Based on this finding, we propose LayerMatch scheme for approximating the representation of a GAN generator that can be used for unsupervised domain-specific pretraining.
Deep learning-based detectors usually produce a redundant set of object bounding boxes including many duplicate detections of the same object.
Ranked #1 on Object Detection on WiderPerson
We propose f-BRS (feature backpropagating refinement scheme) that solves an optimization problem with respect to auxiliary variables instead of the network inputs, and requires running forward and backward pass just for a small part of a network.
Ranked #3 on Interactive Segmentation on SBD
We train visual odometry model on synthetic data and do not use ground truth poses hence this model can be considered unsupervised.
We find that while in many cases the accuracy of SLAM is very good, the robustness is still an issue.
We present a novel dataset for training and benchmarking semantic SLAM methods.
Given an input image and a point $(x, y)$, it generates a mask for the object located at $(x, y)$.
Ranked #5 on Panoptic Segmentation on Mapillary val
Optical Flow (OF) and depth are commonly used for visual odometry since they provide sufficient information about camera ego-motion in a rigid scene.