Learning to Discover Knowledge: A Weakly-Supervised Partial Domain Adaptation Approach

TL;DR

This paper introduces a self-paced transfer classifier learning method for weakly-supervised partial domain adaptation, effectively discovering knowledge from noisy source data and adapting it to unlabeled target domains, outperforming existing methods.

Contribution

It proposes a novel self-paced learning approach that handles noisy source labels and unlabeled target data, providing a strong baseline for generalized domain adaptation tasks.

Findings

Significantly outperforms state-of-the-art methods on benchmark datasets.

Effectively discovers faithful knowledge from noisy source domains.

Successfully adapts knowledge to unlabeled target domains.

Abstract

Domain adaptation has shown appealing performance by leveraging knowledge from a source domain with rich annotations. However, for a specific target task, it is cumbersome to collect related and high-quality source domains. In real-world scenarios, large-scale datasets corrupted with noisy labels are easy to collect, stimulating a great demand for automatic recognition in a generalized setting, i.e., weakly-supervised partial domain adaptation (WS-PDA), which transfers a classifier from a large source domain with noises in labels to a small unlabeled target domain. As such, the key issues of WS-PDA are: 1) how to sufficiently discover the knowledge from the noisy labeled source domain and the unlabeled target domain, and 2) how to successfully adapt the knowledge across domains. In this paper, we propose a simple yet effective domain adaptation approach, termed as self-paced transfer classifier learning (SP-TCL), to address the above issues, which could be regarded as a well-performing baseline for several generalized domain adaptation tasks. The proposed model is established upon the self-paced learning scheme, seeking a preferable classifier for the target domain. Specifically, SP-TCL learns to discover faithful knowledge via a carefully designed prudent loss function and simultaneously adapts the learned knowledge to the target domain by iteratively excluding source examples from training under the self-paced fashion. Extensive evaluations on several benchmark datasets demonstrate that SP-TCL significantly outperforms state-of-the-art approaches on several generalized domain adaptation tasks.