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 develo** 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 …

Class-incremental learning (CIL) aims to adapt to emerging new classes without forgetting
old ones. Traditional CIL models are trained from scratch to continually acquire knowledge …

In this work, we introduce Semantic-SAM, an augmented image segmentation foundation for
segmenting and recognizing anything at desired granularities. Compared to the …

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 …

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 …

Novel classes frequently arise in our dynamically changing world, eg, new users in the
authentication system, and a machine learning model should recognize new classes without …

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