Curriculum learning (CL) is a training strategy that trains a machine learning model from
easier data to harder data, which imitates the meaningful learning order in human curricula …

Deep learning has achieved remarkable success in numerous domains with help from large
amounts of big data. However, the quality of data labels is a concern because of the lack of …

Contrastive language-image pretraining (CLIP) using image-text pairs has achieved
impressive results on image classification in both zero-shot and transfer learning settings …

Abstract Out-of-distribution (OOD) detection is critical to ensuring the reliability and safety of
machine learning systems. For instance, in autonomous driving, we would like the driving …

Abstract We present Region-aware Open-vocabulary Vision Transformers (RO-ViT)--a
contrastive image-text pretraining recipe to bridge the gap between image-level pretraining …

State-of-the-art computer vision systems are trained to predict a fixed set of predetermined
object categories. This restricted form of supervision limits their generality and usability since …

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

Training machine learning models in a meaningful order, from the easy samples to the hard
ones, using curriculum learning can provide performance improvements over the standard …

The existing weakly supervised semantic segmentation (WSSS) methods pay much
attention to generating accurate and complete class activation maps (CAMs) as pseudo …

Deep learning (DL) techniques have obtained remarkable achievements on various tasks,
such as image recognition, object detection, and language modeling. However, building a …