Instance Level Affinity-Based Transfer for Unsupervised Domain Adaptation
Authors:
- 1 June 2021
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 5357-5367
Abstract
Domain adaptation deals with training models using large scale labeled data from a specific source domain and then adapting the knowledge to certain target domains that have few or no labels. Many prior works learn domain agnostic feature representations for this purpose using a global distribution alignment objective which does not take into account the finer class specific structure in the source and target domains. We address this issue in our work and propose an instance affinity based criterion for source to target transfer during adaptation, called ILA-DA. We first propose a reliable and efficient method to extract similar and dissimilar samples across source and target, and utilize a multi-sample contrastive loss to drive the domain alignment process. ILA-DA simultaneously accounts for intra-class clustering as well as inter-class separation among the categories, resulting in less noisy classifier boundaries, improved transferability and increased accuracy. We verify the effectiveness of ILA-DA by observing consistent improvements in accuracy over popular domain adaptation approaches on a variety of benchmark datasets and provide insights into the proposed alignment approach. Code will be made publicly available at https://github.com/astuti/ILA-DA.Keywords
All Related Versions
This publication has 42 references indexed in Scilit:
- Unsupervised Domain Adaptation with Imbalanced Cross-Domain Data2015
- FaceNet: A unified embedding for face recognition and clustering2015
- Building a bird recognition app and large scale dataset with citizen scientists: The fine print in fine-grained dataset collection2015
- Unbiased look at dataset bias2011
- DAML: Domain Adaptation Metric LearningIEEE Transactions on Image Processing, 2011
- Domain Adaptation via Transfer Component AnalysisIEEE Transactions on Neural Networks, 2010
- A theory of learning from different domainsMachine Learning, 2009
- Domain Adaptation Problems: A DASVM Classification Technique and a Circular Validation StrategyIEEE Transactions on Pattern Analysis and Machine Intelligence, 2009
- Generating Estimates of Classification Confidence for a Case-Based Spam FilterLecture Notes in Computer Science, 2005
- Nearest unlike neighbor (NUN): an aid to decision confidence estimationOptical Engineering, 1995