相关论文: Same Target, Different Basins: Hard vs. Soft Label…

Developing robust models against adversarial perturbations has been an active area of research and many algorithms have been proposed to train individual robust models. Taking these pretrained robust models, we aim to study whether it is…

While semi-supervised learning (SSL) algorithms provide an efficient way to make use of both labelled and unlabelled data, they generally struggle when the number of annotated samples is very small. In this work, we consider the problem of…

We address the problem of active learning under label shift: when the class proportions of source and target domains differ. We introduce a "medial distribution" to incorporate a tradeoff between importance weighting and class-balanced…

A common practice in building NLP datasets, especially using crowd-sourced annotations, involves obtaining multiple annotator judgements on the same data instances, which are then flattened to produce a single "ground truth" label or score,…

Building an accurate computer-aided diagnosis system based on data-driven approaches requires a large amount of high-quality labeled data. In medical imaging analysis, multiple expert annotators often produce subjective estimates about…

To discover intrinsic inter-class transition probabilities underlying data, learning with noise transition has become an important approach for robust deep learning on corrupted labels. Prior methods attempt to achieve such transition…

Point supervision has become a scalable solution to address dense annotation for infrared small target detection, but its performance is limited by two coupled bottlenecks: unstable pseudo-label evolution in cluttered, low-contrast infrared…

In scenarios where training data is limited due to observation costs or data scarcity, enriching the label information associated with each instance becomes crucial for building high-accuracy classification models. In such contexts, it is…

Supervised machine learning assumes that labeled data provide accurate measurements of the concepts models are meant to learn. Yet in practice, human labeling introduces systematic variation arising from ambiguous items, divergent…

Multi-label classification is prevalent in real-world settings, but the behavior of Large Language Models (LLMs) in this setting is understudied. We investigate how autoregressive LLMs perform multi-label classification, focusing on…

Recent advances in pre-trained vision-language models have demonstrated remarkable zero-shot generalization capabilities. To further enhance these models' adaptability to various downstream tasks, prompt tuning has emerged as a…

Recent state-of-the-art methods in imbalanced semi-supervised learning (SSL) rely on confidence-based pseudo-labeling with consistency regularization. To obtain high-quality pseudo-labels, a high confidence threshold is typically adopted.…

Weak supervision (WS) is a rich set of techniques that produce pseudolabels by aggregating easily obtained but potentially noisy label estimates from a variety of sources. WS is theoretically well understood for binary classification, where…

Algorithms designed for addressing typical supervised classification problems can only learn from a fixed set of samples and labels, making them unsuitable for the real world, where data arrives as a stream of samples often associated with…

In semantic segmentation, training data down-sampling is commonly performed due to limited resources, the need to adapt image size to the model input, or improve data augmentation. This down-sampling typically employs different strategies…

As the adoption of deep learning techniques in industrial applications grows with increasing speed and scale, successful deployment of deep learning models often hinges on the availability, volume, and quality of annotated data. In this…

In this work, we propose a simple yet effective semi-supervised learning approach called Augmented Distribution Alignment. We reveal that an essential sampling bias exists in semi-supervised learning due to the limited number of labeled…

For semi-supervised learning with imbalance classes, the long-tailed distribution of data will increase the model prediction bias toward dominant classes, undermining performance on less frequent classes. Existing methods also face…

High-quality labels are expensive to obtain for many machine learning tasks, such as medical image classification tasks. Therefore, probabilistic (weak) labels produced by weak supervision tools are used to seed a process in which…

Real-world datasets usually are class-imbalanced and corrupted by label noise. To solve the joint issue of long-tailed distribution and label noise, most previous works usually aim to design a noise detector to distinguish the noisy and…