Related papers: Extracting Clean and Balanced Subset for Noisy Lon…

In this paper, we study the problem of learning image classification models with label noise. Existing approaches depending on human supervision are generally not scalable as manually identifying correct or incorrect labels is…

Noisy label learning aims to train deep neural networks using a large amount of samples with noisy labels, whose main challenge comes from how to deal with the inaccurate supervision caused by wrong labels. Existing works either take the…

Long-tailed instance segmentation is a challenging task due to the extreme imbalance of training samples among classes. It causes severe biases of the head classes (with majority samples) against the tailed ones. This renders "how to…

Many practical medical imaging scenarios include categories that are under-represented but still crucial. The relevance of image recognition models to real-world applications lies in their ability to generalize to these rare classes as well…

In this paper, we address the problem of effectively self-training neural networks in a low-resource setting. Self-training is frequently used to automatically increase the amount of training data. However, in a low-resource scenario, it is…

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…

Label noise is a critical factor that degrades the generalization performance of deep neural networks, thus leading to severe issues in real-world problems. Existing studies have employed strategies based on either loss or uncertainty to…

Noisy labels, inevitably existing in pseudo segmentation labels generated from weak object-level annotations, severely hampers model optimization for semantic segmentation. Previous works often rely on massive hand-crafted losses and…

Long-Tailed Semi-Supervised Learning (LTSSL) aims to learn from class-imbalanced data where only a few samples are annotated. Existing solutions typically require substantial cost to solve complex optimization problems, or class-balanced…

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…

Recent studies indicate that deep neural networks degrade in generalization performance under noisy supervision. Existing methods focus on isolating clean subsets or correcting noisy labels, facing limitations such as high computational…

Self-supervised learning (SSL) has shown remarkable data representation capabilities across a wide range of datasets. However, when applied to real-world datasets with long-tailed distributions, performance on multiple downstream tasks…

A thorough and holistic scene understanding is crucial for autonomous vehicles, where LiDAR semantic segmentation plays an indispensable role. However, most existing methods focus on the network design while neglecting the inherent…

Conventional multi-label classification (MLC) methods assume that all samples are fully labeled and identically distributed. Unfortunately, this assumption is unrealistic in large-scale MLC data that has long-tailed (LT) distribution and…

Real-time optical Motion Capture (MoCap) systems have not benefited from the advances in modern data-driven modeling. In this work we apply machine learning to solve noisy unstructured marker estimates in real-time and deliver robust…

When labeled data is insufficient, semi-supervised learning with the pseudo-labeling technique can significantly improve the performance of automatic speech recognition. However, pseudo-labels are often noisy, containing numerous incorrect…

It is crucial to distinguish mislabeled samples for dealing with noisy labels. Previous methods such as Coteaching and JoCoR introduce two different networks to select clean samples out of the noisy ones and only use these clean ones to…

Training deep neural networks with noisy labels remains a significant challenge, often leading to degraded performance. Existing methods for handling label noise typically rely on either transition matrix, noise detection, or meta-learning…

Training deep neural networks (DNNs) with limited supervision has been a popular research topic as it can significantly alleviate the annotation burden. Self-training has been successfully applied in semi-supervised learning tasks, but one…

Deep clustering, which learns representation and semantic clustering without labels information, poses a great challenge for deep learning-based approaches. Despite significant progress in recent years, most existing methods focus on…