Self-Adaptive Partial Domain Adaptation

2021/09/18 by Jian Hu, Hu, Jian, Hongya Tuo +15
Computer Science · #Computer Vision and Pattern Recognition (cs.CV) #Domain Adaptation and Few-Shot Learning #FOS: Computer and information sciences #Machine Learning and ELM #Multimodal Machine Learning Applications #cs.CV

paper · pdf · doi:10.48550/arxiv.2109.08829

10 pages, 14 figures

arxiv created 2021/09/18 · openalex publication_date 2021/09/18 · arxiv updated 2021/09/21 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

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.

Citations

• ImageNet Large Scale Visual Recognition Challenge
• DeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognition
• ImageNet classification with deep convolutional neural networks
• Unsupervised Domain Adaptation with Residual Transfer Networks
• Label Efficient Learning of Transferable Representations across Domains and Tasks
• Conditional Adversarial Domain Adaptation
• Transferrable Prototypical Networks for Unsupervised Domain Adaptation
• Adversarial Discriminative Domain Adaptation
• Partial Adversarial Domain Adaptation
• ADVENT: Adversarial Entropy Minimization for Domain Adaptation in Semantic Segmentation
• Domain Adaptive YOLO for One-Stage Cross-Domain Detection

Related

• Associative Partial Domain Adaptation
• Adaptively-Accumulated Knowledge Transfer for Partial Domain Adaptation
• Learning to Transfer Examples for Partial Domain Adaptation
• From Big to Small: Adaptive Learning to Partial-Set Domains
• Learning to Discover Knowledge: A Weakly-Supervised Partial Domain Adaptation Approach