Domain Alignment With Triplets

Abstract

Deep domain adaptation methods can reduce the distribution discrepancy by learning domain-invariant embedddings. However, these methods only focus on aligning the whole data distributions, without considering the class-level relations among source and target images. Thus, a target embeddings of a bird might be aligned to source embeddings of an airplane. This semantic misalignment can directly degrade the classifier performance on the target dataset. To alleviate this problem, we present a similarity constrained alignment (SCA) method for unsupervised domain adaptation. When aligning the distributions in the embedding space, SCA enforces a similarity-preserving constraint to maintain class-level relations among the source and target images, i.e., if a source image and a target image are of the same class label, their corresponding embeddings are supposed to be aligned nearby, and vise versa. In the absence of target labels, we assign pseudo labels for target images. Given labeled sourc

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keydeng2018domain

Related papers

• Dual-triplet Metric Learning For Unsupervised Domain Adaptation In Video-based Face Recognition (2020)5.84
• Prototype-based Semantic Consistency Alignment For Domain Adaptive Retrieval (2025)0.00
• Correspondence-free Domain Alignment For Unsupervised Cross-domain Image Retrieval (2023)9.23
• Bda-sketret: Bi-level Domain Adaptation For Zero-shot SBIR (2022)10.35
• Adapt And Align To Improve Zero-shot Sketch-based Image Retrieval (2023)0.00
• Domain Adaptation In Multi-view Embedding For Cross-modal Video Retrieval (2021)0.00
• Few-shot Unsupervised Domain Adaptation With Image-to-class Sparse Similarity Encoding (2021)7.16
• Informative And Representative Triplet Selection For Multilabel Remote Sensing Image Retrieval (2021)10.74