Few-shot learning (FSL) has emerged as an effective learning method and shows great
potential. Despite the recent creative works in tackling FSL tasks, learning valid information …

As an emerging and challenging problem in the computer vision community, weakly
supervised object localization and detection plays an important role for developing new …

The scaling of Transformers has driven breakthrough capabilities for language models. At
present, the largest large language models (LLMs) contain upwards of 100B parameters …

The current modus operandi in adapting pre-trained models involves updating all the
backbone parameters, ie., full fine-tuning. This paper introduces Visual Prompt Tuning (VPT) …

Recent work has shown that self-supervised pre-training leads to improvements over
supervised learning on challenging visual recognition tasks. CLIP, an exciting new …

Abstract Within Convolutional Neural Network (CNN), the convolution operations are good
at extracting local features but experience difficulty to capture global representations. Within …

Unsupervised localization and segmentation are long-standing computer vision challenges
that involve decomposing an image into semantically-meaningful segments without any …

Interpretability in machine learning (ML) is crucial for high stakes decisions and
troubleshooting. In this work, we provide fundamental principles for interpretable ML, and …

Recognizing out-of-distribution (OOD) samples is critical for machine learning systems
deployed in the open world. The vast majority of OOD detection methods are driven by a …

One of the major challenges in training text-to-image generation models is the need of a
large number of high-quality text-image pairs. While image samples are often easily …