全文链接：
http://openaccess.thecvf.com/content_ICCV_2019/html/Luo_Spectral_Feature_Transformation_for_Person_Re-Identification_ICCV_2019_paper.html

The source code is here.

Introduction

• The two most prevalent types of loss functions in ReID are classification loss (e.g. softmax cross entropy loss) and metric learning based loss (e.g. triplet loss and contrastive loss):

  1. Classification loss has promising convergence but is vulnerable to overfitting. It processes samples individually and only builds connections implicitly through the classifier.

  2. Metric learning based loss explicitly optimizes the distances between samples. While the similarity structure it builds only involves a pair/triplet of data points and ignores other informative samples. This leads to a large proportion of trivial pairs/triplets which could overwhelm the training process and eventually makes the model suffer from slow convergence.

• Most existing methods process data points individually or only involves a fraction of samples while building a similarity structure. They ignore dense informative connections among samples more or less. The lack of holistic observation eventually leads to inferior performance. To relieve the issue, we propose to formulate the whole data batch as a similarity graph.

全文链接：
http://openaccess.thecvf.com/content_ICCV_2019/html/Yu_Robust_Person_Re-Identification_by_Modelling_Feature_Uncertainty_ICCV_2019_paper.html

The source code is here.

Challenges

• Two types of noise are prevalent in practice:

  1. label noise caused by human annotator errors, i.e., people assigned with the wrong identities

  2. data outliers caused by person detector errors or occlusion

• Having both types of noisy samples in a training set inevitably has a detrimental effect on the learned feature embedding:

Noisy samples are often far from inliers of the same class in the input (image) space.

To minimise intra-class distance and pull the noisy samples close to their class centre, a ReID model often needs to sacrifice inter-class separability, leading to performance degradation.

全文链接：
https://www.semanticscholar.org/paper/Batch-DropBlock-Network-for-Person-and-Beyond-Dai-Chen/2e4e3d80e0a789dcf45e61401c8af4e3fa96dfea

Challenges

• the large variation of poses, background, illumination, camera conditions and view angle changes

• Because the body parts such as faces, hands and feet are unstable as the view angle changes, the CNN tends to focus on the main body part and the other descriminative body parts, i.e., some attentive local features are consequently suppressed.

Related Work

1. Pose-based works seek to localize different body parts and align their associated features.

2. Part-based works use coarse partitions or attention selection network to improve feature learning.

Motivation

1. Pose-based networks usually require additional body pose or segment information.

2. These networks are designed using specific partition mechanisms, such as a horizontal partition, which is fit for person re-ID but hard to be generalized to other metric learning tasks.

全文链接：
http://openaccess.thecvf.com/content_ICCV_2019/html/Wu_Unsupervised_Graph_Association_for_Person_Re-Identification_ICCV_2019_paper.html

The source code is here.

Introduction

Chanllenge One

Since in supervised learning deep CNN is a data-driven method, it requires a large number of pair-wise labelled data in training to learn view-invariant representations. However, labelling sufficient pairwise RE-ID data is expensive and time-consuming. How to improve the performance and scalability of deep RE-ID algorithm without pair-wise labelled data (i.e., unsupervised learning) is a great challenge in recent person RE-ID research.

Related Work

There have been a series of unsupervised image based methods to address this problem, which can be roughly divided into three categories:

1. image-to-image translation

   transfer the source domain images to the target domain by GAN network

2. domain adaptation

   transfer the source domain trained model to the target domain in an unsupervised manner

3. unsupervised clustering

   obtain the pseudo labels of target domain data through the unsupervised clustering algorithms and fine tune the source domain model with pseudo labels on target domain.

Chanllenge Two

The precondition of above mentioned methods is that there are some similarities between the source domain and the target domain.

Beyond Human Parts: Dual Part-Aligned Representations for Person Re-Identification

全文链接：
http://openaccess.thecvf.com/content_ICCV_2019/html/Guo_Beyond_Human_Parts_Dual_Part-Aligned_Representations_for_Person_Re-Identification_ICCV_2019_paper.html

The source code is here.

Challenges - Misalignment Problem

The significant visual appearance changes caused by:

1. human pose variation

2. lighting conditions

3. part occlusions

4. background cluttering

5. distinct camera viewpoints ……

Related Work

1. Hand-crafted partitioning

   relies on manually designed splits of the input image or the feature maps into grid cells or horizontal stripes, based on the assumption that the human parts are well-aligned in the RGB color space

2. The attention mechanism

   tries to learn an attention map over the last output feature map and constructs the aligned part features accordingly

3. Predicting a set of predefined attributes as useful features to guide the matching process.

4. Injecting human pose estimation or human parsing results to extract the human part aligned features based on the predicted human key points or semantic human part regions, while the success of such approaches heavily counts on the accuracy of human parsing models or pose estimators.

Motivation

Most of the previous studies mainly focus on learning more accurate human part representations, while neglecting the influence of potentially useful contextual cues that could be addressed as “non-human” parts.

Beyond these predefined part categories, there still exist many objects or parts which could be critical for person re-identification, but tend to be recognized as background by the pre-trained human parsing models.