Resource Aware Person Re-identification Across Multiple Resolutions

Wang, Yan; Wang, Lequn; You, Yurong; Zou, Xu; Chen, Vincent; Li, Serena; Huang, Gao; Hariharan, Bharath; Weinberger, Kilian Q.

doi:10.1109/cvpr.2018.00839

Cited by 249 publications

(141 citation statements)

References 61 publications

Supporting

Mentioning

141

Contrasting

Order By: Relevance

“…Recently, supervised learning frameworks comprising of CNNs have been used for re-ID because of their ability to capture semantic and spatial information [8], [9], [21]- [23]. Broadly, the methods can be divided into two categories: deep representation learning and deep metric learning.…”

Section: A Person Re-idmentioning

confidence: 99%

“…Broadly, the methods can be divided into two categories: deep representation learning and deep metric learning. The first aims at creating a discriminative feature representation for the images [8], [24], [25]. In [24], a robust feature embedding is learnt by training the model in multiple domains with domain guided dropout.…”

Section: A Person Re-idmentioning

confidence: 99%

“…In [24], a robust feature embedding is learnt by training the model in multiple domains with domain guided dropout. In [8], the authors fuse multiple embeddings across layers to capture spatial details lost in the last layer. In contrast, deep metric learning intends to learn the similarity between images belonging to the same person [10], [26], [27].…”

Section: A Person Re-idmentioning

confidence: 99%

“…Prior work has focused on extracting discriminative features from individuals' appearances [1]- [3] and designing (or learning) appropriate distance metrics for feature matching [2], [4]- [7]. More recently, deep convolutional neural networks (CNNs) have been widely applied for the re-ID problem because of their flexible architectures which jointly learn the two stages [8]- [11], significantly improving the overall performance.…”

Section: Introductionmentioning

confidence: 99%

“…The success of zero-shot re-ID depends highly upon the feature representation that we choose for the images. For this, we leverage a deep-CNN [8] which extracts highly discriminative features from the gallery images.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

An Empirical Study of Person Re-Identification with Attributes

Shree

Chao

Campbell

2019

2019 28th IEEE International Conference on Robot and Human Interactive Communication (RO-MAN)

View full text Add to dashboard Cite

Person re-identification aims to identify a person from an image collection, given one image of that person as the query. There is, however, a plethora of real-life scenarios where we may not have a priori library of query images and therefore must rely on information from other modalities. In this paper, an attribute-based approach is proposed where the person of interest (POI) is described by a set of visual attributes, which are used to perform the search. We compare multiple algorithms and analyze how the quality of attributes impacts the performance. While prior work mostly relies on high precision attributes annotated by experts, we conduct a human-subject study and reveal that certain visual attributes could not be consistently described by human observers, making them less reliable in real applications. A key conclusion is that the performance achieved by non-expert attributes, instead of expert-annotated ones, is a more faithful indicator of the status quo of attribute-based approaches for person re-identification.

show abstract

Section: A Person Re-idmentioning

confidence: 99%

Section: A Person Re-idmentioning

confidence: 99%

Section: A Person Re-idmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

An Empirical Study of Person Re-Identification with Attributes

Shree

Chao

Campbell

2019

2019 28th IEEE International Conference on Robot and Human Interactive Communication (RO-MAN)

View full text Add to dashboard Cite

show abstract

Topology and channel affinity reinforced global attention for person re‐identification

Wang

Gao

Xin

et al. 2021

Int J of Intelligent Sys

View full text Add to dashboard Cite

Person re‐identification (re‐id), with the goal to recognize persons from images captured by nonoverlapping cameras, is a challenging topic in computer vision. It has been studied extensively in recent years, and the attention mechanism is widely applied in person re‐id. But many works mainly focus on extracting discriminative features from local saliency regions, while ignoring some potentially global information between whole‐body features and body‐part features. In this study, we first proposed two effective global information for extracting discriminative features: spatial topology information (STI) and channel affinity information (CAI). On this basis, we further propose a Multi‐information Fusion reinforced Global Attention (MIFGA) module which can effectively fuse a variety of information and utilize more comprehensive information to guide the learning of attention, so as to obtain pedestrian features that are conducive to clustering. Specifically, the proposed MIFGA module includes spatial attention (MIFGA‐S) and channel attention (MIFGA‐C). MIFGA‐S mainly utilizes local feature semantic information and STI to guide the learning of spatial attention. Furthermore, to mine the potential topology information in original feature maps, the self‐learning graph convolution network is proposed. MIFGA‐C fuses channel semantic information and CAI to guide the learning of channel attention. Extensive ablation studies demonstrate that our proposed MIFGA significantly enhances the baseline model and achieves a competitive performance compared with the state‐of‐the‐art person re‐id methods on standard data sets Market‐1501, DukeMTMC‐reID, and CUHK03.

show abstract

Self-Referenced Deep Learning

Zhu²,

Gong

2019

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Knowledge distillation is an effective approach to transferring knowledge from a teacher neural network to a student target network for satisfying the low-memory and fast running requirements in practice use. Whilst being able to create stronger target networks compared to the vanilla non-teacher based learning strategy, this scheme needs to train additionally a large teacher model with expensive computational cost. In this work, we present a Self-Referenced Deep Learning (SRDL) strategy. Unlike both vanilla optimisation and existing knowledge distillation, SRDL distils the knowledge discovered by the in-training target model back to itself to regularise the subsequent learning procedure therefore eliminating the need for training a large teacher model. SRDL improves the model generalisation performance compared to vanilla learning and conventional knowledge distillation approaches with negligible extra computational cost. Extensive evaluations show that a variety of deep networks benefit from SRDL resulting in enhanced deployment performance on both coarse-grained object categorisation tasks (CIFAR10, CIFAR100, Tiny ImageNet, and ImageNet) and fine-grained person instance identification tasks (Market-1501).

show abstract

Resource Aware Person Re-identification Across Multiple Resolutions

Cited by 249 publications

References 61 publications

An Empirical Study of Person Re-Identification with Attributes

An Empirical Study of Person Re-Identification with Attributes

Topology and channel affinity reinforced global attention for person re‐identification

Self-Referenced Deep Learning

Contact Info

Product

Resources

About