Although self-/un-supervised methods have led to rapid progress in visual representation
learning, these methods generally treat objects and scenes using the same lens. In this …

Out-of-distribution (OOD) detection is the problem of identifying inputs which are unrelated to
the in-distribution task. The OOD detection performance when the in-distribution (ID) is …

We argue that there are many notions of'similarity'and that models, like humans, should be
able to adapt to these dynamically. This contrasts with most representation learning …

Existing methods for isolating hard subpopulations and spurious correlations in datasets
often require human intervention. This can make these methods labor-intensive and dataset …

People are relying on AI agents to assist them with various tasks. The human must know
when to rely on the agent, collaborate with the agent, or ignore its suggestions. In this work …

We introduce the Song Describer dataset (SDD), a new crowdsourced corpus of high-quality
audio-caption pairs, designed for the evaluation of music-and-language models. The …

Data quality is crucial for training accurate, unbiased, and trustworthy machine learning
models as well as for their correct evaluation. Recent work, however, has shown that even …

While the ImageNet dataset has been driving computer vision research over the past
decade, significant label noise and ambiguity have made top-1 accuracy an insufficient …

Data augmentation (DA) encodes invariance and provides implicit regularization critical to a
model's performance in image classification tasks. However, while DA improves average …

Pre-training on large-scale datasets and then fine-tuning on downstream tasks have
become a standard practice in deep learning. However, pre-training data often contain label …