paper-with-me

Papers

Selective Transfer with Reinforced Transfer Network for Partial Domain Adaptation

2019-05-26 · CVPR 2020 6 · Zhihong Chen, Chao Chen, Zhaowei Cheng, Boyuan Jiang, Ke Fang, Xinyu Jin

One crucial aspect of partial domain adaptation (PDA) is how to select the relevant source samples in the shared classes for knowledge transfer. Previous PDA methods tackle this problem by re-weighting the source samples based on their high-level information (deep features). However, since the domain shift between source and target domains, only using the deep features for sample selection is defective. We argue that it is more reasonable to additionally exploit the pixel-level information for PDA problem, as the appearance difference between outlier source classes and target classes is significantly large. In this paper, we propose a reinforced transfer network (RTNet), which utilizes both high-level and pixel-level information for PDA problem. Our RTNet is composed of a reinforced data selector (RDS) based on reinforcement learning (RL), which filters out the outlier source samples, and a domain adaptation model which minimizes the domain discrepancy in the shared label space. Specifically, in the RDS, we design a novel reward based on the reconstruct errors of selected source samples on the target generator, which introduces the pixel-level information to guide the learning of RDS. Besides, we develope a state containing high-level information, which used by the RDS for sample selection. The proposed RDS is a general module, which can be easily integrated into existing DA models to make them fit the PDA situation. Extensive experiments indicate that RTNet can achieve state-of-the-art performance for PDA tasks on several benchmark datasets.

📄 PDF Abstract BibTeX arXiv:1905.10756

Code (0)

등록된 구현이 없습니다.

Tasks

Domain AdaptationPartial Domain AdaptationReinforcement LearningReinforcement Learning (RL)Transfer Learning

Similar Papers 제목 키워드 기반

Wasserstein Selective Transfer Learning for Cross-domain Text Mining

2021-11-01 · EMNLP 2021 11 · Lingyun Feng, Minghui Qiu, Yaliang Li, Haitao Zheng 외

Transfer learning (TL) seeks to improve the learning of a data-scarce target domain by using information from source domains. However, the source and target domains usually have different data distributions, which may le…

Transfer Learning

Learning to Selectively Transfer: Reinforced Transfer Learning for Deep Text Matching

2018-12-30 · Chen Qu, Feng Ji, Minghui Qiu, Liu Yang 외

Deep text matching approaches have been widely studied for many applications including question answering and information retrieval systems. To deal with a domain that has insufficient labeled data, these approaches can …

Information RetrievalNatural Language InferenceParaphrase IdentificationQuestion Answering+3

Partial Transfer Learning with Selective Adversarial Networks

2017-07-25 · CVPR 2018 6 · Zhangjie Cao, Mingsheng Long, Jian-Min Wang, Michael. I. Jordan

Adversarial learning has been successfully embedded into deep networks to learn transferable features, which reduce distribution discrepancy between the source and target domains. Existing domain adversarial networks ass…

Transfer Learning

An Entropy-guided Reinforced Partial Convolutional Network for Zero-Shot Learning

2021-11-03 · Yun Li, Zhe Liu, Lina Yao, Xianzhi Wang 외

Zero-Shot Learning (ZSL) aims to transfer learned knowledge from observed classes to unseen classes via semantic correlations. A promising strategy is to learn a global-local representation that incorporates global infor…

Generalized Zero-Shot LearningZero-Shot Learning

From Big to Small: Adaptive Learning to Partial-Set Domains

2022-03-14 · Zhangjie Cao, Kaichao You, Ziyang Zhang, Jianmin Wang 외

Domain adaptation targets at knowledge acquisition and dissemination from a labeled source domain to an unlabeled target domain under distribution shift. Still, the common requirement of identical class space shared acro…

Domain AdaptationPartial Domain Adaptation