paper-with-me

Papers

Parameter Sharing Exploration and Hetero-Center based Triplet Loss for Visible-Thermal Person Re-Identification

2020-08-14 · Haijun Liu, Xiaoheng Tan, Xichuan Zhou

This paper focuses on the visible-thermal cross-modality person re-identification (VT Re-ID) task, whose goal is to match person images between the daytime visible modality and the nighttime thermal modality. The two-stream network is usually adopted to address the cross-modality discrepancy, the most challenging problem for VT Re-ID, by learning the multi-modality person features. In this paper, we explore how many parameters of two-stream network should share, which is still not well investigated in the existing literature. By well splitting the ResNet50 model to construct the modality-specific feature extracting network and modality-sharing feature embedding network, we experimentally demonstrate the effect of parameters sharing of two-stream network for VT Re-ID. Moreover, in the framework of part-level person feature learning, we propose the hetero-center based triplet loss to relax the strict constraint of traditional triplet loss through replacing the comparison of anchor to all the other samples by anchor center to all the other centers. With the extremely simple means, the proposed method can significantly improve the VT Re-ID performance. The experimental results on two datasets show that our proposed method distinctly outperforms the state-of-the-art methods by large margins, especially on RegDB dataset achieving superior performance, rank1/mAP/mINP 91.05%/83.28%/68.84%. It can be a new baseline for VT Re-ID, with a simple but effective strategy.

📄 PDF Abstract BibTeX arXiv:2008.06223

Code (1)

hijune6/Hetero-center-triplet-loss-for-VT-Re-ID 공식 구현 pytorch

Tasks

Cross-Modality Person Re-identificationCross-Modal Person Re-IdentificationPerson Re-IdentificationTriplet

Methods 이 논문이 사용한 방법론

Triplet Loss The goal of Triplet loss, in the context of Siamese Networks, is to maximize the joint probability among all score-pairs i.e. the product of all probabilities. By using its…

Similar Papers 제목 키워드 기반

Extending NGU to Multi-Agent RL: A Preliminary Study

2025-12-01 · Juan Hernandez, Diego Fernández, Manuel Cifuentes, Denis Parra 외 arxiv

The Never Give Up (NGU) algorithm has proven effective in reinforcement learning tasks with sparse rewards by combining episodic novelty and intrinsic motivation. In this work, we extend NGU to multi-agent environments a…

Reinforcement Learning

Unified Batch All Triplet Loss for Visible-Infrared Person Re-identification

2021-03-08 · Wenkang Li, Ke Qi, Wenbin Chen, Yicong Zhou

Visible-Infrared cross-modality person re-identification (VI-ReID), whose aim is to match person images between visible and infrared modality, is a challenging cross-modality image retrieval task. Batch Hard Triplet loss…

AllCross-Modality Person Re-identificationImage RetrievalPerson Re-Identification+2

PCCT: Progressive Class-Center Triplet Loss for Imbalanced Medical Image Classification

2022-07-11 · Kanghao Chen, Weixian Lei, Rong Zhang, Shen Zhao 외

Imbalanced training data is a significant challenge for medical image classification. In this study, we propose a novel Progressive Class-Center Triplet (PCCT) framework to alleviate the class imbalance issue particularl…

image-classificationImage ClassificationMedical Image ClassificationTriplet

Collaborative Training of Heterogeneous Reinforcement Learning Agents in Environments with Sparse Rewards: What and When to Share?

2022-02-24 · Alain Andres, Esther Villar-Rodriguez, Javier Del Ser

In the early stages of human life, babies develop their skills by exploring different scenarios motivated by their inherent satisfaction rather than by extrinsic rewards from the environment. This behavior, referred to a…

Efficient ExplorationTransfer Learning

Wasserstein-Barycenter Consensus for Cooperative Multi-Agent Reinforcement Learning

2025-06-14 · Ali Baheri

Cooperative multi-agent reinforcement learning (MARL) demands principled mechanisms to align heterogeneous policies while preserving the capacity for specialized behavior. We introduce a novel consensus framework that de…

Multi-agent Reinforcement Learningreinforcement-learningReinforcement Learning