Abstract Machine learning methods strive to acquire a robust model during the training
process that can effectively generalize to test samples, even in the presence of distribution …

Test-time adaptation (TTA) intends to adapt the pretrained model to test distributions with
only unlabeled test data streams. Most of the previous TTA methods have achieved great …

In this paper, we study the application of Test-time domain adaptation in semantic
segmentation (TTDA-Seg) where both efficiency and effectiveness are crucial. Existing …

Test-time adaptation (TTA) adapts a source model to the distribution shift in testing data
without using any source data. There have been plenty of algorithms concentrated on …

Abstract We present Ev-NeRF, a Neural Radiance Field derived from event data. While
event cameras can measure subtle brightness changes in high frame rates, the …

Visual domain adaptation (DA) seeks to transfer trained models to unseen, unlabeled
domains across distribution shift, but approaches typically focus on adapting convolutional …

Recent advances in 2D zero-shot and few-shot recognition often leverage large pre-trained
vision-language models (VLMs) such as CLIP. Due to a shortage of suitable datasets, it is …

Event camera, as an emerging biologically-inspired vision sensor for capturing motion
dynamics, presents new potential for 3D human pose tracking, or video-based 3D human …

As asynchronous event data is more frequently engaged in various vision tasks, the risk of
backdoor attacks becomes more evident. However, research into the potential risk …

Though the object detection performance on standard benchmarks has been improved
drastically in the last decade current object detectors are often vulnerable to domain shift …