The Self-Optimal-Transport (SOT) feature transform is designed to upgrade the set of features of a data instance to facilitate downstream matching or grouping related tasks. The transformed set encodes a rich representation of high order relations between the instance features. Distances between transformed features capture their direct original similarity and their third party agreement regarding similarity to other features in the set. A particular min-cost-max-flow fractional matching problem, whose entropy regularized version can be approximated by an optimal transport (OT) optimization, results in our transductive transform which is efficient, differentiable, equivariant, parameterless and probabilistically interpretable. Empirically, the transform is highly effective and flexible in its use, consistently improving networks it is inserted into, in a variety of tasks and training schemes. We demonstrate its merits through the problem of unsupervised clustering and its efficiency and wide applicability for few-shot-classification, with state-of-the-art results, and large-scale person re-identification.
Most existing person re-identification methods compute pairwise similarity by extracting robust visual features and learning the discriminative metric. Owing to visual ambiguities, these content-based methods that determine the pairwise relationship only based on the similarity between them, inevitably produce a suboptimal ranking list. Instead, the pairwise similarity can be estimated more accurately along the geodesic path of the underlying data manifold by exploring the rich contextual information of the sample. In this paper, we propose a lightweight post-processing person re-identification method in which the pairwise measure is determined by the relationship between the sample and the counterpart's context in an unsupervised way. We translate the point-to-point comparison into the bilateral point-to-set comparison. The sample's context is composed of its neighbor samples with two different definition ways: the first order context and the second order context, which are used to compute the pairwise similarity in sequence, resulting in a progressive post-processing model. The experiments on four large-scale person re-identification benchmark datasets indicate that (1) the proposed method can consistently achieve higher accuracies by serving as a post-processing procedure after the content-based person re-identification methods, showing its state-of-the-art results, (2) the proposed lightweight method only needs about 6 milliseconds for optimizing the ranking results of one sample, showing its high-efficiency. Code is available at: https://github.com/123ci/PBCmodel.
Person re-identification has seen significant advancement in recent years. However, the ability of learned models to generalize to unknown target domains still remains limited. One possible reason for this is the lack of large-scale and diverse source training data, since manually labeling such a dataset is very expensive and privacy sensitive. To address this, we propose to automatically synthesize a large-scale person re-identification dataset following a set-up similar to real surveillance but with virtual environments, and then use the synthesized person images to train a generalizable person re-identification model. Specifically, we design a method to generate a large number of random UV texture maps and use them to create different 3D clothing models. Then, an automatic code is developed to randomly generate various different 3D characters with diverse clothes, races and attributes. Next, we simulate a number of different virtual environments using Unity3D, with customized camera networks similar to real surveillance systems, and import multiple 3D characters at the same time, with various movements and interactions along different paths through the camera networks. As a result, we obtain a virtual dataset, called RandPerson, with 1,801,816 person images of 8,000 identities. By training person re-identification models on these synthesized person images, we demonstrate, for the first time, that models trained on virtual data can generalize well to unseen target images, surpassing the models trained on various real-world datasets, including CUHK03, Market-1501, DukeMTMC-reID, and almost MSMT17. The RandPerson dataset is available at https://github.com/VideoObjectSearch/RandPerson.
We propose a novel online multi-object visual tracker using a Gaussian mixture Probability Hypothesis Density (GM-PHD) filter and deep appearance learning. The GM-PHD filter has a linear complexity with the number of objects and observations while estimating the states and cardinality of time-varying number of objects, however, it is susceptible to miss-detections and does not include the identity of objects. We use visual-spatio-temporal information obtained from object bounding boxes and deeply learned appearance representations to perform estimates-to-tracks data association for target labeling as well as formulate an augmented likelihood and then integrate into the update step of the GM-PHD filter. We also employ additional unassigned tracks prediction after the data association step to overcome the susceptibility of the GM-PHD filter towards miss-detections caused by occlusion. Extensive evaluations on MOT16, MOT17 and HiEve benchmark datasets show that our tracker significantly outperforms several state-of-the-art trackers in terms of tracking accuracy and identification.
Person re-identification has become a very popular research topic in the computer vision community owing to its numerous applications and growing importance in visual surveillance. Person re-identification remains challenging due to occlusion, illumination and significant intra-class variations across different cameras. In this paper, we propose a multi-task network base on an improved Res2Net model that simultaneously computes the identification loss and verification loss of two pedestrian images. Given a pair of pedestrian images, the system predicts the identities of the two input images and whether they belong to the same identity. In order to obtain deeper feature information of pedestrians, we propose to use the latest Res2Net model for feature extraction of each input image. Experiments on several large-scale person re-identification benchmark datasets demonstrate the accuracy of our approach. For example, rank-1 accuracies are 83.18% (+1.38) and 93.14% (+0.84) for the DukeMTMC and Market-1501 datasets, respectively. The proposed method shows encouraging improvements compared with state-of-the-art methods.
We propose a novel online multi-target visual tracker based on the recently developed Hypothesized and Independent Stochastic Population (HISP) filter. The HISP filter combines advantages of traditional tracking approaches like MHT and point-process-based approaches like PHD filter, and it has linear complexity while maintaining track identities. We apply this filter for tracking multiple targets in video sequences acquired under varying environmental conditions and targets density using a tracking-by-detection approach. We also adopt deep CNN appearance representation by training a verification-identification network (VerIdNet) on large-scale person re-identification data sets. We construct an augmented likelihood in a principled manner using this deep CNN appearance features and spatio-temporal information. Furthermore, we solve the problem of two or more targets having identical label considering the weight propagated with each confirmed hypothesis. Extensive experiments on MOT16 and MOT17 benchmark data sets show that our tracker significantly outperforms several state-of-the-art trackers in terms of tracking accuracy.
In this work, we propose a novel Spatial-Temporal Attention (STA) approach to tackle the large-scale person re-identification task in videos. Different from the most existing methods, which simply compute representations of video clips using frame-level aggregation (e.g. average pooling), the proposed STA adopts a more effective way for producing robust clip-level feature representation. Concretely, our STA fully exploits those discriminative parts of one target person in both spatial and temporal dimensions, which results in a 2-D attention score matrix via inter-frame regularization to measure the importances of spatial parts across different frames. Thus, a more robust clip-level feature representation can be generated according to a weighted sum operation guided by the mined 2-D attention score matrix. In this way, the challenging cases for video-based person re-identification such as pose variation and partial occlusion can be well tackled by the STA. We conduct extensive experiments on two large-scale benchmarks, i.e. MARS and DukeMTMC-VideoReID. In particular, the mAP reaches 87.7% on MARS, which significantly outperforms the state-of-the-arts with a large margin of more than 11.6%.
Online multi-object tracking is a fundamental problem in time-critical video analysis applications. A major challenge in the popular tracking-by-detection framework is how to associate unreliable detection results with existing tracks. In this paper, we propose to handle unreliable detection by collecting candidates from outputs of both detection and tracking. The intuition behind generating redundant candidates is that detection and tracks can complement each other in different scenarios. Detection results of high confidence prevent tracking drifts in the long term, and predictions of tracks can handle noisy detection caused by occlusion. In order to apply optimal selection from a considerable amount of candidates in real-time, we present a novel scoring function based on a fully convolutional neural network, that shares most computations on the entire image. Moreover, we adopt a deeply learned appearance representation, which is trained on large-scale person re-identification datasets, to improve the identification ability of our tracker. Extensive experiments show that our tracker achieves real-time and state-of-the-art performance on a widely used people tracking benchmark.
Simple Online and Realtime Tracking (SORT) is a pragmatic approach to multiple object tracking with a focus on simple, effective algorithms. In this paper, we integrate appearance information to improve the performance of SORT. Due to this extension we are able to track objects through longer periods of occlusions, effectively reducing the number of identity switches. In spirit of the original framework we place much of the computational complexity into an offline pre-training stage where we learn a deep association metric on a large-scale person re-identification dataset. During online application, we establish measurement-to-track associations using nearest neighbor queries in visual appearance space. Experimental evaluation shows that our extensions reduce the number of identity switches by 45%, achieving overall competitive performance at high frame rates.
Large-scale is a trend in person re-identification (re-id). It is important that real-time search be performed in a large gallery. While previous methods mostly focus on discriminative learning, this paper makes the attempt in integrating deep learning and hashing into one framework to evaluate the efficiency and accuracy for large-scale person re-id. We integrate spatial information for discriminative visual representation by partitioning the pedestrian image into horizontal parts. Specifically, Part-based Deep Hashing (PDH) is proposed, in which batches of triplet samples are employed as the input of the deep hashing architecture. Each triplet sample contains two pedestrian images (or parts) with the same identity and one pedestrian image (or part) of the different identity. A triplet loss function is employed with a constraint that the Hamming distance of pedestrian images (or parts) with the same identity is smaller than ones with the different identity. In the experiment, we show that the proposed Part-based Deep Hashing method yields very competitive re-id accuracy on the large-scale Market-1501 and Market-1501+500K datasets.
Person re-identification (person re-ID) is mostly viewed as an image retrieval problem. This task aims to search a query person in a large image pool. In practice, person re-ID usually adopts automatic detectors to obtain cropped pedestrian images. However, this process suffers from two types of detector errors: excessive background and part missing. Both errors deteriorate the quality of pedestrian alignment and may compromise pedestrian matching due to the position and scale variances. To address the misalignment problem, we propose that alignment can be learned from an identification procedure. We introduce the pedestrian alignment network (PAN) which allows discriminative embedding learning and pedestrian alignment without extra annotations. Our key observation is that when the convolutional neural network (CNN) learns to discriminate between different identities, the learned feature maps usually exhibit strong activations on the human body rather than the background. The proposed network thus takes advantage of this attention mechanism to adaptively locate and align pedestrians within a bounding box. Visual examples show that pedestrians are better aligned with PAN. Experiments on three large-scale re-ID datasets confirm that PAN improves the discriminative ability of the feature embeddings and yields competitive accuracy with the state-of-the-art methods.
One of the major restrictions on the performance of video-based person re-id is partial noise caused by occlusion, blur and illumination. Since different spatial regions of a single frame have various quality, and the quality of the same region also varies across frames in a tracklet, a good way to address the problem is to effectively aggregate complementary information from all frames in a sequence, using better regions from other frames to compensate the influence of an image region with poor quality. To achieve this, we propose a novel Region-based Quality Estimation Network (RQEN), in which an ingenious training mechanism enables the effective learning to extract the complementary region-based information between different frames. Compared with other feature extraction methods, we achieved comparable results of 92.4%, 76.1% and 77.83% on the PRID 2011, iLIDS-VID and MARS, respectively. In addition, to alleviate the lack of clean large-scale person re-id datasets for the community, this paper also contributes a new high-quality dataset, named "Labeled Pedestrian in the Wild (LPW)" which contains 7,694 tracklets with over 590,000 images. Despite its relatively large scale, the annotations also possess high cleanliness. Moreover, it's more challenging in the following aspects: the age of characters varies from childhood to elderhood; the postures of people are diverse, including running and cycling in addition to the normal walking state.
In recent years, a variety of proposed methods based on deep convolutional neural networks (CNNs) have improved the state of the art for large-scale person re-identification (ReID). While a large number of optimizations and network improvements have been proposed, there has been relatively little evaluation of the influence of training data and baseline network architecture. In particular, it is usually assumed either that networks are trained on labeled data from the deployment location (scene-dependent), or else adapted with unlabeled data, both of which complicate system deployment. In this paper, we investigate the feasibility of achieving scene-independent person ReID by forming a large composite dataset for training. We present an in-depth comparison of several CNN baseline architectures for both scene-dependent and scene-independent ReID, across a range of training dataset sizes. We show that scene-independent ReID can produce leading-edge results, competitive with unsupervised domain adaption techniques. Finally, we introduce a new dataset for comparing within-camera and across-camera person ReID.