Related papers: Neural Collapse Inspired Attraction-Repulsion-Bala…

Despite extensive research spanning several decades, class imbalance is still considered a profound difficulty for both machine learning and deep learning models. While data oversampling is the foremost technique to address this issue,…

Most existing object detectors suffer from class imbalance problems that hinder balanced performance. In particular, anchor free object detectors have to solve the background imbalance problem due to detection in a per-pixel prediction…

Label noise and class imbalance commonly coexist in real-world data. Previous works for robust learning, however, usually address either one type of the data biases and underperform when facing them both. To mitigate this gap, this work…

Active Learning for discriminative models has largely been studied with the focus on individual samples, with less emphasis on how classes are distributed or which classes are hard to deal with. In this work, we show that this is harmful.…

Semi-supervised learning (SSL), thanks to the significant reduction of data annotation costs, has been an active research topic for large-scale 3D scene understanding. However, the existing SSL-based methods suffer from severe training…

Automatic target recognition (ATR) is an important use case for synthetic aperture radar (SAR) image interpretation. Recent years have seen significant advancements in SAR ATR technology based on semi-supervised learning. However, existing…

Back-propagation is a popular machine learning algorithm that uses gradient descent in training neural networks for supervised learning, but can be very slow. A number of algorithms have been developed to speed up convergence and improve…

Class-imbalance is a common problem in machine learning practice. Typical Imbalanced Learning (IL) methods balance the data via intuitive class-wise resampling or reweighting. However, previous studies suggest that beyond class-imbalance,…

Instance-sensitive losses for semantic segmentation such as blob loss and CC loss were designed to address instance imbalance, ensuring small lesions generate the same gradient as large ones, but operate only on single-class segmentation.…

Spurious correlations that lead models to correct predictions for the wrong reasons pose a critical challenge for robust real-world generalization. Existing research attributes this issue to group imbalance and addresses it by maximizing…

With the rapid growth of memory and computing power, datasets are becoming increasingly complex and imbalanced. This is especially severe in the context of clinical data, where there may be one rare event for many cases in the majority…

Multi-task learning aims to learn multiple related tasks simultaneously and has achieved great success in various fields. However, the disparity in loss and gradient scales among tasks often leads to performance compromises, and the…

Corrupted labels and class imbalance are commonly encountered in practically collected training data, which easily leads to over-fitting of deep neural networks (DNNs). Existing approaches alleviate these issues by adopting a sample…

Multi-label class-incremental learning (MLCIL) is essential for real-world multi-label applications, allowing models to learn new labels while retaining previously learned knowledge continuously. However, recent MLCIL approaches can only…

Sampling-based path planning algorithms play an important role in autonomous robotics. However, a common problem among these algorithms is that the initial path generated is not optimal, and the convergence is too slow for real-world…

Deep neural networks may perform poorly when training datasets are heavily class-imbalanced. Recently, two-stage methods decouple representation learning and classifier learning to improve performance. But there is still the vital issue of…

There are many real-world classification problems wherein the issue of data imbalance (the case when a data set contains substantially more samples for one/many classes than the rest) is unavoidable. While under-sampling the problematic…

Class imbalance is a widespread challenge in NLP tasks, significantly hindering robust performance across diverse domains and applications. We introduce Hardness-Aware Meta-Resample (HAMR), a unified framework that adaptively addresses both…

One-stage object detectors are trained by optimizing classification-loss and localization-loss simultaneously, with the former suffering much from extreme foreground-background class imbalance issue due to the large number of anchors. This…

Class imbalance remains a fundamental challenge in machine learning, where standard classifiers exhibit severe performance degradation in minority classes. Although existing approaches address imbalance through resampling or cost-sensitive…