Related papers: Training Under Attentional Competition Produces Pe…

Adversarial learning can learn fairer and less biased models of language than standard methods. However, current adversarial techniques only partially mitigate model bias, added to which their training procedures are often unstable. In this…

Classifiers such as deep neural networks have been shown to be vulnerable against adversarial perturbations on problems with high-dimensional input space. While adversarial training improves the robustness of image classifiers against such…

The advances in natural language processing (NLP) pose both opportunities and challenges. While recent progress enables the development of high-performing models for a variety of tasks, it also poses the risk of models learning harmful…

Learning to categorize requires distinguishing category members from non-members by detecting the features that covary with membership. Whether this process can induce changes in perception is still a matter of debate. In prior studies, we…

When humans perform a task, such as playing a game, they selectively pay attention to certain parts of the visual input, gathering relevant information and sequentially combining it to build a representation from the sensory data. In this…

Current unsupervised image-to-image translation techniques struggle to focus their attention on individual objects without altering the background or the way multiple objects interact within a scene. Motivated by the important role of…

Self-training and contrastive learning have emerged as leading techniques for incorporating unlabeled data, both under distribution shift (unsupervised domain adaptation) and when it is absent (semi-supervised learning). However, despite…

Contrastive representation learning has emerged as a promising technique for continual learning as it can learn representations that are robust to catastrophic forgetting and generalize well to unseen future tasks. Previous work in…

We present results from a pilot experiment to measure if machine recommendations can debias human perceptual biases in visualization tasks. We specifically studied the ``pull-down'' effect, i.e., people underestimate the average position of…

Covariate distribution shifts and adversarial perturbations present robustness challenges to the conventional statistical learning framework: mild shifts in the test covariate distribution can significantly affect the performance of the…

Contrastive learning has achieved state-of-the-art performance in various self-supervised learning tasks and even outperforms its supervised counterpart. Despite its empirical success, theoretical understanding of the superiority of…

The study of action selection in humans can present challenges of task design since our actions are usually defined by many degrees of freedom and therefore occupy a large action-space. While saccadic eye-movement offers a more constrained…

People routinely rely on data to make decisions, but the process can be riddled with biases. We show that patterns in data might be noticed first or more strongly, depending on how the data is visually represented or what the viewer finds…

Contrastive learning has emerged as a competitive pretraining method for object detection. Despite this progress, there has been minimal investigation into the robustness of contrastively pretrained detectors when faced with domain shifts.…

We present a self-supervised learning method to learn audio and video representations. Prior work uses the natural correspondence between audio and video to define a standard cross-modal instance discrimination task, where a model is…

The presence of objects that are confusingly similar to the tracked target, poses a fundamental challenge in appearance-based visual tracking. Such distractor objects are easily misclassified as the target itself, leading to eventual…

Adversarial training aims to defend against adversaries: malicious opponents whose sole aim is to harm predictive performance in any way possible. This presents a rather harsh perspective, which we assert results in unnecessarily…

Pretrained large-scale vision-language models like CLIP have exhibited strong generalization over unseen tasks. Yet imperceptible adversarial perturbations can significantly reduce CLIP's performance on new tasks. In this work, we identify…

We have carried out binocular rivalry experiments with a large number of subjects to obtain high quality statistics on probability distribution of dominance duration (PDDD) for two cases where (a) the rival stimulus is continuously…

Although an object may appear in numerous contexts, we often describe it in a limited number of ways. Language allows us to abstract away visual variation to represent and communicate concepts. Building on this intuition, we propose an…