Select, Label, and Mix: Learning Discriminative Invariant
Feature Representations for Partial Domain Adaptation
Aadarsh Sahoo1
Rameswar Panda1
Rogerio Feris1
Kate Saenko1,2
Abir Das3
1 MIT-IBM Watson AI Lab
2 Boston University
3 IIT Kharagpur
NeurIPS DistShift Workshop 2021
WACV 2023

Abstract

Partial domain adaptation which assumes that the unknown target label space is a subset of the source label space has attracted much attention in computer vision. Despite recent progress, existing methods often suffer from three key problems: negative transfer, lack of discriminability and domain invariance in the latent space. To alleviate the above issues, we develop a novel `Select, Label, and Mix' (SLM) framework that aims to learn discriminative invariant feature representations for partial domain adaptation. First, we present an efficient "select" module that automatically filters out the outlier source samples to avoid negative transfer while aligning distributions across both domains. Second, the "label" module iteratively trains the classifier using both the labeled source domain data and the generated pseudo-labels for the target domain to enhance the discriminability of the latent space. Finally, the "mix" module utilizes domain mixup jointly with the other two modules to explore more intrinsic structures across domains leading to a domain-invariant latent space for partial domain adaptation. Extensive experiments on several benchmark datasets demonstrate the superiority of our proposed framework over state-of-the-art methods.

Experimental Results Overview


Results on Office-31 Dataset.


Results on Office-Home Dataset.


Results on ImageNet-Caltech and VisDA-2017 Datasets.


Results by varying the number of outlier classes. (Office-31: A->W)


Paper & Code

Aadarsh Sahoo, Rameswar Panda, Rogerio Feris, Kate Saenko, Abir Das
Select, Label, and Mix: Learning Discriminative Invariant Feature Representations for Partial Domain Adaptation
NeurIPS DistShift Workshop (NeurIPS-W), 2021 [Extended Draft Under Review]
[PDF] [Supp] [Poster] [Presentation] [Slides] [Code]