Related papers: Distribution Alignment: A Unified Framework for Lo…
Graph classification, aiming at learning the graph-level representations for effective class assignments, has received outstanding achievements, which heavily relies on high-quality datasets that have balanced class distribution. In fact,…
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…
Real world data often exhibits a long-tailed and open-ended (with unseen classes) distribution. A practical recognition system must balance between majority (head) and minority (tail) classes, generalize across the distribution, and…
Long-tailed data is still a big challenge for deep neural networks, even though they have achieved great success on balanced data. We observe that vanilla training on long-tailed data with cross-entropy loss makes the instance-rich head…
Long-tailed recognition with imbalanced class distribution naturally emerges in practical machine learning applications. Existing methods such as data reweighing, resampling, and supervised contrastive learning enforce the class balance…
Most of the medical tasks naturally exhibit a long-tailed distribution due to the complex patient-level conditions and the existence of rare diseases. Existing long-tailed learning methods usually treat each class equally to re-balance the…
Continual learning (CL) with long-tailed data distributions remains a critical challenge for real-world AI systems, where models must sequentially adapt to new classes while retaining knowledge of old ones, despite severe class imbalance.…
In the real open world, data tends to follow long-tailed class distributions, motivating the well-studied long-tailed recognition (LTR) problem. Naive training produces models that are biased toward common classes in terms of higher…
Deep learning-based models encounter challenges when processing long-tailed data in the real world. Existing solutions usually employ some balancing strategies or transfer learning to deal with the class imbalance problem, based on the…
Long-tailed problem has been an important topic in face recognition task. However, existing methods only concentrate on the long-tailed distribution of classes. Differently, we devote to the long-tailed domain distribution problem, which…
Long-tailed imbalance distribution is a common issue in practical computer vision applications. Previous works proposed methods to address this problem, which can be categorized into several classes: re-sampling, re-weighting, transfer…
Natural data are often long-tail distributed over semantic classes. Existing recognition methods tackle this imbalanced classification by placing more emphasis on the tail data, through class re-balancing/re-weighting or ensembling over…
Solving long-tail large vocabulary object detection with deep learning based models is a challenging and demanding task, which is however under-explored.In this work, we provide the first systematic analysis on the underperformance of…
Most existing object instance detection and segmentation models only work well on fairly balanced benchmarks where per-category training sample numbers are comparable, such as COCO. They tend to suffer performance drop on realistic datasets…
Long-tailed recognition is ubiquitous and challenging in deep learning and even in the downstream finetuning of foundation models, since the skew class distribution generally prevents the model generalization to the tail classes. Despite…
Deep learning enables impressive performance in image recognition using large-scale artificially-balanced datasets. However, real-world datasets exhibit highly class-imbalanced distributions, yielding two main challenges: relative imbalance…
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…
Active learning aims to reduce the labeling effort that is required to train algorithms by learning an acquisition function selecting the most relevant data for which a label should be requested from a large unlabeled data pool. Active…
Main challenges in long-tailed recognition come from the imbalanced data distribution and sample scarcity in its tail classes. While techniques have been proposed to achieve a more balanced training loss and to improve tail classes data…
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…