Scalable Person Re-identification: A Benchmark

ACM Trans. Multimedia Comput. Commun. Appl.

2017

Self Cite

657

375

Abstract-In this paper, we revisit two popular convolutional neural networks (CNN) in person re-identification (re-ID), i.e.,verification and identification models. The two models have their respective advantages and limitations due to different loss functions. In this paper, we shed light on how to combine the two models to learn more discriminative pedestrian descriptors. Specifically, we propose a siamese network that simultaneously computes the identification loss and verification loss. Given a pair of training images, the network predicts the identities of the two input images and whether they belong to the same identity. Our network learns a discriminative embedding and a similarity measurement at the same time, thus making full usage of the re-ID annotations.Our method can be easily applied on different pre-trained networks. Albeit simple, the learned embedding improves the state-of-the-art performance on two public person re-ID benchmarks. Further, we show our architecture can also be applied in image retrieval.

“…Every identity has 9.6 training images on average in CUHK03 [2] and has 17.2 images in Market1501 [3]. CNN can learn discriminative embeddings by itself without part-matching.…”

Section: B Identification Modelsmentioning

confidence: 99%

Section: B Identification Modelsmentioning

confidence: 99%

mentioning

confidence: 99%

mentioning

confidence: 99%

See 2 more Smart Citations

A Discriminatively Learned CNN Embedding for Person Reidentification

Zheng

ACM Trans. Multimedia Comput. Commun. Appl.

2017

Self Cite

657

375

“…Examples include place retrieval [167], pedestrian retrieval [168], vehicle retrieval [169], logo retrieval [77], etc. Images in these tasks have specific prior knowledge that can be made use of.…”

Section: Towards Specialized Instance Retrievalmentioning

confidence: 99%

SIFT Meets CNN: A Decade Survey of Instance Retrieval

Zheng

IEEE Trans. Pattern Anal. Mach. Intell.

Tian

2018

Self Cite

655

319

Abstract-In the early days, content-based image retrieval (CBIR) was studied with global features. Since 2003, image retrieval based on local descriptors (de facto SIFT) has been extensively studied for over a decade due to the advantage of SIFT in dealing with image transformations. Recently, image representations based on the convolutional neural network (CNN) have attracted increasing interest in the community and demonstrated impressive performance. Given this time of rapid evolution, this article provides a comprehensive survey of instance retrieval over the last decade. Two broad categories, SIFT-based and CNN-based methods, are presented. For the former, according to the codebook size, we organize the literature into using large/medium-sized/small codebooks. For the latter, we discuss three lines of methods, i.e., using pre-trained or fine-tuned CNN models, and hybrid methods. The first two perform a single-pass of an image to the network, while the last category employs a patch-based feature extraction scheme. This survey presents milestones in modern instance retrieval, reviews a broad selection of previous works in different categories, and provides insights on the connection between SIFT and CNN-based methods. After analyzing and comparing retrieval performance of different categories on several datasets, we discuss promising directions towards generic and specialized instance retrieval.

One‐shot video‐based person re‐identification with variance subsampling algorithm

Zhao

Computer Animation & Virtual

et al. 2020

Previous works propose the distance-based sampling for unlabeled datapoints to address the few-shot person re-identification task, however, many selected samples may be assigned with wrong labels due to poor feature quality in these works, which negatively affects the learning procedure. In this article, we propose a novel sampling strategy to improve the quality of assigned pseudo-labels, thus promoting the final performance. To illustrate, we first propose the concept of variance confidence to measure the credibility of pseudo-labels, then we apply a novel variance subsampling algorithm to improve the accuracy of the selected sample labels. Our method combines distance confidence and variance confidence as a two-round sampling criterion. Meanwhile, a variation decay strategy is used in our sampling process in combination with the actual distribution of features. We evaluate our approach on two publicly available datasets, MARS and DukeMTMC-VideoReID, and achieve state-of-the-art one-shot performance.