Memory-Assisted Sub-Prototype Mining for Universal Domain Adaptation
Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.
Keywords: Transfer Learning, Universal Domain Adaption, Memory-Assisted Network, Sub-Prototype Mining
Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2024/AuthorGuide.
TL;DR: We propose Memory-Assisted Sub-Prototype Mining(MemSPM), which explores the memory mechanism to learn sub-prototypes for improving the model’s adaption performance and interpretability.
Abstract: Universal domain adaptation aims to align the classes and reduce the feature gap between the same category of the source and target domains. The target private category is set as the unknown class during the adaptation process, as it is not included in the source domain. However, most existing methods overlook the intra-class structure within a category, especially in cases where there exists significant concept shift between the samples belonging to the same category. When samples with large concept shift are forced to be pushed together, it may negatively affect the adaptation performance. Moreover, from the interpretability aspect, it is unreasonable to align visual features with significant differences, such as fighter jets and civil aircraft, into the same category. Unfortunately, due to such semantic ambiguity and annotation cost, categories are not always classified in detail, making it difficult for the model to perform precise adaptation. To address these issues, we propose a novel Memory-Assisted Sub-Prototype Mining (MemSPM) method that can learn the differences between samples belonging to the same category and mine sub-classes when there exists significant concept shift between them. By doing so, our model learns a more reasonable feature space that enhances the transferability and reflects the inherent differences among samples annotated as the same category. We evaluate the effectiveness of our MemSPM method over multiple scenarios, including UniDA, OSDA, and PDA. Our method achieves state-of-the-art performance on four benchmarks in most cases.
Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors' identity.
No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.
Primary Area: transfer learning, meta learning, and lifelong learning
Submission Number: 4348
Loading