contrastive Adaptation and Distillation for Semi-Supervised Instance Segmentation
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866911199173541888 |
|---|---|
| author | Taghavi, Pardis Liu, Tian Li, Renjie Langari, Reza Tu, Zhengzhong |
| author_facet | Taghavi, Pardis Liu, Tian Li, Renjie Langari, Reza Tu, Zhengzhong |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_21904 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | CAST: Contrastive Adaptation and Distillation for Semi-Supervised Instance Segmentation Taghavi, Pardis Liu, Tian Li, Renjie Langari, Reza Tu, Zhengzhong Computer Vision and Pattern Recognition Artificial Intelligence 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. |
| title | CAST: Contrastive Adaptation and Distillation for Semi-Supervised Instance Segmentation |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2505.21904 |