Zero-shot domain adaptation based on dual-level mix and contrast

2024-06-27 · Yu Zhe, Jun Sakuma

Zero-shot domain adaptation (ZSDA) is a domain adaptation problem in the situation that labeled samples for a target task (task of interest) are only available from the source domain at training time, but for a task different from the task of interest (irrelevant task), labeled samples are available from both source and target domains. In this situation, classical domain adaptation techniques can only learn domain-invariant features in the irrelevant task. However, due to the difference in sample distribution between the two tasks, domain-invariant features learned in the irrelevant task are biased and not necessarily domain-invariant in the task of interest. To solve this problem, this paper proposes a new ZSDA method to learn domain-invariant features with low task bias. To this end, we propose (1) data augmentation with dual-level mixups in both task and domain to fill the absence of target task-of-interest data, (2) an extension of domain adversarial learning to learn domain-invariant features with less task bias, and (3) a new dual-level contrastive learning method that enhances domain-invariance and less task biasedness of features. Experimental results show that our proposal achieves good performance on several benchmarks.

📄 PDF Abstract BibTeX arXiv:2406.18996

Code (0)

등록된 구현이 없습니다.

Tasks

Contrastive Learning Data Augmentation Domain Adaptation

Methods 이 논문이 사용한 방법론

Contrastive Learning 설명 없음

SIDA: Synthetic Image Driven Zero-shot Domain Adaptation

2025-07-24 · Ye-Chan Kim, SeungJu Cha, Si-Woo Kim, Taewhan Kim 외 arxiv

Zero-shot domain adaptation is a method for adapting a model to a target domain without utilizing target domain image data. To enable adaptation without target images, existing studies utilize CLIP's embedding space and …

Domain Adaptation Style Transfer

Similarity Min-Max: Zero-Shot Day-Night Domain Adaptation

2023-07-17 · ICCV 2023 1 · Rundong Luo, Wenjing Wang, Wenhan Yang, Jiaying Liu

Low-light conditions not only hamper human visual experience but also degrade the model's performance on downstream vision tasks. While existing works make remarkable progress on day-night domain adaptation, they rely he…

Action Recognition Domain Adaptation Semantic Segmentation Temporal Action Localization+1

Zero-Shot Cross-Domain Dialogue State Tracking via Dual Low-Rank Adaptation

2024-07-31 · Xiang Luo, Zhiwen Tang, Jin Wang, Xuejie Zhang

Zero-shot dialogue state tracking (DST) seeks to enable dialogue systems to transition to unfamiliar domains without manual annotation or extensive retraining. Prior research has approached this objective by embedding pr…

Dialogue State Tracking

Conditional Coupled Generative Adversarial Networks for Zero-Shot Domain Adaptation

2020-09-11 · ICCV 2019 10 · Jinghua Wang, Jianmin Jiang

Machine learning models trained in one domain perform poorly in the other domains due to the existence of domain shift. Domain adaptation techniques solve this problem by training transferable models from the label-rich …

Domain Adaptation

EntroAD: Structural Entropy-Guided Prompt Adaptation for Zero-Shot Anomaly Detection

2026-05-27 · Xinyu Zhao, Qingyun Sun, Jiayi Luo, Jianxin Li arxiv

Zero-Shot Anomaly Detection (ZSAD) aims to detect anomalies in unseen domains without target-domain adaptation. Recent CLIP-based methods have shown promising performance by leveraging prompt learning and visual-text ali…

Anomaly Detection Domain Adaptation