paper-with-me

Papers

HBReID: Harder Batch for Re-identification

2021-12-09 · Wen Li, Furong Xu, Jianan Zhao, Ruobing Zheng, Cheng Zou, Meng Wang, Yuan Cheng

Triplet loss is a widely adopted loss function in ReID task which pulls the hardest positive pairs close and pushes the hardest negative pairs far away. However, the selected samples are not the hardest globally, but the hardest only in a mini-batch, which will affect the performance. In this report, a hard batch mining method is proposed to mine the hardest samples globally to make triplet harder. More specifically, the most similar classes are selected into a same mini-batch so that the similar classes could be pushed further away. Besides, an adversarial scene removal module composed of a scene classifier and an adversarial loss is used to learn scene invariant feature representations. Experiments are conducted on dataset MSMT17 to prove the effectiveness, and our method surpasses all of the previous methods and sets state-of-the-art result.

📄 PDF Abstract BibTeX arXiv:2112.04761

Code (0)

등록된 구현이 없습니다.

Tasks

Person Re-IdentificationTriplet

Similar Papers 제목 키워드 기반

Smoothed Online Classification can be Harder than Batch Classification

2024-05-24 · Vinod Raman, Unique Subedi, Ambuj Tewari

We study online classification under smoothed adversaries. In this setting, at each time point, the adversary draws an example from a distribution that has a bounded density with respect to a fixed base measure, which is…

Binary ClassificationClassification

microGAN: Promoting Variety through Microbatch Discrimination

2018-09-27 · Goncalo Mordido, Haojin Yang, Christoph Meinel

We propose to tackle the mode collapse problem in generative adversarial networks (GANs) by using multiple discriminators and assigning a different portion of each minibatch, called microbatch, to each discriminator. We …

Diversity

microbatchGAN: Stimulating Diversity with Multi-Adversarial Discrimination

2020-01-10 · Gonçalo Mordido, Haojin Yang, Christoph Meinel

We propose to tackle the mode collapse problem in generative adversarial networks (GANs) by using multiple discriminators and assigning a different portion of each minibatch, called microbatch, to each discriminator. We …

Diversity

Batch Normalization and the impact of batch structure on the behavior of deep convolution networks

2018-02-21 · Mohamed Hajaj, Duncan Gillies

Batch normalization was introduced in 2015 to speed up training of deep convolution networks by normalizing the activations across the current batch to have zero mean and unity variance. The results presented here show a…

Unity

Exponential Lower Bounds for Batch Reinforcement Learning: Batch RL can be Exponentially Harder than Online RL

2020-12-14 · Andrea Zanette

Several practical applications of reinforcement learning involve an agent learning from past data without the possibility of further exploration. Often these applications require us to 1) identify a near optimal policy o…

reinforcement-learningReinforcement LearningReinforcement Learning (RL)