Towards Improved Proxy-based Deep Metric Learning via Data-Augmented Domain Adaptation

2024-01-01 · Li Ren, Chen Chen, Liqiang Wang, Kien Hua

Deep Metric Learning (DML) plays an important role in modern computer vision research, where we learn a distance metric for a set of image representations. Recent DML techniques utilize the proxy to interact with the corresponding image samples in the embedding space. However, existing proxy-based DML methods focus on learning individual proxy-to-sample distance while the overall distribution of samples and proxies lacks attention. In this paper, we present a novel proxy-based DML framework that focuses on aligning the sample and proxy distributions to improve the efficiency of proxy-based DML losses. Specifically, we propose the Data-Augmented Domain Adaptation (DADA) method to adapt the domain gap between the group of samples and proxies. To the best of our knowledge, we are the first to leverage domain adaptation to boost the performance of proxy-based DML. We show that our method can be easily plugged into existing proxy-based DML losses. Our experiments on benchmarks, including the popular CUB-200-2011, CARS196, Stanford Online Products, and In-Shop Clothes Retrieval, show that our learning algorithm significantly improves the existing proxy losses and achieves superior results compared to the existing methods.

📄 PDF Abstract BibTeX arXiv:2401.00617

Code (1)

noahsark/dada 공식 구현 pytorch

Tasks

Domain Adaptation Metric Learning Retrieval

Methods 이 논문이 사용한 방법론

SET Dynamic Sparse Training method where weight mask is updated randomly periodically

Focus 설명 없음

Pressure-Testing Deception Probes in LLMs: Scaling, Robustness, and the Geometry of Deceptive Representations

2026-05-27 · Sachin Kumar arxiv

Linear probes trained on LLM activations are increasingly proposed as deception-detection metrics, yet report AUROC exceeding 0.96 on clean benchmarks while collapsing under distributional shift. This paper systematicall…

Learning Memory-Augmented Unidirectional Metrics for Cross-Modality Person Re-Identification

2022-01-01 · CVPR 2022 1 · Jialun Liu, Yifan Sun, Feng Zhu, Hongbin Pei 외

This paper tackles the cross-modality person re-identification (re-ID) problem by suppressing the modality discrepancy. In cross-modality re-ID, the query and gallery images are in different modalities. Given a train…

Cross-Modality Person Re-identification Person Re-Identification

Quantifying Memorization and Retriever Performance in Retrieval-Augmented Vision-Language Models

2025-02-19 · Peter Carragher, Abhinand Jha, R Raghav, Kathleen M. Carley

Large Language Models (LLMs) demonstrate remarkable capabilities in question answering (QA), but metrics for assessing their reliance on memorization versus retrieval remain underdeveloped. Moreover, while finetuned mode…

Memorization Question Answering Retrieval

On Assessing the Usefulness of Proxy Domains for Developing and Evaluating Embodied Agents

2021-09-29 · Anthony Courchesne, Andrea Censi, Liam Paull

In many situations it is either impossible or impractical to develop and evaluate agents entirely on the target domain on which they will be deployed. This is particularly true in robotics, where doing experiments on har…

Proxy Fairness

2018-06-28 · Maya Gupta, Andrew Cotter, Mahdi Milani Fard, Serena Wang

We consider the problem of improving fairness when one lacks access to a dataset labeled with protected groups, making it difficult to take advantage of strategies that can improve fairness but require protected group la…

Fairness