Gated Siamese Convolutional Neural Network Architecture for Human Re-identification

By Rahul Rama Varior, Mrinal Haloi, G. Wang. 2016

813 citations recorded by the source corpus.

Matching pedestrians across multiple camera views, known as human re-identification, is a challenging research problem that has numerous applications in visual surveillance. With the resurgence of Convolutional Neural Networks (CNNs), several end-to-end deep Siamese CNN architectures have been proposed for human re-identification with the objective of projecting the images of similar pairs (i.e. same identity) to be closer to each other and those of dissimilar pairs to be distant from each other. However, current networks extract fixed representations for each image regardless of other images which are paired with it and the comparison with other images is done only at the final level. In this setting, the network is at risk of failing to extract finer local patterns that may be essential to distinguish positive pairs from hard negative pairs. In this paper, we propose a gating function to selectively emphasize such fine common local patterns by comparing the mid-level features across pairs of images. This produces flexible representations for the same image according to the images they are paired with. We conduct experiments on the CUHK03, Market-1501 and VIPeR datasets and demonstrate improved performance compared to a baseline Siamese CNN architecture.

Subfields: Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

Citations in the corpus

Feature Boosting Network For 3D Pose Estimation (2019, methodology): “Our proposed context consistency gate is inspired by the gating mechanism [25], [26], [27], [28], [29], which is shown to be an”
Spatio-Temporal LSTM with Trust Gates for 3D Human Action Recognition (2016, background): “Recurrent neural networks (RNNs) which are a variant of neural nets for handling sequential data with variable length, have been successfully applied to language modeling [10–12], image captioning [13, 14], video analysis [15–24], human re-identification [25,26], and RGB-based action recognition [27”
In Defense of the Triplet Loss for Person Re-Identification (2017, background): “However, using pretrained networks also leads to a design lock-in, and does not allow for the exploration of new deep learning advances or different architectures.”
Semantics Disentangling for Text-To-Image Generation (2019, methodology): “Inspired by the advantages of Siamese structure used in different tasks [32, 33, 4, 10, 43] which can find the similarity between a pair of sequences, we treat our discriminator as an image comparator so as to preserve the semantic consistency among the generated images as long as their descriptions”
Continual Representation Learning for Biometric Identification (2020, background): “Biometric identification [23,51], including face recognition [11, 37, 67] and person re-identification (re-id) [34, 66, 71], has achieved significant progress in the recent years due to the advances in modern learnable representations [8, 9, 11, 20, 34, 52, 60, 67] and emerging large datasets [17, 2”
Learning Deep Context-Aware Features over Body and Latent Parts for Person Re-identification (2017, methodology): “Market1501: For the Market1501 dataset, several stateof-the-art methods are compared, including Bag of Words (BOW) [53], Weighted Approximate Rank Component Analysis (WARCA) [15], Discriminative Null Space (DNS) [47], Spatially Constrained Similarity function on Polynomial feature map (SCSP) [2], an”
RGB-Infrared Cross-Modality Person Re-identification (2017, background): “Networks with two inputs similar to two-stream structure are also favorable in Re-ID tasks, for example, Ahmed’s net [1], SIR-CIR net [42], gated siamese net [41], etc.”
Person Re-identification by Deep Learning Multi-scale Representations (2017, background): “Recently, deep learning re-id models [26, 4, 49, 57, 45, 78, 65, 7, 11, 66, 9, 61, 27] start to take over and have obtained impressive performance.”
Mask-Guided Contrastive Attention Model for Person Re-identification (2018, background): “In the past years, numerous of methods [47, 39, 25, 36, 26, 37, 43, 34] have been proposed to address this problem.”
Improving Person Re-identification by Attribute and Identity Learning (2017, methodology): “We first describe two baselines in Section 4.1 and then the APR network in Section 4.2”
HydraPlus-Net: Attentive Deep Features for Pedestrian Analysis (2017, methodology): “The Market-1501 [38] dataset is also evaluated with the metric learning WARCA-L [11], a novel Siamese LSTM architecture LOMO+CN [27], the Siamese CNN with learnable gate S-CNN [26], and the bag of words model BoW-best [38].”
Multi-scale Deep Learning Architectures for Person Re-identification (2017, methodology): “More recently, an extension of the siamese network has been studied for person re-id [50].”
AlignedReID: Surpassing Human-Level Performance in Person Re-Identification (2017, background): “With the renaissance of deep learning, the convolutional neural network (CNN) has dominated this field [24, 32, 6, 54, 16, 24], by learning features in an end-to-end fashion through various metric learning losses such as contrastive loss [32], triplet loss [18], improved triplet loss [6], quadruplet”
Learning Discriminative Features with Multiple Granularities for Person Re-Identification (2018, background): “commonly used in siamese-liked networks [33], which focuses on maximizing the distances between inter-class pairs and minimizing that between intra-class pairs.”
Cross-Modality Person Re-Identification With Shared-Specific Feature Transfer (2020, methodology): “Other methods are based on metric learning, focusing on proper loss functions, like the contrastive loss [40], triplet loss [17], quadruplet loss [2], etc.”
Attention-Aware Compositional Network for Person Re-identification (2018, background): “The first category mainly includes the traditional feature descriptors [53, 52, 51, 27, 7, 31, 35] and deep learning features [43, 41, 42, 12, 25, 40].”
Omni-Scale Feature Learning for Person Re-Identification (2019, methodology): “Deep ReID Architectures Most existing deep ReID CNNs [25, 1, 53, 41, 12, 45, 57] borrow architectures designed for generic object categorisation problems, such as ImageNet 1K object classification.”