PROB adapts the Deformable DETR model by adding the proposed 'probabilistic objectness' head. In training, we alternate between distribution estimation (top right) and objectness likelihood ...

Abstract: Oriented object detection is a challenging and relatively new problem. Most existing approaches are based on deep learning and explore Oriented Bounding Boxes (OBBs) to represent the objects ...

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 ...

It is a common sight at public parks, schools and housing complexes: waste scattered on the grass just a few feet away from ...