# Semi-Supervised Adaptation of Vision-Language Models for Image Classification

arXiv: https://arxiv.org/abs/2608.25485 · HTML: https://mlsanity.com/paper/2608.25485/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Embodied and 3D vision-language models, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 10 of its 16 references that are in the map.
- First posted on arXiv 26 Aug 2026.

## Placed in

- Multimodal LLMs / vision-language models / [Embodied and 3D vision-language models](https://mlsanity.com/mllm/embodied-and-3d-vision-language-models/)

## Builds on (most cited first, 10 of 10)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Remote Sensing Image Scene Classification: Benchmark and State of the Art](https://mlsanity.com/paper/1703.00121/) (2017)
- [FlexMatch: Boosting Semi-Supervised Learning with Curriculum Pseudo Labeling](https://mlsanity.com/paper/2110.08263/) (2021)
- [FreeMatch: Self-adaptive Thresholding for Semi-supervised Learning](https://mlsanity.com/paper/2205.07246/) (2022)
- [SoftMatch: Addressing the Quantity-Quality Trade-off in Semi-supervised Learning](https://mlsanity.com/paper/2301.10921/) (2023)
- [CLIP-Powered Domain Generalization and Domain Adaptation: A Comprehensive Survey](https://mlsanity.com/paper/2504.14280/) (2025)
- [MSMatch: Semi-Supervised Multispectral Scene Classification with Few Labels](https://mlsanity.com/paper/2103.10368/) (2021)
- [Self Adaptive Threshold Pseudo-labeling and Unreliable Sample Contrastive Loss for Semi-supervised Image Classification](https://mlsanity.com/paper/2407.03596/) (2024)
- [ORION: ORthonormal Text Encoding for Universal VLM AdaptatION](https://mlsanity.com/paper/2602.19530/) (2026)

## Abstract (arXiv)

Vision-language models like CLIP have shown sig- nificant potential in handling natural images, yet their perfor- mance is often limited by the distinct characteristics of satellite imagery. While parameter-efficient adaptation techniques exist, their efficacy is frequently limited by the scarcity of annotated samples. In this letter, we propose Self-Evolutionary CLIP (SE- CLIP), a semi-supervised framework designed for recursive label mining in scene classification. The approach follows a dual-phase pipeline, where an initial warm-up on a few annotated seeds is followed by a recursive discovery phase that iteratively identifies high-confidence samples from unlabeled pools. To maintain the integrity of the evolving support set, we employ a class-balanced selection strategy that prevents the model from being dominated by easily learned categories. Results on the UCM and NWPU benchmarks indicate that SE-CLIP significantly outperforms existing semi-supervised approaches. The framework provides a viable solution for adapting VLMs to the remote sensing domain with minimal human intervention.