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 ...
Training on video (w/o flow) . We load the weight pre-trained on the static image dataset, and use DAVIS and FBMS to train our framework. python finetune.py --model ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results