Related papers: Exemplar-Based Contrastive Self-Supervised Learnin…

The dynamic nature of open-world scenarios has attracted more attention to class incremental learning (CIL). However, existing CIL methods typically presume the availability of complete ground-truth labels throughout the training process,…

Few-Shot Class-Incremental Learning has shown remarkable efficacy in efficient learning new concepts with limited annotations. Nevertheless, the heuristic few-shot annotations may not always cover the most informative samples, which largely…

Being able to learn from small amounts of data is a key characteristic of human intelligence, but exactly {\em how} small? In this paper, we introduce a novel experimental paradigm that allows us to examine classification in an extremely…

Data collected from the real world typically exhibit long-tailed distributions, where frequent classes contain abundant data while rare ones have only a limited number of samples. While existing supervised learning approaches have been…

Few-shot class incremental learning (FSCIL) portrays the problem of learning new concepts gradually, where only a few examples per concept are available to the learner. Due to the limited number of examples for training, the techniques…

Unsupervised feature learning has made great strides with contrastive learning based on instance discrimination and invariant mapping, as benchmarked on curated class-balanced datasets. However, natural data could be highly correlated and…

Recent research shows that in-context learning (ICL) can be effective even when demonstrations have missing or incorrect labels. To shed light on this capability, we examine a canonical setting where the demonstrations are drawn according…

Recently, contrastive learning has achieved great results in self-supervised learning, where the main idea is to push two augmentations of an image (positive pairs) closer compared to other random images (negative pairs). We argue that not…

Continual learning aims to improve the ability of modern learning systems to deal with non-stationary distributions, typically by attempting to learn a series of tasks sequentially. Prior art in the field has largely considered supervised…

Unsupervised clustering aims at discovering the semantic categories of data according to some distance measured in the representation space. However, different categories often overlap with each other in the representation space at the…

Few-shot learning is challenging due to its very limited data and labels. Recent studies in big transfer (BiT) show that few-shot learning can greatly benefit from pretraining on large scale labeled dataset in a different domain. This paper…

Business analytics and machine learning have become essential success factors for various industries - with the downside of cost-intensive gathering and labeling of data. Few-shot learning addresses this challenge and reduces data gathering…

Established experimental procedures for one-shot machine learning do not test the ability to learn or remember specific instances of classes, a key feature of animal intelligence. Distinguishing specific instances is necessary for many…

Self-training is an effective approach to semi-supervised learning. The key idea is to let the learner itself iteratively generate "pseudo-supervision" for unlabeled instances based on its current hypothesis. In combination with consistency…

In biomedical studies, it is often desirable to characterize the interactive mode of multiple disease outcomes beyond their marginal risk. Ising model is one of the most popular choices serving for this purpose. Nevertheless, learning…

In response to an object presentation, supervised learning schemes generally respond with a parsimonious label. Upon a similar presentation we humans respond again with a label, but are flooded, in addition, by a myriad of associations. A…

Contrastive self-supervised learning (SSL) learns an embedding space that maps similar data pairs closer and dissimilar data pairs farther apart. Despite its success, one issue has been overlooked: the fairness aspect of representations…

Multi-Class Incremental Learning (MCIL) aims to learn new concepts by incrementally updating a model trained on previous concepts. However, there is an inherent trade-off to effectively learning new concepts without catastrophic forgetting…

Feature quality is paramount for classification performance, particularly in few-shot scenarios. Contrastive learning, a widely adopted technique for enhancing feature quality, leverages sample relations to extract intrinsic features that…

A complementary label (CL) simply indicates an incorrect class of an example, but learning with CLs results in multi-class classifiers that can predict the correct class. Unfortunately, the problem setting only allows a single CL for each…