This study addresses the issue of fusing infrared and visible images that appear differently
for object detection. Aiming at generating an image of high visual quality, previous …

Multi-modality image fusion and segmentation play a vital role in autonomous driving and
robotic operation. Early efforts focus on boosting the performance for only one task, eg …

Backdoor attack intends to embed hidden backdoors into deep neural networks (DNNs), so
that the attacked models perform well on benign samples, whereas their predictions will be …

Recent learning-based image fusion methods have marked numerous progress in pre-
registered multi-modality data, but suffered serious ghosts dealing with misaligned multi …

Recent advances of data-driven machine learning have revolutionized fields like computer
vision, reinforcement learning, and many scientific and engineering domains. In many real …

Deep neural networks (DNNs) have demonstrated their superiority in practice. Arguably, the
rapid development of DNNs is largely benefited from high-quality (open-sourced) datasets …

Gradient methods have become mainstream techniques for Bi-Level Optimization (BLO) in
learning fields. The validity of existing works heavily rely on either a restrictive Lower-Level …

Enhancing images in low-light scenes is a challenging but widely concerned task in the
computer vision. The mainstream learning-based methods mainly acquire the enhanced …

Open-world classification systems should discern out-of-distribution (OOD) data whose
labels deviate from those of in-distribution (ID) cases, motivating recent studies in OOD …

Symmetry-based neural networks often constrain the architecture in order to achieve
invariance or equivariance to a group of transformations. In this paper, we propose an …