Adaptive Prompt Learning with Negative Textual Semantics and Uncertainty Modeling for Universal Multi-Source Domain Adaptation
This work addresses domain adaptation challenges for machine learning applications where labeled data from multiple sources must be adapted to unlabeled target domains with unknown classes, representing an incremental improvement by incorporating textual semantics.
The paper tackles the problem of universal multi-source domain adaptation (UniMDA) by proposing APNE-CLIP, which integrates adaptive prompts, negative textual semantics, and uncertainty modeling to improve classification under domain and class shifts, achieving state-of-the-art results in experiments.
Universal Multi-source Domain Adaptation (UniMDA) transfers knowledge from multiple labeled source domains to an unlabeled target domain under domain shifts (different data distribution) and class shifts (unknown target classes). Existing solutions focus on excavating image features to detect unknown samples, ignoring abundant information contained in textual semantics. In this paper, we propose an Adaptive Prompt learning with Negative textual semantics and uncErtainty modeling method based on Contrastive Language-Image Pre-training (APNE-CLIP) for UniMDA classification tasks. Concretely, we utilize the CLIP with adaptive prompts to leverage textual information of class semantics and domain representations, helping the model identify unknown samples and address domain shifts. Additionally, we design a novel global instance-level alignment objective by utilizing negative textual semantics to achieve more precise image-text pair alignment. Furthermore, we propose an energy-based uncertainty modeling strategy to enlarge the margin distance between known and unknown samples. Extensive experiments demonstrate the superiority of our proposed method.