Central Feature Learning for Unsupervised Person Re-identification

2021 ◽  
pp. 2151007
Author(s):  
Binquan Wang ◽  
Muhammad Asim ◽  
Guoqi Ma ◽  
Ming Zhu
Keyword(s):  
Learning Strategy ◽  
Feature Learning ◽  
Feature Space ◽  
Error Prediction ◽  
Central Feature ◽  
Memory Module ◽  
Prediction Module ◽  
Similar Images ◽  
The Stability ◽  
Error Memory

The Exemplar Memory (EM) design has shown its effectiveness in facilitating the unsupervised person re-identification (RE-ID). However, there are obvious defects in the update strategies with most existing results, such as the inability to eliminate static errors and ensure convergence stability of learning. To address these issues, in this paper, we propose a novel center feature learning scheme to improve the update strategies of the traditional EM design for unsupervised RE-ID problems. First, the EM module is regarded as a center feature of a cluster of images, then the goal is transformed into pulling the similar images close to while pushing the dissimilar images away from the center feature space. Second, in order to provide effective guidelines on reducing static errors, we propose an error-memory module to improve the central feature learning performances. In addition, an error-prediction module is designed as well to ensure the stability of convergence. Besides, a camera-invariance learning strategy is also introduced to further improve the proposed algorithm. Finally, extensive comparative experiments are conducted on Market-1501 and DukeMTMC-reID datasets to demonstrate the effectiveness and improvements of the proposed method over existing results. The code of this work is available at https://github.com/binquanwang/CFL_master .

scholarly journals Review of claudin proteins as potential biomarkers for necrotizing enterocolitis

2021 ◽  
Author(s):  
Victoria Griffiths ◽  
Niazy Al Assaf ◽  
Rizwan Khan
Keyword(s):  
Necrotizing Enterocolitis ◽  
Intestinal Permeability ◽  
Central Feature ◽  
Search Terms ◽  
Area Of Interest ◽  
Noninvasive Biomarker ◽  
Current Area ◽  
The Stability ◽  
Human Neonates ◽  
A Current

Abstract Background Claudin proteins are a component of tight junctions found in cell-cell adhesion complexes. A central feature of necrotizing enterocolitis (NEC) is intestinal permeability, with changes to claudin proteins potentially contributing to intestinal instability, inflammation, and the progression of NEC. A current area of interest is the development of a novel, noninvasive biomarker for the detection of NEC in neonates at risk of developing this disease, in order to reduce morbidity and mortality through earlier intervention. Aims This review aims to explore the relevance of claudin proteins in the pathophysiology of NEC and their potential usefulness as a biomarker. Methods This review was conducted using the search terms “claudin” + “necrotizing enterocolitis”, with 27 papers selected for review. Results Claudin proteins appear to have a role in the stability of the gut epithelium through the regulation of intestinal permeability, maturity, and inflammation. Formula feeding has been shown to promote inflammation and result in changes to claudin proteins, while breastfeeding and certain nutritional supplements lead to reduced inflammation and improved intestinal stability as demonstrated through changes to claudin protein expression. Preliminary studies in human neonates suggest that urinary claudin measurements may be used to predict the development of NEC. Conclusions Alterations to claudin proteins may reflect changes seen to intestinal permeability and inflammation in the context of NEC. Further research is necessary to understand the relevance of claudin proteins in the pathophysiology of NEC and their use as a biomarker.

scholarly journals Part-Aware Mask-Guided Attention for Thorax Disease Classification

Entropy ◽  
2021 ◽  
Vol 23 (6) ◽  
pp. 653
Author(s):  
Ruihua Zhang ◽  
Fan Yang ◽  
Yan Luo ◽  
Jianyi Liu ◽  
Jinbin Li ◽  
...  
Keyword(s):  
Visual Cues ◽  
Learning Strategy ◽  
Feature Learning ◽  
Classification Performance ◽  
Disease Classification ◽  
Feature Representations ◽  
Chest X Ray ◽  
Global And Local ◽  
Aided Diagnosis ◽  
Single Organ

Thorax disease classification is a challenging task due to complex pathologies and subtle texture changes, etc. It has been extensively studied for years largely because of its wide application in computer-aided diagnosis. Most existing methods directly learn global feature representations from whole Chest X-ray (CXR) images, without considering in depth the richer visual cues lying around informative local regions. Thus, these methods often produce sub-optimal thorax disease classification performance because they ignore the very informative pathological changes around organs. In this paper, we propose a novel Part-Aware Mask-Guided Attention Network (PMGAN) that learns complementary global and local feature representations from all-organ region and multiple single-organ regions simultaneously for thorax disease classification. Specifically, multiple innovative soft attention modules are designed to progressively guide feature learning toward the global informative regions of whole CXR image. A mask-guided attention module is designed to further search for informative regions and visual cues within the all-organ or single-organ images, where attention is elegantly regularized by automatically generated organ masks and without introducing computation during the inference stage. In addition, a multi-task learning strategy is designed, which effectively maximizes the learning of complementary local and global representations. The proposed PMGAN has been evaluated on the ChestX-ray14 dataset and the experimental results demonstrate its superior thorax disease classification performance against the state-of-the-art methods.

Rapid Technique Correction Using Old Way/new Way: Two Case Studies with Olympic Athletes

2002 ◽  
Vol 16 (1) ◽  
pp. 79-99 ◽  
Author(s):  
Yuri Hanin ◽  
Tapio Korjus ◽  
Petteri Jouste ◽  
Paul Baxter
Keyword(s):  
Performance Enhancement ◽  
Learning Strategy ◽  
Cognitive Learning ◽  
Movement Pattern ◽  
Adaptation Period ◽  
Olympic Athletes ◽  
Video Recordings ◽  
Self Reports ◽  
Single Learning Trial ◽  
Error Memory

Exploratory studies examine the effectiveness of old way/new way, an innovative meta-cognitive learning strategy initially developed in education settings, in the rapid and permanent correction of established technique difficulties experienced by two Olympic athletes in javelin and sprinting. Individualized interventions included video-assisted error analysis, step-wise enhancement of kinesthetic awareness, reactivation of the error memory, discrimination, and generalization of the correct movement pattern. Self-reports, coach’s ratings, and video recordings were used as measures of technique improvement. A single learning trial produced immediate and permanent technique improvement (80% or higher correct action) and full transfer of learning, without the need for the customary adaptation period. Findings are consistent with the performance enhancement effects of old way/new way demonstrated experimentally in nonsport settings.

INVARIANT OBJECT RECOGNITION BASED ON A NEURAL NETWORK OF CASCADED RCE NETS

1993 ◽  
Vol 07 (04) ◽  
pp. 815-829 ◽  
Author(s):  
WEI LI ◽  
NASSER M. NASRABADI
Keyword(s):  
Neural Network ◽  
Learning Strategy ◽  
Feature Vector ◽  
Recognition Rate ◽  
Feature Space ◽  
Recognition System ◽  
Coulomb Energy ◽  
Geometrical Shape ◽  
Shape Information ◽  
Shift Rotation

A neural network of cascaded Restricted Coulomb Energy (RCE) nets is constructed for the recognition of two-dimensional objects. A number of RCE nets are cascaded together to form a classifier where the overlapping decision regions are progressively resolved by a set of cascaded networks. Similarities among objects which have complex decision boundaries in the feature space are resolved by this multi-net approach. The generalization ability of an RCE net recognition system, referring to the ability of the system to correctly recognize a new pattern even when the number of learning exemplars is small, is increased by the proposed coarse-to-fine learning strategy. A feature extraction technique is used to map the geometrical shape information of an object into an ordered feature vector of fixed length. This feature vector is then used as an input to the neural network. The feature vector is invariant to object changes such as positional shift, rotation, scaling, illumination variance, variation of camera setup, perspective distortion, and noise distortion. Experimental results for recognition of several objects are also presented. A correct recognition rate of 100% was achieved for both the training and the testing input patterns.

scholarly journals Learning Uniform Semantic Features for Natural Language and Programming Language Globally, Locally and Sequentially

2019 ◽  
Vol 33 ◽  
pp. 5845-5852
Author(s):  
Yudong Zhang ◽  
Wenhao Zheng ◽  
Ming Li
Keyword(s):  
Natural Language ◽  
Programming Language ◽  
Semantic Representation ◽  
Feature Learning ◽  
Feature Space ◽  
General Purpose ◽  
Semantic Features ◽  
Textual Data ◽  
Software Mining ◽  
Sequential Information

Semantic feature learning for natural language and programming language is a preliminary step in addressing many software mining tasks. Many existing methods leverage information in lexicon and syntax to learn features for textual data. However, such information is inadequate to represent the entire semantics in either text sentence or code snippet. This motivates us to propose a new approach to learn semantic features for both languages, through extracting three levels of information, namely global, local and sequential information, from textual data. For tasks involving both modalities, we project the data of both types into a uniform feature space so that the complementary knowledge in between can be utilized in their representation. In this paper, we build a novel and general-purpose feature learning framework called UniEmbed, to uniformly learn comprehensive semantic representation for both natural language and programming language. Experimental results on three real-world software mining tasks show that UniEmbed outperforms state-of-the-art models in feature learning and prove the capacity and effectiveness of our model.

KNN Loss and Deep KNN

2021 ◽  
Vol 182 (2) ◽  
pp. 95-110
Author(s):  
Linh Le ◽  
Ying Xie ◽  
Vijay V. Raghavan
Keyword(s):  
Deep Learning ◽  
Supervised Learning ◽  
Nearest Neighbor ◽  
Learning Strategy ◽  
Feature Space ◽  
Kernel Functions ◽  
Training Data ◽  
K Nearest Neighbor ◽  
Map Data

The k Nearest Neighbor (KNN) algorithm has been widely applied in various supervised learning tasks due to its simplicity and effectiveness. However, the quality of KNN decision making is directly affected by the quality of the neighborhoods in the modeling space. Efforts have been made to map data to a better feature space either implicitly with kernel functions, or explicitly through learning linear or nonlinear transformations. However, all these methods use pre-determined distance or similarity functions, which may limit their learning capacity. In this paper, we present two loss functions, namely KNN Loss and Fuzzy KNN Loss, to quantify the quality of neighborhoods formed by KNN with respect to supervised learning, such that minimizing the loss function on the training data leads to maximizing KNN decision accuracy on the training data. We further present a deep learning strategy that is able to learn, by minimizing KNN loss, pairwise similarities of data that implicitly maps data to a feature space where the quality of KNN neighborhoods is optimized. Experimental results show that this deep learning strategy (denoted as Deep KNN) outperforms state-of-the-art supervised learning methods on multiple benchmark data sets.

scholarly journals Cross-Modality 2D-3D Face Recognition via Multiview Smooth Discriminant Analysis Based on ELM

2014 ◽  
Vol 2014 ◽  
pp. 1-9 ◽  
Author(s):  
Yi Jin ◽  
Jiuwen Cao ◽  
Qiuqi Ruan ◽  
Xueqiao Wang
Keyword(s):  
Face Recognition ◽  
Discriminant Analysis ◽  
Feature Learning ◽  
Feature Space ◽  
Feedforward Neural Networks ◽  
3D Face Recognition ◽  
3D Face ◽  
Face Features ◽  
Fast Training ◽  
Learning Machine

In recent years, 3D face recognition has attracted increasing attention from worldwide researchers. Rather than homogeneous face data, more and more applications require flexible input face data nowadays. In this paper, we propose a new approach for cross-modality 2D-3D face recognition (FR), which is called Multiview Smooth Discriminant Analysis (MSDA) based on Extreme Learning Machines (ELM). Adding the Laplacian penalty constrain for the multiview feature learning, the proposed MSDA is first proposed to extract the cross-modality 2D-3D face features. The MSDA aims at finding a multiview learning based common discriminative feature space and it can then fully utilize the underlying relationship of features from different views. To speed up the learning phase of the classifier, the recent popular algorithm named Extreme Learning Machine (ELM) is adopted to train the single hidden layer feedforward neural networks (SLFNs). To evaluate the effectiveness of our proposed FR framework, experimental results on a benchmark face recognition dataset are presented. Simulations show that our new proposed method generally outperforms several recent approaches with a fast training speed.

scholarly journals Partial Label Learning via Label Enhancement

2019 ◽  
Vol 33 ◽  
pp. 5557-5564 ◽  
Author(s):  
Ning Xu ◽  
Jiaqi Lv ◽  
Xin Geng
Keyword(s):  
Predictive Model ◽  
Learning Strategy ◽  
Feature Space ◽  
Ground Truth ◽  
Learning Approaches ◽  
Topological Information ◽  
Common Strategy ◽  
Training Examples ◽  
Partial Label Learning ◽  
Label Distribution

Partial label learning aims to learn from training examples each associated with a set of candidate labels, among which only one label is valid for the training example. The common strategy to induce predictive model is trying to disambiguate the candidate label set, such as disambiguation by identifying the ground-truth label iteratively or disambiguation by treating each candidate label equally. Nonetheless, these strategies ignore considering the generalized label distribution corresponding to each instance since the generalized label distribution is not explicitly available in the training set. In this paper, a new partial label learning strategy named PL-LE is proposed to learn from partial label examples via label enhancement. Specifically, the generalized label distributions are recovered by leveraging the topological information of the feature space. After that, a multi-class predictive model is learned by fitting a regularized multi-output regressor with the generalized label distributions. Extensive experiments show that PL-LE performs favorably against state-ofthe-art partial label learning approaches.

Sign in / Sign up

Export Citation Format

Share Document