We propose MaskCut approach to generate pseudo-masks for multiple objects in an image. CutLER can learn unsupervised object detectors and instance segmentors solely on ImageNet-1K. CutLER exhibits ...

Abstract: Autonomous vehicles must recognize their surroundings and distinguish between dynamic and static objects to avoid collisions. Most recent moving object segmentation (MOS) studies project ...

Abstract: In applications such as autonomous driving and medical imaging, semantic segmentation of small objects remains a key challenge as traditional models often fail to capture finegrained details ...

Hello everyone, thanks for your patience. HOSIG has now been accepted by AAAI 2026. Related code and data will be released gradually over the next three months ...