Selective Transfer with Reinforced Transfer Network for Partial Domain Adaptation

TL;DR

This paper introduces RTNet, a novel approach for partial domain adaptation that combines high-level features and pixel-level information through reinforcement learning to select relevant source samples, improving adaptation performance.

Contribution

The paper proposes a reinforced transfer network (RTNet) with a reinforced data selector that integrates pixel-level and high-level information for better source sample selection in PDA.

Findings

Achieves state-of-the-art results on benchmark datasets.

Effectively filters out outlier source samples.

Demonstrates the benefit of combining pixel-level and high-level features.

Abstract

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.