# Co-STAR: Collaborative Curriculum Self-Training with Adaptive Regularization for Source-Free Video Domain Adaptation

arXiv: https://arxiv.org/abs/2504.11669 · HTML: https://mlsanity.com/paper/2504.11669/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in Prompt learning and adaptation of CLIP, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 39 of its 61 references that are in the map.
- First posted on arXiv 15 Apr 2025.

## Placed in

- Multimodal LLMs / vision-language models / [Prompt learning and adaptation of CLIP](https://mlsanity.com/mllm/prompt-learning-and-adaptation-of-clip/)
- Synthetic data and self-improvement for LLMs / [Self-improving MLLMs and synthetic data](https://mlsanity.com/synth/self-improving-mllms-and-synthetic-data/)

## Builds on (most cited first, 30 of 39)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [The Kinetics Human Action Video Dataset](https://mlsanity.com/paper/1705.06950/) (2017)
- [Do We Really Need to Access the Source Data? Source Hypothesis Transfer for Unsupervised Domain Adaptation](https://mlsanity.com/paper/2002.08546/) (2020)
- [A Survey on Visual Transformer](https://mlsanity.com/paper/2012.12556/) (2020)
- [VideoCLIP: Contrastive Pre-training for Zero-shot Video-Text Understanding](https://mlsanity.com/paper/2109.14084/) (2021)
- [Convolutional Two-Stream Network Fusion for Video Action Recognition](https://mlsanity.com/paper/1604.06573/) (2016)
- [Temporal Relational Reasoning in Videos](https://mlsanity.com/paper/1711.08496/) (2017)
- [ActionCLIP: A New Paradigm for Video Action Recognition](https://mlsanity.com/paper/2109.08472/) (2021)
- [On The Power of Curriculum Learning in Training Deep Networks](https://mlsanity.com/paper/1904.03626/) (2019)
- [Moments in Time Dataset: one million videos for event understanding](https://mlsanity.com/paper/1801.03150/) (2018)
- [Source Data-absent Unsupervised Domain Adaptation through Hypothesis Transfer and Labeling Transfer](https://mlsanity.com/paper/2012.07297/) (2020)
- [ST3D: Self-training for Unsupervised Domain Adaptation on 3D Object Detection](https://mlsanity.com/paper/2103.05346/) (2021)
- [Source-free Domain Adaptation via Avatar Prototype Generation and Adaptation](https://mlsanity.com/paper/2106.15326/) (2021)
- [When Do Curricula Work?](https://mlsanity.com/paper/2012.03107/) (2020)
- [Constructing Self-motivated Pyramid Curriculums for Cross-Domain Semantic Segmentation: A Non-Adversarial Approach](https://mlsanity.com/paper/1908.09547/) (2019)
- [Temporal Attentive Alignment for Large-Scale Video Domain Adaptation](https://mlsanity.com/paper/1907.12743/) (2019)
- [Domain Adaptation without Source Data](https://mlsanity.com/paper/2007.01524/) (2020)
- [Source-Free Unsupervised Domain Adaptation: A Survey](https://mlsanity.com/paper/2301.00265/) (2022)
- [Revisiting Classifier: Transferring Vision-Language Models for Video Recognition](https://mlsanity.com/paper/2207.01297/) (2022)
- [A Balanced and Uncertainty-aware Approach for Partial Domain Adaptation](https://mlsanity.com/paper/2003.02541/) (2020)
- [C-SFDA: A Curriculum Learning Aided Self-Training Framework for Efficient Source Free Domain Adaptation](https://mlsanity.com/paper/2303.17132/) (2023)
- [Contrast and Mix: Temporal Contrastive Video Domain Adaptation with Background Mixing](https://mlsanity.com/paper/2110.15128/) (2021)
- [Pseudo-Labeling Curriculum for Unsupervised Domain Adaptation](https://mlsanity.com/paper/1908.00262/) (2019)
- [A Curriculum Domain Adaptation Approach to the Semantic Segmentation of Urban Scenes](https://mlsanity.com/paper/1812.09953/) (2018)
- [ARID: A New Dataset for Recognizing Action in the Dark](https://mlsanity.com/paper/2006.03876/) (2020)
- [Uncertainty-guided Model Generalization to Unseen Domains](https://mlsanity.com/paper/2103.07531/) (2021)
- [Curriculum Graph Co-Teaching for Multi-Target Domain Adaptation](https://mlsanity.com/paper/2104.00808/) (2021)
- [Model Adaptation: Unsupervised Domain Adaptation without Source Data](https://mlsanity.com/paper/2502.19316/) (2025)

## Built on by (most cited first, 2 of 2)

- [Hierarchical Bayesian Framework for Multisource Domain Adaptation](https://mlsanity.com/paper/2512.18553/) (2025)
- [Return of Frustratingly Easy Unsupervised Video Domain Adaptation](https://mlsanity.com/paper/2605.19510/) (2026)

## Abstract (arXiv)

Recent advances in Source-Free Unsupervised Video Domain Adaptation (SFUVDA) leverage vision-language models to enhance pseudo-label generation. However, challenges such as noisy pseudo-labels and over-confident predictions limit their effectiveness in adapting well across domains. We propose Co-STAR, a novel framework that integrates curriculum learning with collaborative self-training between a source-trained teacher and a contrastive vision-language model (CLIP). Our curriculum learning approach employs a reliability-based weight function that measures bidirectional prediction alignment between the teacher and CLIP, balancing between confident and uncertain predictions. This function preserves uncertainty for difficult samples, while prioritizing reliable pseudo-labels when the predictions from both models closely align. To further improve adaptation, we propose Adaptive Curriculum Regularization, which modifies the learning priority of samples in a probabilistic, adaptive manner based on their confidence scores and prediction stability, mitigating overfitting to noisy and over-confident samples. Extensive experiments across multiple video domain adaptation benchmarks demonstrate that Co-STAR consistently outperforms state-of-the-art SFUVDA methods. Code is available at: https://github.com/Plrbear/Co-Star