# Semantic Relation-Enhanced CLIP Adapter for Domain Adaptive Zero-Shot Learning

arXiv: https://arxiv.org/abs/2510.21808 · HTML: https://mlsanity.com/paper/2510.21808/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 21 of its 25 references that are in the map.
- First posted on arXiv 21 Oct 2025.

## Builds on (most cited first, 21 of 21)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [Conditional Prompt Learning for Vision-Language Models](https://mlsanity.com/paper/2203.05557/) (2022)
- [Adversarial Discriminative Domain Adaptation](https://mlsanity.com/paper/1702.05464/) (2017)
- [CLIP-Adapter: Better Vision-Language Models with Feature Adapters](https://mlsanity.com/paper/2110.04544/) (2021)
- [DenseCLIP: Language-Guided Dense Prediction with Context-Aware Prompting](https://mlsanity.com/paper/2112.01518/) (2021)
- [Tip-Adapter: Training-free Adaption of CLIP for Few-shot Classification](https://mlsanity.com/paper/2207.09519/) (2022)
- [Semi-supervised Domain Adaptation via Minimax Entropy](https://mlsanity.com/paper/1904.06487/) (2019)
- [WebVision Database: Visual Learning and Understanding from Web Data](https://mlsanity.com/paper/1708.02862/) (2017)
- [Zero-shot Recognition via Semantic Embeddings and Knowledge Graphs](https://mlsanity.com/paper/1803.08035/) (2018)
- [Open Set Domain Adaptation by Backpropagation](https://mlsanity.com/paper/1804.10427/) (2018)
- [Rethinking Knowledge Graph Propagation for Zero-Shot Learning](https://mlsanity.com/paper/1805.11724/) (2018)
- [SENTRY: Selective Entropy Optimization via Committee Consistency for Unsupervised Domain Adaptation](https://mlsanity.com/paper/2012.11460/) (2020)
- [Safe Self-Refinement for Transformer-based Domain Adaptation](https://mlsanity.com/paper/2204.07683/) (2022)
- [Source-Free Domain Adaptation with Frozen Multimodal Foundation Model](https://mlsanity.com/paper/2311.16510/) (2023)
- [Transductive Unbiased Embedding for Zero-Shot Learning](https://mlsanity.com/paper/1803.11320/) (2018)
- [Robust Unsupervised Domain Adaptation for Neural Networks via Moment Alignment](https://mlsanity.com/paper/1711.06114/) (2017)
- [Towards Novel Target Discovery Through Open-Set Domain Adaptation](https://mlsanity.com/paper/2105.02432/) (2021)
- [Unsupervised Open Domain Recognition by Semantic Discrepancy Minimization](https://mlsanity.com/paper/1904.08631/) (2019)
- [Open-Set Domain Adaptation with Visual-Language Foundation Models](https://mlsanity.com/paper/2307.16204/) (2023)
- [Category-Prompt Refined Feature Learning for Long-Tailed Multi-Label Image Classification](https://mlsanity.com/paper/2408.08125/) (2024)

## Abstract (arXiv)

The high cost of data annotation has spurred research on training deep learning models in data-limited scenarios. Existing paradigms, however, fail to balance cross-domain transfer and cross-category generalization, giving rise to the demand for Domain-Adaptive Zero-Shot Learning (DAZSL). Although vision-language models (e.g., CLIP) have inherent advantages in the DAZSL field, current studies do not fully exploit their potential. Applying CLIP to DAZSL faces two core challenges: inefficient cross-category knowledge transfer due to the lack of semantic relation guidance, and degraded cross-modal alignment during target domain fine-tuning. To address these issues, we propose a Semantic Relation-Enhanced CLIP (SRE-CLIP) Adapter framework, integrating a Semantic Relation Structure Loss and a Cross-Modal Alignment Retention Strategy. As the first CLIP-based DAZSL method, SRE-CLIP achieves state-of-the-art performance on the I2AwA and I2WebV benchmarks, significantly outperforming existing approaches.