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: Although it is well believed for years that modeling relations between objects would help object recognition, there has not been evidence that the idea is working in the deep learning era.

Abstract: Three-dimensional objects are commonly represented as 3D boxes in a point-cloud. This representation mimics the well-studied image-based 2D bounding-box detection but comes with additional ...