Related papers: Rectify the Regression Bias in Long-Tailed Object …
Machine learning models fail to perform well on real-world applications when 1) the category distribution P(Y) of the training dataset suffers from long-tailed distribution and 2) the test data is drawn from different conditional…
The fine-tuning paradigm in addressing long-tail learning tasks has sparked significant interest since the emergence of foundation models. Nonetheless, how fine-tuning impacts performance in long-tail learning was not explicitly quantified.…
Long-tail learning has received significant attention in recent years due to the challenge it poses with extremely imbalanced datasets. In these datasets, only a few classes (known as the head classes) have an adequate number of training…
Long-tailed object detection (LTOD) aims to handle the extreme data imbalance in real-world datasets, where many tail classes have scarce instances. One popular strategy is to explore extra data with image-level labels, yet it produces…
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…
Real-world data typically follow a long-tailed distribution, where a few majority categories occupy most of the data while most minority categories contain a limited number of samples. Classification models minimizing cross-entropy struggle…
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 world is long-tailed. What does this mean for computer vision and visual recognition? The main two implications are (1) the number of categories we need to consider in applications can be very large, and (2) the number of training…
When trained with severely imbalanced data, deep neural networks often struggle to accurately recognize classes with only a few samples. Previous studies in long-tailed recognition have attempted to rebalance biased learning using known…
Long-tailed (LT) classification is an unavoidable and challenging problem in the real world. Most existing long-tailed classification methods focus only on solving the class-wise imbalance while ignoring the attribute-wise imbalance. The…
Real-world data usually present long-tailed distributions. Training on imbalanced data tends to render neural networks perform well on head classes while much worse on tail classes. The severe sparseness of training instances for the tail…
In the real-world setting, data often follows a long-tailed distribution, where head classes contain significantly more training samples than tail classes. Consequently, models trained on such data tend to be biased toward head classes. The…
Long-tail class incremental learning (LT CIL) remains highly challenging because the scarcity of samples in tail classes not only hampers their learning but also exacerbates catastrophic forgetting under continuously evolving and imbalanced…
Existing long-tailed recognition methods, aiming to train class-balanced models from long-tailed data, generally assume the models would be evaluated on the uniform test class distribution. However, practical test class distributions often…
In this paper, our goal is to design a simple learning paradigm for long-tail visual recognition, which not only improves the robustness of the feature extractor but also alleviates the bias of the classifier towards head classes while…
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…
Beyond class frequency, we recognize the impact of class-wise relationships among various class-specific predictions and the imbalance in label masks on long-tailed segmentation learning. To address these challenges, we propose an…
In the real world, long-tailed data distributions are prevalent, making it challenging for models to effectively learn and classify tail classes. However, we discover that in the field of drug chemistry, certain tail classes exhibit higher…
Recognizing images with long-tailed distributions remains a challenging problem while there lacks an interpretable mechanism to solve this problem. In this study, we formulate Long-tailed recognition as Domain Adaption (LDA), by modeling…
Existing methods for object detection in UAV images ignored an important challenge - imbalanced class distribution in UAV images - which leads to poor performance on tail classes. We systematically investigate existing solutions to…