This is an implementation of the Mask R-CNN paper which edits the original Mask_RCNN repository (which only supports TensorFlow 1.x), so that it works with Python 3.10 and TensorFlow 2.14.0. This new ...

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: Super-resolution (SR) aims to restore a high-resolution (HR) image from its low-resolution (LR) counterpart. Existing works try to achieve an overall average recovery over all regions to ...

Abstract: We propose the gradient-weighted Object Detector Activation Maps (ODAM), a visual explanation technique for interpreting the predictions of object detectors. Utilizing the gradients of ...