Training a Student Expert via Semi-Supervised Foundation Model Distillation

• URL: http://arxiv.org/abs/2604.03841v1
• Date: Sat, 04 Apr 2026 19:45:25 GMT
• Title: Training a Student Expert via Semi-Supervised Foundation Model Distillation
• Abstract summary: We introduce a semi-supervised knowledge distillation framework that compresses pre-trained vision foundation models into compact experts.<n>The framework 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.
• Score: 14.605642634292655
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Foundation models deliver strong perception but are often too computationally heavy to deploy, and adapting them typically requires costly annotations. We introduce a semi-supervised knowledge distillation (SSKD) framework that compresses pre-trained vision foundation models (VFMs) into compact experts using limited labeled and abundant unlabeled data, and instantiate it for instance segmentation where per-pixel labels are particularly expensive. The framework 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 our approach is an 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 more effectively leverage unlabeled images. On Cityscapes and ADE20K, our $\approx 11\times$ smaller student improves over its zero-shot VFM teacher(s) by +11.9 and +8.6 AP, surpasses adapted teacher(s) by +3.4 and +1.5 AP, and outperforms state-of-the-art SSKD methods on benchmarks.

Related papers

• LIFT and PLACE: A Simple, Stable, and Effective Knowledge Distillation Framework for Lightweight Diffusion Models [9.025382179940767]
  coarse-to-fine distillation framework with LInear FiTtingbased distillation (LIFT) and Piecewise Local Adaptive Coefficient Estimation (PLACE)<n>Experiments show LIFT and PLACE is effective across diffusion spaces (image/latent), backbones (U-Net/DiT), tasks (unconditional/conditional), datasets, and even extends to flow-based models such as MMDiT (SD3)
  arXiv  Detail & Related papers  (2026-05-19T12:03:53Z)
• Dual-Foundation Models for Unsupervised Domain Adaptation [2.279449016085348]
  Training segmentation models requires costly, labor-intensive annotations on real-world datasets.<n>Unsupervised Domain Adaptation (UDA) addresses this by training models on labeled synthetic data and adapting them to unlabeled real images.<n>We propose a dual-foundation UDA framework that leverages two complementary foundation models.
  arXiv  Detail & Related papers  (2026-05-05T04:52:08Z)
• Rethinking Long-tailed Dataset Distillation: A Uni-Level Framework with Unbiased Recovery and Relabeling [105.8570596633629]
  We rethink long-tailed dataset distillation by revisiting the limitations of trajectory-based methods.<n>We adopt the statistical alignment perspective to jointly model bias and restore fair supervision.<n>Our approach improves top-1 accuracy by 15.6% on CIFAR-100-LT and 11.8% on Tiny-ImageNet-LT.
  arXiv  Detail & Related papers  (2025-11-24T07:57:01Z)
• CAST: Contrastive Adaptation and Distillation for Semi-Supervised Instance Segmentation [14.605642634292655]
  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.<n>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.
  arXiv  Detail & Related papers  (2025-05-28T02:45:42Z)
• TinyR1-32B-Preview: Boosting Accuracy with Branch-Merge Distillation [19.938309176933902]
  We introduce the Branch-Merge distillation approach, which enhances model compression through two phases.<n>We validate our distillation approach using DeepSeek-R1 as the teacher and DeepSeek-R1-Distill-Qwen-32B as the student.<n>The resulting merged model, TinyR1-32B-Preview, outperforms its counterpart DeepSeek-R1-Distill-Qwen-32B across multiple benchmarks.
  arXiv  Detail & Related papers  (2025-03-06T16:25:53Z)
• Fine-grained Image-to-LiDAR Contrastive Distillation with Visual Foundation Models [55.99654128127689]
  Visual Foundation Models (VFMs) are used to generate semantic labels for weakly-supervised pixel-to-point contrastive distillation.<n>We adapt sampling probabilities of points to address imbalances in spatial distribution and category frequency.<n>Our approach consistently surpasses existing image-to-LiDAR contrastive distillation methods in downstream tasks.
  arXiv  Detail & Related papers  (2024-05-23T07:48:19Z)
• 2D Feature Distillation for Weakly- and Semi-Supervised 3D Semantic Segmentation [92.17700318483745]
  We propose an image-guidance network (IGNet) which builds upon the idea of distilling high level feature information from a domain adapted synthetically trained 2D semantic segmentation network. IGNet achieves state-of-the-art results for weakly-supervised LiDAR semantic segmentation on ScribbleKITTI, boasting up to 98% relative performance to fully supervised training with only 8% labeled points.
  arXiv  Detail & Related papers  (2023-11-27T07:57:29Z)
• Deep Semi-supervised Knowledge Distillation for Overlapping Cervical Cell Instance Segmentation [54.49894381464853]
  We propose to leverage both labeled and unlabeled data for instance segmentation with improved accuracy by knowledge distillation. We propose a novel Mask-guided Mean Teacher framework with Perturbation-sensitive Sample Mining. Experiments show that the proposed method improves the performance significantly compared with the supervised method learned from labeled data only.
  arXiv  Detail & Related papers  (2020-07-21T13:27:09Z)
• Distilling Object Detectors with Task Adaptive Regularization [97.52935611385179]
  Current state-of-the-art object detectors are at the expense of high computational costs and are hard to deploy to low-end devices. Knowledge distillation, which aims at training a smaller student network by transferring knowledge from a larger teacher model, is one of the promising solutions for model miniaturization.
  arXiv  Detail & Related papers  (2020-06-23T15:58:22Z)
• Un-Mix: Rethinking Image Mixtures for Unsupervised Visual Representation Learning [108.999497144296]
  Recently advanced unsupervised learning approaches use the siamese-like framework to compare two "views" from the same image for learning representations. This work aims to involve the distance concept on label space in the unsupervised learning and let the model be aware of the soft degree of similarity between positive or negative pairs. Despite its conceptual simplicity, we show empirically that with the solution -- Unsupervised image mixtures (Un-Mix), we can learn subtler, more robust and generalized representations from the transformed input and corresponding new label space.
  arXiv  Detail & Related papers  (2020-03-11T17:59:04Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.