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 ...
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 ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results