Related papers: Cross-label Suppression: A Discriminative and Fast…

To enhance group robustness to spurious correlations, prior work often relies on auxiliary group annotations and assumes identical sets of groups across training and test domains. To overcome these limitations, we propose to leverage…

Multi-label classification (MLC) studies the problem where each instance is associated with multiple relevant labels, which leads to the exponential growth of output space. MLC encourages a popular framework named label compression (LC) for…

Image classification datasets exhibit a non-negligible fraction of mislabeled examples, often due to human error when one class superficially resembles another. This issue poses challenges in supervised contrastive learning (SCL), where the…

In recent years, research on learning with noisy labels has focused on devising novel algorithms that can achieve robustness to noisy training labels while generalizing to clean data. These algorithms often incorporate sophisticated…

Traditional computer vision models are trained to predict a fixed set of predefined categories. Recently, natural language has been shown to be a broader and richer source of supervision that provides finer descriptions to visual concepts…

Recent studies have shown that regularization techniques using soft labels, e.g., label smoothing, Mixup, and CutMix, not only enhance image classification accuracy but also mitigate miscalibration due to overconfident predictions, and…

Overconfidence has been shown to impair generalization and calibration of a neural network. Previous studies remedy this issue by adding a regularization term to a loss function, preventing a model from making a peaked distribution. Label…

Text classification, an integral task in natural language processing, involves the automatic categorization of text into predefined classes. Creating supervised labeled datasets for low-resource languages poses a considerable challenge.…

Label Smoothing (LS) is widely adopted to reduce overconfidence in neural network predictions and improve generalization. Despite these benefits, recent studies reveal two critical issues with LS. First, LS induces overconfidence in…

Contrastive learning and self-supervised techniques have gained prevalence in computer vision for the past few years. It is essential for medical image analysis, which is often notorious for its lack of annotations. Most existing…

Training neural networks with one-hot target labels often results in overconfidence and overfitting. Label smoothing addresses this issue by perturbing the one-hot target labels by adding a uniform probability vector to create a regularized…

Based on the observation that semantic segmentation errors are partially predictable, we propose a compact formulation using confusion statistics of the trained classifier to refine (re-estimate) the initial pixel label hypotheses. The…

While deep learning strategies achieve outstanding results in computer vision tasks, one issue remains: The current strategies rely heavily on a huge amount of labeled data. In many real-world problems, it is not feasible to create such an…

With the development of deep learning, medical image classification has been significantly improved. However, deep learning requires massive data with labels. While labeling the samples by human experts is expensive and time-consuming,…

In many multilingual text classification problems, the documents in different languages often share the same set of categories. To reduce the labeling cost of training a classification model for each individual language, it is important to…

In this work, we propose a novel supervised contrastive loss that enables the integration of taxonomic hierarchy information during the representation learning process. A supervised contrastive loss operates by enforcing that images with…

Collaborative learning has successfully applied knowledge transfer to guide a pool of small student networks towards robust local minima. However, previous approaches typically struggle with drastically aggravated student homogenization…

Supervised learning can be viewed as distilling relevant information from input data into feature representations. This process becomes difficult when supervision is noisy as the distilled information might not be relevant. In fact, recent…

Self-supervised learning (SSL) methods targeting scene images have seen a rapid growth recently, and they mostly rely on either a dedicated dense matching mechanism or a costly unsupervised object discovery module. This paper shows that…

Cross-lingual text classification(CLTC) is the task of classifying documents written in different languages into the same taxonomy of categories. This paper presents a novel approach to CLTC that builds on model distillation, which adapts…