Related papers: Prior2Posterior: Model Prior Correction for Long-T…
In scenarios with long-tailed distributions, the model's ability to identify tail classes is limited due to the under-representation of tail samples. Class rebalancing, information augmentation, and other techniques have been proposed to…
How to estimate the uncertainty of a given model is a crucial problem. Current calibration techniques treat different classes equally and thus implicitly assume that the distribution of training data is balanced, but ignore the fact that…
We propose GradTail, an algorithm that uses gradients to improve model performance on the fly in the face of long-tailed training data distributions. Unlike conventional long-tail classifiers which operate on converged - and possibly…
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 imbalanced distribution of long-tailed data presents a considerable challenge for deep learning models, as it causes them to prioritize the accurate classification of head classes but largely disregard tail classes. The biased decision…
Long-tailed classification, where a small number of frequent classes dominate many rare ones, remains challenging because models systematically favor frequent classes at inference time. Existing post-hoc methods such as logit adjustment…
Conformal prediction has emerged as a rigorous means of providing deep learning models with reliable uncertainty estimates and safety guarantees. Yet, its performance is known to degrade under distribution shift and long-tailed class…
Real-world visual data often exhibits a long-tailed distribution, where some ''head'' classes have a large number of samples, yet only a few samples are available for ''tail'' classes. Such imbalanced distribution causes a great challenge…
Many data distributions in the real world are hardly uniform. Instead, skewed and long-tailed distributions of various kinds are commonly observed. This poses an interesting problem for machine learning, where most algorithms assume or work…
Long-tailed relation classification is a challenging problem as the head classes may dominate the training phase, thereby leading to the deterioration of the tail performance. Existing solutions usually address this issue via…
Methods in long-tail learning focus on improving performance for data-poor (rare) classes; however, performance for such classes remains much lower than performance for more data-rich (frequent) classes. Analyzing the predictions of…
Real-world datasets often exhibit long-tailed distributions, where a few dominant "Head" classes have abundant samples while most "Tail" classes are severely underrepresented, leading to biased learning and poor generalization for the Tail.…
Unlike the case when using a balanced training dataset, the per-class recall (i.e., accuracy) of neural networks trained with an imbalanced dataset are known to vary a lot from category to category. The convention in long-tailed recognition…
Diffusion models have made significant advances recently in high-quality image synthesis and related tasks. However, diffusion models trained on real-world datasets, which often follow long-tailed distributions, yield inferior fidelity for…
Balancing training on long-tail data distributions remains a long-standing challenge in deep learning. While methods such as re-weighting and re-sampling help alleviate the imbalance issue, limited sample diversity continues to hinder…
The real-world data distribution is essentially long-tailed, which poses great challenge to the deep model. In this work, we propose a new method, Gradual Balanced Loss and Adaptive Feature Generator (GLAG) to alleviate imbalance. GLAG…
Real-world data often exhibits a long-tailed distribution, in which head classes occupy most of the data, while tail classes only have very few samples. Models trained on long-tailed datasets have poor adaptability to tail classes and the…
Although contrastive learning methods have shown prevailing performance on a variety of representation learning tasks, they encounter difficulty when the training dataset is long-tailed. Many researchers have combined contrastive learning…
Recognition problems in long-tailed data, in which the sample size per class is heavily skewed, have gained importance because the distribution of the sample size per class in a dataset is generally exponential unless the sample size is…
Most existing methods that cope with noisy labels usually assume that the class distributions are well balanced, which has insufficient capacity to deal with the practical scenarios where training samples have imbalanced distributions. To…