Related papers: Range Loss for Deep Face Recognition with Long-tai…

Learning with a {\it convex loss} function has been a dominating paradigm for many years. It remains an interesting question how non-convex loss functions help improve the generalization of learning with broad applicability. In this paper,…

While the novel class discovery has recently made great progress, existing methods typically focus on improving algorithms on class-balanced benchmarks. However, in real-world recognition tasks, the class distributions of their…

The performance of face recognition system degrades when the variability of the acquired faces increases. Prior work alleviates this issue by either monitoring the face quality in pre-processing or predicting the data uncertainty along with…

Machine unlearning, which aims to efficiently remove the influence of specific data from trained models, is crucial for upholding data privacy regulations like the ``right to be forgotten". However, existing research predominantly evaluates…

Recently, large-scale pre-trained vision-language models have presented benefits for alleviating class imbalance in long-tailed recognition. However, the long-tailed data distribution can corrupt the representation space, where the distance…

Instance segmentation has witnessed a remarkable progress on class-balanced benchmarks. However, they fail to perform as accurately in real-world scenarios, where the category distribution of objects naturally comes with a long tail.…

Convolutional neural networks require numerous data for training. Considering the difficulties in data collection and labeling in some specific tasks, existing approaches generally use models pre-trained on a large source domain (e.g.…

Long-tailed distributions in class-imbalanced data present a fundamental challenge for deep learning models, which tend to be biased toward majority classes. While recent methods for long-tailed recognition have mitigated this issue, they…

The training datasets used in long-tailed recognition are extremely unbalanced, resulting in significant variation in per-class accuracy across categories. Prior works mostly used average accuracy to evaluate their algorithms, which easily…

In the real world, medical datasets often exhibit a long-tailed data distribution (i.e., a few classes occupy most of the data, while most classes have rarely few samples), which results in a challenging imbalance learning scenario. For…

This paper proposes a deep representation learning using an information-theoretic loss with an aim to increase the inter-class distances as well as within-class similarity in the embedded space. Tasks such as anomaly and out-of-distribution…

Long-tailed class distributions are prevalent among the practical applications of object detection and instance segmentation. Prior work in long-tail instance segmentation addresses the imbalance of losses between rare and frequent…

Skeleton-based action recognition has recently made significant progress. However, data imbalance is still a great challenge in real-world scenarios. The performance of current action recognition algorithms declines sharply when training…

Deep long-tailed learning aims to train useful deep networks on practical, real-world imbalanced distributions, wherein most labels of the tail classes are associated with a few samples. There has been a large body of work to train…

The generalization gap on the long-tailed data sets is largely owing to most categories only occupying a few training samples. Decoupled training achieves better performance by training backbone and classifier separately. What causes the…

The natural world often follows a long-tailed data distribution where only a few classes account for most of the examples. This long-tail causes classifiers to overfit to the majority class. To mitigate this, prior solutions commonly adopt…

Pre-training plays a vital role in various vision tasks, such as object recognition and detection. Commonly used pre-training methods, which typically rely on randomized approaches like uniform or Gaussian distributions to initialize model…

Federated Learning (FL) has become a popular distributed learning paradigm that involves multiple clients training a global model collaboratively in a data privacy-preserving manner. However, the data samples usually follow a long-tailed…

Deep classifiers have achieved great success in visual recognition. However, real-world data is long-tailed by nature, leading to the mismatch between training and testing distributions. In this paper, we show that the Softmax function,…

With the recent development of deep convolutional neural networks and large-scale datasets, deep face recognition has made remarkable progress and been widely used in various applications. However, unlike the existing public face datasets,…