In this paper, we present an efficient and robust deep learning solution for novel view synthesis of complex scenes.
Most online multi-object trackers perform object detection stand-alone in a neural net without any input from tracking.
Ranked #1 on Instance Segmentation on nuScenes
The outputs from the teacher network are used as soft labels for supervising the training of a new network.
Ranked #3 on Knowledge Distillation on ImageNet
This task is confronted with two challenges: how to establish the 3D correspondences from views to the BEV map and how to assemble occupancy information across views.
In this paper, we investigate the bias-variance tradeoff brought by distillation with soft labels.
In the classification tree, as the number of parent class nodes are significantly less, their logits are less noisy and can be utilized to suppress the wrong/noisy logits existed in the fine-grained class nodes.
Ranked #5 on Few-Shot Object Detection on LVIS v1.0 val
In this paper, we propose a novel network design mechanism for efficient embedded computing.
Ranked #3 on Face Verification on CFP-FP
Here our goal is to automatically find a compact neural network model with high performance that is suitable for mobile devices.
We study the problem of unsupervised domain adaptive re-identification (re-ID) which is an active topic in computer vision but lacks a theoretical foundation.
Ranked #13 on Unsupervised Domain Adaptation on Market to Duke