Class Rectification Hard Mining for Imbalanced Deep Learning
Qi Dong,Shaogang Gong,Xiatian Zhu +2 more
- pp 1869-1878
Reads0
Chats0
TLDR
This work develops an end-to-end deep learning framework capable of avoiding the dominant effect of majority classes by discovering sparsely sampled boundaries of minority classes by introducing a Class Rectification Loss (CRL) regularising algorithm.Abstract:
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 attribute classes. To address this problem, we formulate a novel scheme for batch incremental hard sample mining of minority attribute classes from imbalanced large scale training data. We develop an end-to-end deep learning framework capable of avoiding the dominant effect of majority classes by discovering sparsely sampled boundaries of minority classes. This is made possible by introducing a Class Rectification Loss (CRL) regularising algorithm. We demonstrate the advantages and scalability of CRL over existing state-of-the-art attribute recognition and imbalanced data learning models on two large scale imbalanced benchmark datasets, the CelebA facial attribute dataset and the X-Domain clothing attribute dataset.read more
Citations
More filters
Proceedings ArticleDOI
Class-Balanced Loss Based on Effective Number of Samples
TL;DR: This work designs a re-weighting scheme that uses the effective number of samples for each class to re-balance the loss, thereby yielding a class-balanced loss and introduces a novel theoretical framework to measure data overlap by associating with each sample a small neighboring region rather than a single point.
Proceedings ArticleDOI
Large-Scale Long-Tailed Recognition in an Open World
TL;DR: An integrated OLTR algorithm is developed that maps an image to a feature space such that visual concepts can easily relate to each other based on a learned metric that respects the closed-world classification while acknowledging the novelty of the open world.
Proceedings ArticleDOI
Learning a Unified Classifier Incrementally via Rebalancing
TL;DR: This work develops a new framework for incrementally learning a unified classifier, e.g. a classifier that treats both old and new classes uniformly, and incorporates three components, cosine normalization, less-forget constraint, and inter-class separation, to mitigate the adverse effects of the imbalance.
Posted Content
Meta-Weight-Net: Learning an Explicit Mapping For Sample Weighting
TL;DR: Synthetic and real experiments substantiate the capability of the method for achieving proper weighting functions in class imbalance and noisy label cases, fully complying with the common settings in traditional methods, and more complicated scenarios beyond conventional cases.
Journal ArticleDOI
Imbalance Problems in Object Detection: A Review
TL;DR: A comprehensive review of the imbalance problems in object detection is presented in this article, where the authors introduce a problem-based taxonomy and discuss each problem in depth and present a unifying yet critical perspective on the solutions in the literature.
References
More filters
Proceedings ArticleDOI
Attribute-based People Search: Lessons Learnt from a Practical Surveillance System
TL;DR: It is shown that a novel set of multimodal integral filters and proper normalization of attribute scores are critical to obtain good performance in the problem of attribute-based people search in real surveillance environments.
Proceedings ArticleDOI
Multi-task Curriculum Transfer Deep Learning of Clothing Attributes
TL;DR: A novel Multi-Task Curriculum Transfer (MTCT) deep learning method to explore multiple sources of different types of web annotations with multi-labelled fine-grained attributes for model transfer learning from well-controlled shop clothing images collected from web retailers to in-the-wild images from the street.
Posted Content
Multi-Task Curriculum Transfer Deep Learning of Clothing Attributes
TL;DR: In this paper, a multi-task curriculum transfer (MTCT) deep learning method was proposed to explore multiple sources of different types of web annotations with multi-labelled fine-grained attributes.