Related papers: Spuriosity Didn't Kill the Classifier: Using Invar…

Given an unlabeled dataset and an annotation budget, we study how to selectively label a fixed number of instances so that semi-supervised learning (SSL) on such a partially labeled dataset is most effective. We focus on selecting the right…

Source-free domain adaptation (SFDA) aims to adapt a well-trained source model to an unlabelled target domain without accessing the source dataset, making it applicable in a variety of real-world scenarios. Existing SFDA methods ONLY assess…

The paradigm of worst-group loss minimization has shown its promise in avoiding to learn spurious correlations, but requires costly additional supervision on spurious attributes. To resolve this, recent works focus on developing weaker…

Recent years have witnessed the great success of self-supervised learning (SSL) in recommendation systems. However, SSL recommender models are likely to suffer from spurious correlations, leading to poor generalization. To mitigate spurious…

In many real-world applications, researchers aim to deploy models trained in a source domain to a target domain, where obtaining labeled data is often expensive, time-consuming, or even infeasible. While most existing literature assumes…

Unsupervised domain adaptation aims to transfer knowledge from a labeled source domain to an unlabeled target domain. Previous methods focus on learning domain-invariant features to decrease the discrepancy between the feature distributions…

In various situations one is given only the predictions of multiple classifiers over a large unlabeled test data. This scenario raises the following questions: Without any labeled data and without any a-priori knowledge about the…

Consistency regularization-based methods are prevalent in semi-supervised learning (SSL) algorithms due to their exceptional performance. However, they mainly depend on domain-specific data augmentations, which are not usable in domains…

Consistency regularization on label predictions becomes a fundamental technique in semi-supervised learning, but it still requires a large number of training iterations for high performance. In this study, we analyze that the consistency…

Semi-supervised learning (SSL) methods effectively leverage unlabeled data to improve model generalization. However, SSL models often underperform in open-set scenarios, where unlabeled data contain outliers from novel categories that do…

The problem of fully supervised classification is that it requires a tremendous amount of annotated data, however, in many datasets a large portion of data is unlabeled. To alleviate this problem semi-supervised learning (SSL) leverages the…

In many classification datasets, the task labels are spuriously correlated with some input attributes. Classifiers trained on such datasets often rely on these attributes for prediction, especially when the spurious correlation is high, and…

In this paper, we present a Nuisance-label Supervision (NLS) module, which can make models more robust to nuisance factor variations. Nuisance factors are those irrelevant to a task, and an ideal model should be invariant to them. For…

We study adapting trained object detectors to unseen domains manifesting significant variations of object appearance, viewpoints and backgrounds. Most current methods align domains by either using image or instance-level feature alignment…

Informally, a 'spurious correlation' is the dependence of a model on some aspect of the input data that an analyst thinks shouldn't matter. In machine learning, these have a know-it-when-you-see-it character; e.g., changing the gender of a…

Recent semi-supervised learning (SSL) methods typically include a filtering strategy to improve the quality of pseudo labels. However, these filtering strategies are usually hand-crafted and do not change as the model is updated, resulting…

Pseudo-labelling is a popular technique in unsuper-vised domain adaptation for semantic segmentation. However, pseudo labels are noisy and inevitably have confirmation bias due to the discrepancy between source and target domains and…

We consider a semi-supervised classification problem with non-stationary label-shift in which we observe a labelled data set followed by a sequence of unlabelled covariate vectors in which the marginal probabilities of the class labels may…

The amount of manually labeled data is limited in medical applications, so semi-supervised learning and automatic labeling strategies can be an asset for training deep neural networks. However, the quality of the automatically generated…

Pseudo-labels are confident predictions made on unlabeled target data by a classifier trained on labeled source data. They are widely used for adapting a model to unlabeled data, e.g., in a semi-supervised learning setting. Our key insight…