Person Re-identification by Deep Learning Multi-scale Representations
Yanbei Chen,Xiatian Zhu,Shaogang Gong +2 more
- pp 2590-2600
Reads0
Chats0
TLDR
A novel Deep Pyramid Feature Learning (DPFL) CNN architecture for multi-scale appearance feature fusion optimised simultaneously by concurrent per-scale re-id losses and interactive cross-scale consensus regularisation in a closed-loop design is formulated.Abstract:
Existing person re-identification (re-id) methods depend mostly on single-scale appearance information. This not only ignores the potentially useful explicit information of other different scales, but also loses the chance of mining the implicit correlated complementary advantages across scales. In this work, we demonstrate the benefits of learning multi-scale person appearance features using Convolutional Neural Networks (CNN) by aiming to jointly learn discriminative scale-specific features and maximise multiscale feature fusion selections in image pyramid inputs. Specifically, we formulate a novel Deep Pyramid Feature Learning (DPFL) CNN architecture for multi-scale appearance feature fusion optimised simultaneously by concurrent per-scale re-id losses and interactive cross-scale consensus regularisation in a closed-loop design. Extensive comparative evaluations demonstrate the re-id advantages of the proposed DPFL model over a wide range of state-of-the-art re-id methods on three benchmarks Market-1501, CUHK03, and DukeMTMC-reID.read more
Citations
More filters
Posted Content
In Defense of the Triplet Loss for Person Re-Identification
TL;DR: It is shown that, for models trained from scratch as well as pretrained ones, using a variant of the triplet loss to perform end-to-end deep metric learning outperforms most other published methods by a large margin.
Journal ArticleDOI
Random Erasing Data Augmentation
TL;DR: Random Erasing as mentioned in this paper randomly selects a rectangle region in an image and erases its pixels with random values, which reduces the risk of overfitting and makes the model robust to occlusion.
Book ChapterDOI
Beyond Part Models: Person Retrieval with Refined Part Pooling (and A Strong Convolutional Baseline)
TL;DR: In this paper, a part-based convolutional baseline (PCB) is proposed to learn discriminative part-informed features for person retrieval and two contributions are made: (i) a network named Part-based Convolutional Baseline (PCBB) which outputs a convolutionAL descriptor consisting of several part-level features.
Proceedings ArticleDOI
Learning Discriminative Features with Multiple Granularities for Person Re-Identification
TL;DR: Comprehensive experiments implemented on the mainstream evaluation datasets including Market-1501, DukeMTMC-reid and CUHK03 indicate that the proposed end-to-end feature learning strategy robustly achieves state-of-the-art performances and outperforms any existing approaches by a large margin.
Proceedings ArticleDOI
Harmonious Attention Network for Person Re-identification
Wei Li,Xiatian Zhu,Shaogang Gong +2 more
TL;DR: A novel Harmonious Attention CNN (HA-CNN) model is formulated for joint learning of soft pixel attention and hard regional attention along with simultaneous optimisation of feature representations, dedicated to optimise person re-id in uncontrolled (misaligned) images.
References
More filters
Proceedings ArticleDOI
Deep Residual Learning for Image Recognition
TL;DR: In this article, the authors proposed a residual learning framework to ease the training of networks that are substantially deeper than those used previously, which won the 1st place on the ILSVRC 2015 classification task.
Proceedings Article
ImageNet Classification with Deep Convolutional Neural Networks
TL;DR: The state-of-the-art performance of CNNs was achieved by Deep Convolutional Neural Networks (DCNNs) as discussed by the authors, which consists of five convolutional layers, some of which are followed by max-pooling layers, and three fully-connected layers with a final 1000-way softmax.
Proceedings Article
Very Deep Convolutional Networks for Large-Scale Image Recognition
Karen Simonyan,Andrew Zisserman +1 more
TL;DR: In this paper, the authors investigated the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting and showed that a significant improvement on the prior-art configurations can be achieved by pushing the depth to 16-19 layers.
Journal ArticleDOI
Distinctive Image Features from Scale-Invariant Keypoints
TL;DR: This paper presents a method for extracting distinctive invariant features from images that can be used to perform reliable matching between different views of an object or scene and can robustly identify objects among clutter and occlusion while achieving near real-time performance.
Proceedings ArticleDOI
Histograms of oriented gradients for human detection
Navneet Dalal,Bill Triggs +1 more
TL;DR: It is shown experimentally that grids of histograms of oriented gradient (HOG) descriptors significantly outperform existing feature sets for human detection, and the influence of each stage of the computation on performance is studied.