D Zhang, J Han, G Cheng… - IEEE transactions on …, 2021 - ieeexplore.ieee.org
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 …
Z Peng, W Huang, S Gu, L Xie… - Proceedings of the …, 2021 - openaccess.thecvf.com
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 …
Y Ming, Z Cai, J Gu, Y Sun, W Li… - Advances in neural …, 2022 - proceedings.neurips.cc
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 …