Semantic Library Adaptation: LoRA Retrieval and Fusion for Open-Vocabulary Semantic Segmentation
This addresses domain adaptation for open-vocabulary semantic segmentation, enabling versatile real-world applications without fine-tuning, though it is incremental as it builds on existing adapter and embedding techniques.
The paper tackles the problem of domain shift degrading open-vocabulary semantic segmentation models by introducing Semantic Library Adaptation (SemLA), a training-free framework that dynamically merges relevant LoRA adapters based on CLIP embeddings, achieving superior adaptability and performance across a 20-domain benchmark.
Open-vocabulary semantic segmentation models associate vision and text to label pixels from an undefined set of classes using textual queries, providing versatile performance on novel datasets. However, large shifts between training and test domains degrade their performance, requiring fine-tuning for effective real-world applications. We introduce Semantic Library Adaptation (SemLA), a novel framework for training-free, test-time domain adaptation. SemLA leverages a library of LoRA-based adapters indexed with CLIP embeddings, dynamically merging the most relevant adapters based on proximity to the target domain in the embedding space. This approach constructs an ad-hoc model tailored to each specific input without additional training. Our method scales efficiently, enhances explainability by tracking adapter contributions, and inherently protects data privacy, making it ideal for sensitive applications. Comprehensive experiments on a 20-domain benchmark built over 10 standard datasets demonstrate SemLA's superior adaptability and performance across diverse settings, establishing a new standard in domain adaptation for open-vocabulary semantic segmentation.