Related papers: Unsupervised Concept Discovery Mitigates Spurious …

Contrastive vision-language models like CLIP have shown great progress in transfer learning. In the inference stage, the proper text description, also known as prompt, needs to be carefully designed to correctly classify the given images.…

Noisy labels can negatively impact the performance of deep neural networks. One common solution is label refurbishment, which involves reconstructing noisy labels through predictions and distributions. However, these methods may introduce…

While deep neural networks can achieve state-of-the-art performance in many tasks, these models are more fragile than they appear. They are prone to learning spurious correlations in their training data, leading to surprising failure cases.…

Recently, deep learning has experienced rapid expansion, contributing significantly to the progress of supervised learning methodologies. However, acquiring labeled data in real-world settings can be costly, labor-intensive, and sometimes…

Semi-supervised learning aims to boost the accuracy of a model by exploring unlabeled images. The state-of-the-art methods are consistency-based which learn about unlabeled images by encouraging the model to give consistent predictions for…

Deep learning methods have shown promise in unsupervised domain adaptation, which aims to leverage a labeled source domain to learn a classifier for the unlabeled target domain with a different distribution. However, such methods typically…

Pseudo-labeling has proven to be a promising semi-supervised learning (SSL) paradigm. Existing pseudo-labeling methods commonly assume that the class distributions of training data are balanced. However, such an assumption is far from…

Federated learning aims to tackle the ``isolated data island" problem, where it trains a collective model from physically isolated clients while safeguarding the privacy of users' data. However, supervised federated learning necessitates…

The deployment of language models brings challenges in generating reliable information, especially when these models are fine-tuned using human preferences. To extract encoded knowledge without (potentially) biased human labels,…

Meta-learning performs adaptation through a limited amount of support set, which may cause a sample bias problem. To solve this problem, transductive meta-learning is getting more and more attention, going beyond the conventional inductive…

In document classification for, e.g., legal and biomedical text, we often deal with hundreds of classes, including very infrequent ones, as well as temporal concept drift caused by the influence of real world events, e.g., policy changes,…

Discovering new intents is a crucial task in dialogue systems. Most existing methods are limited in transferring the prior knowledge from known intents to new intents. They also have difficulties in providing high-quality supervised signals…

We propose an information-theoretic bias measurement technique through a causal interpretation of spurious correlation, which is effective to identify the feature-level algorithmic bias by taking advantage of conditional mutual information.…

In this paper, we propose a novel unsupervised clustering approach exploiting the hidden information that is indirectly introduced through a pseudo classification objective. Specifically, we randomly assign a pseudo parent-class label to…

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…

Unsupervised person re-identification (Re-ID) attracts increasing attention due to its potential to resolve the scalability problem of supervised Re-ID models. Most existing unsupervised methods adopt an iterative clustering mechanism,…

The reliability of machine learning systems critically assumes that the associations between features and labels remain similar between training and test distributions. However, unmeasured variables, such as confounders, break this…

Self-supervised learning (SSL) has the potential to benefit many applications, particularly those where manually annotating data is cumbersome. One such situation is the semantic segmentation of point clouds. In this context, existing…

Self-supervised contrastive learning offers a means of learning informative features from a pool of unlabeled data. In this paper, we delve into another useful approach -- providing a way of selecting a core-set that is entirely unlabeled.…

Standard software analytics often involves having a large amount of data with labels in order to commission models with acceptable performance. However, prior work has shown that such requirements can be expensive, taking several weeks to…