Beyond Triplet Loss: A Deep Quadruplet Network for Person Re-identification

Abstract

Person re-identification (ReID) is an important task in wide area video surveillance which focuses on identifying people across different cameras. Recently, deep learning networks with a triplet loss become a common framework for person ReID. However, the triplet loss pays main attentions on obtaining correct orders on the training set. It still suffers from a weaker generalization capability from the training set to the testing set, thus resulting in inferior performance. In this paper, we design a quadruplet loss, which can lead to the model output with a larger inter-class variation and a smaller intra-class variation compared to the triplet loss. As a result, our model has a better generalization ability and can achieve a higher performance on the testing set. In particular, a quadruplet deep network using a margin-based online hard negative mining is proposed based on the quadruplet loss for the person ReID. In extensive experiments, the proposed network outperforms most of the state-of-the-art algorithms on representative datasets which clearly demonstrates the effectiveness of our proposed method.

Impostor Resilient Multimodal Metric Learning for Person Reidentification

“…Though, deep features (DF) and deep matching networks (DMN) have no match with conventional metric learning methods, however, from the results in Table 1 it is clearly evident if two major issues of reidentification (i.e., multimodal transforms, and strong rejection capability against impostors) can be well handled simultaneously, then comparable or even higher performance than deep methods can be attained. Our IRM3 + CVI ( = 15) has 7.1% and 4.94% higher rank@1 than QuadrupletNet [33] and JLML [34], respectively. These obtained results demonstrate the fact that for smaller dataset like VIPeR deep matching networks have insufficient training samples to learn a discriminative network.…”

“…Only K-LFDA when trained with mom LE [24] feature attains comparable performance than DMN. However, motivated to resolve the challenges for reidentification in real world (i.e., multimodal image space, and diverse impostors) IRM3 + CVI ( = 15) has much better results than MCP-CNN [39], E2E-CAN [31], Quadruplet-Net [33], and JLML [34], while our IRM3 + CVI ( = 15) has 1.49% higher rank@1 than DLPA [32]. DLPA extracts deep features by semantically aligning body parts, as well as rectifying pose variations.…”

“…We follow the evaluation protocol of [33] for test/train split for VIPeR, CUHK01, and CUHK03 datasets. However, in our work we have tested CUHK01 for = 486 only, while CUHK03 is tested for both Labelled and Detected settings.…”

Droplet-Transmitted Infection Risk Ranking Based on Close Proximity Interaction

“…Triplet loss is also widely used to learn fine-grained similarity image metrics . Quadruplet loss Chen et al (2017c) strengthens the generalization capability and leads the model to output with a larger inter-class variation and a smaller intra-class variation superior to triplet loss.…”

“…We use the database of CASIA (Yu et al, 2009;Chen et al, 2017c) to train our network model for the task of person re-identification. The task of person re-identification achieved 88.24% top-1 accuracy, mAP = 70.68% only with softmax loss.…”