HBReID: Harder Batch for Re-identification
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.
Code (0)
등록된 구현이 없습니다.
Tasks
Person Re-IdentificationTripletSimilar Papers 제목 키워드 기반
Smoothed Online Classification can be Harder than Batch Classification
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 ClassificationClassificationmicroGAN: Promoting Variety through Microbatch Discrimination
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 …
DiversitymicrobatchGAN: Stimulating Diversity with Multi-Adversarial Discrimination
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 …
DiversityBatch Normalization and the impact of batch structure on the behavior of deep convolution networks
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…
UnityExponential Lower Bounds for Batch Reinforcement Learning: Batch RL can be Exponentially Harder than Online RL
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)