Self-Adaptive Partial Domain Adaptation

TL;DR

This paper introduces SAPDA, an end-to-end network that dynamically adjusts class weights to improve partial domain adaptation, effectively reducing negative transfer and enhancing transferability in cross-domain learning.

Contribution

It proposes a novel self-adaptive mechanism for class weight evaluation that rectifies shared, outlier, and confused classes during domain adaptation.

Findings

Achieves competitive results on multiple benchmarks.

Effectively reduces negative transfer caused by label space mismatch.

Demonstrates the effectiveness of dynamic class weight adjustment.

Abstract

Partial Domain adaptation (PDA) aims to solve a more practical cross-domain learning problem that assumes target label space is a subset of source label space. However, the mismatched label space causes significant negative transfer. A traditional solution is using soft weights to increase weights of source shared domain and reduce those of source outlier domain. But it still learns features of outliers and leads to negative immigration. The other mainstream idea is to distinguish source domain into shared and outlier parts by hard binary weights, while it is unavailable to correct the tangled shared and outlier classes. In this paper, we propose an end-to-end Self-Adaptive Partial Domain Adaptation(SAPDA) Network. Class weights evaluation mechanism is introduced to dynamically self-rectify the weights of shared, outlier and confused classes, thus the higher confidence samples have the more sufficient weights. Meanwhile it can eliminate the negative transfer caused by the mismatching of label space greatly. Moreover, our strategy can efficiently measure the transferability of samples in a broader sense, so that our method can achieve competitive results on unsupervised DA task likewise. A large number of experiments on multiple benchmarks have demonstrated the effectiveness of our SAPDA.