DeepReID: Deep Filter Pairing Neural Network for Person Re-identification

Abstract

Person re-identification is to match pedestrian images from disjoint camera views detected by pedestrian detectors. Challenges are presented in the form of complex variations of lightings, poses, viewpoints, blurring effects, image resolutions, camera settings, occlusions and background clutter across camera views. In addition, misalignment introduced by the pedestrian detector will affect most existing person re-identification methods that use manually cropped pedestrian images and assume perfect detection.In this paper, we propose a novel filter pairing neural network (FPNN) to jointly handle misalignment, photometric and geometric transforms, occlusions and background clutter. All the key components are jointly optimized to maximize the strength of each component when cooperating with others. In contrast to existing works that use handcrafted features, our method automatically learns features optimal for the re-identification task from data. The learned filter pairs encode photometric transforms. Its deep architecture makes it possible to model a mixture of complex photometric and geometric transforms. We build the largest benchmark re-id dataset with 13,164 images of 1,360 pedestrians. Unlike existing datasets, which only provide manually cropped pedestrian images, our dataset provides automatically detected bounding boxes for evaluation close to practical applications. Our neural network significantly outperforms state-of-the-art methods on this dataset.

Multiple-Shot People Re-Identification by Patch-Wise Learning

“…By utilizing information from existing datasets, an adaptive metric learning method is further introduced to strength the multi-modal distribution properties [11]. In the single-shot re-identification field, the relative distance comparison based metric learning [13], kernel based metric learning methods [14], and deep neural network based deep metric [15] are also discussed and presented. Despite a substantial amount of effort, the inter-/intra-class variance issue remains as a great challenge.…”

Co-Metric Learning for Person Re-Identification

“…Some recent works introduce deep learning framework to acquire robust local feature representations and then encoding them. Li et al [14] learned a unified deep filter by introducing a patch matching layer and a max-out grouping layer for person re-identification. Ahmed et al [15] presented a deep convolutional architecture that captured local relationships between person images based on mid-level features.…”

“…(i) Feature construction and learning aim at designing or studying discriminative appearance descriptions [8][9][10][11][12][13][14][15][16][17][18][19][20] that are robust for distinguishing different pedestrians across arbitrary cameras. However, handcrafted feature construction is extremely challenging due to miscellaneous and complicated variations.…”

Person re-identification with mutual re-ranking

“…In [32], selected discriminative and representative local patches are used for learning mid-level feature filters. In [16], the authors used a deep learning framework to learn pairs of mid-level filters which encode the transformation of mid-level appearance between the two cameras. Inspired by the recognition ability of human being, the authors in [31] proposed an unsupervised method for detecting salient and distinctive local patches and used them for matching images.…”