Improved Hard Example Mining by Discovering Attribute-based Hard Person Identity
In this paper, we propose Hard Person Identity Mining (HPIM) that attempts to refine the hard example mining to improve the exploration efficacy in person re-identification. It is motivated by following observation: the more attributes some people share, the more difficult to separate their identities. Based on this observation, we develop HPIM via a transferred attribute describer, a deep multi-attribute classifier trained from the source noisy person attribute datasets. We encode each image into the attribute probabilistic description in the target person re-ID dataset. Afterwards in the attribute code space, we consider each person as a distribution to generate his view-specific attribute codes in different practical scenarios. Hence we estimate the person-specific statistical moments from zeroth to higher order, which are further used to calculate the central moment discrepancies between persons. Such discrepancy is a ground to choose hard identity to organize proper mini-batches, without concerning the person representation changing in metric learning. It presents as a complementary tool of hard example mining, which helps to explore the global instead of the local hard example constraint in the mini-batch built by randomly sampled identities. Extensive experiments on two person re-identification benchmarks validated the effectiveness of our proposed algorithm.
Code (0)
등록된 구현이 없습니다.
Tasks
AttributeMetric LearningPerson Re-IdentificationSimilar Papers 제목 키워드 기반
Class Rectification Hard Mining for Imbalanced Deep Learning
Recognising detailed facial or clothing attributes in images of people is a challenging task for computer vision, especially when the training data are both in very large scale and extremely imbalanced among different at…
AttributeDeep LearningImproved Hard Example Mining Approach for Single Shot Object Detectors
Hard example mining methods generally improve the performance of the object detectors, which suffer from imbalanced training sets. In this work, two existing hard example mining approaches (LRM and focal loss, FL) are ad…
ObjectHard Adversarial Example Mining for Improving Robust Fairness
Adversarial training (AT) is widely considered the state-of-the-art technique for improving the robustness of deep neural networks (DNNs) against adversarial examples (AE). Nevertheless, recent studies have revealed that…
FairnessSeparate and conquer heuristic allows robust mining of contrast sets in classification, regression, and survival data
Identifying differences between groups is one of the most important knowledge discovery problems. The procedure, also known as contrast sets mining, is applied in a wide range of areas like medicine, industry, or economi…
AttributePrognosisregressionUnsupervised Hard Example Mining from Videos for Improved Object Detection
Important gains have recently been obtained in object detection by using training objectives that focus on {\em hard negative} examples, i.e., negative examples that are currently rated as positive or ambiguous by the de…
Face Detectionobject-detectionObject DetectionPedestrian Detection