A Mask-Pooling Model With Local-Level Triplet Loss for Person Re-Identification

Abstract

Person Re-Identification (ReID) is an important yet challenging task in computer vision. Background clutter is one of the greatest challenges to overcome. In this paper, we propose a Maskpooling model with local-level triplet loss (MPM-LTL) to tackle this problem and improve person ReID performance. Specifically, we present a novel pooling method, called mask pooling (MP), to gradually remove background features in feature maps through deep convolutional network. With mask pooling, the network can learn the most crucial person features. Moreover, we raise a novel local-level triplet loss for discriminative feature training. Furthermore, we propose a new hard triplets selection algorithm named Mask-guided TriHard. The method is based on human outline information, which is, to our best knowledge, employed for the first time for hard triplets selection. We achieve the state-of-the-art results on three benchmark person datasets Market-1501 [1], CUHK03 [2] and DukeMTMC-reID [3], [4].

A Discriminative Person Re-Identification Model With Global-Local Attention and Adaptive Weighted Rank List Loss

“…However, the triple loss is affected by the sample distribution, which leads to poor generalization ability of the network. The methods [35,36] are proposed to improve the triplet loss, which has achieved good performance. However, in order to concentrate the positive samples within a certain range, they ignored the internal structure of the samples.…”

“…The methods of MGN [8], CAM [9], GD-Net [10], MSBA [12], BagTricks [14], AGW [15], ABD-Net [16], RAG-SC [17], AANet [22], SONA [24], RRGCCAN [26], IANet [29], EMM [32], MPM-LTL [35], HA-CNN [46] and SCAL [47] are selected for comparison. It is worth noting that we do not use the re-ranking strategy.…”

“…In recent years, the Re-id algorithms [6,7,45] with deep learning have made tremendous progress in solving the aforementioned problems. However, the convolution kernel with a finite receptive field only extracts local features, which makes it difficult to learn global semantic information.…”