• Publications
  • Influence
Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
TLDR
This work introduces a Region Proposal Network (RPN) that shares full-image convolutional features with the detection network, thus enabling nearly cost-free region proposals and further merge RPN and Fast R-CNN into a single network by sharing their convolutionAL features.
Single Image Haze Removal Using Dark Channel Prior
TLDR
A simple but effective image prior—dark channel prior to remove haze from a single input image to improve the quality of outdoor haze-free images.
YOLOX: Exceeding YOLO Series in 2021
TLDR
This report switches the YOLO detector to an anchor-free manner and conducts other advanced detection techniques, i.e., a decoupled head and the leading label assignment strategy SimOTA to achieve state-of-the-art results across a large scale range of models.
RepVGG: Making VGG-style ConvNets Great Again
We present a simple but powerful architecture of convolutional neural network, which has a VGG-like inference-time body composed of nothing but a stack of 3 × 3 convolution and ReLU, while the
PVN3D: A Deep Point-Wise 3D Keypoints Voting Network for 6DoF Pose Estimation
TLDR
A deep Hough voting network is proposed to detect 3D keypoints of objects and then estimate the 6D pose parameters within a least-squares fitting manner, which is a natural extension of 2D-keypoint approaches that successfully work on RGB based 6DoF estimation.
Deep Residual Learning for Image Recognition Supplementary Materials
TLDR
This section introduces the detection method based on the baseline Faster R-CNN system, and considers these layers as analogous to the 13 conv layers in VGG-16, and proposes the idea of “Networks on Conv feature maps” (NoC) to address this issue.
FFB6D: A Full Flow Bidirectional Fusion Network for 6D Pose Estimation
TLDR
This work proposes FFB6D, a Full Flow Bidirectional fusion network designed for 6D pose estimation from a single RGBD image, which learns to combine appearance and geometry information for representation learning as well as output representation selection.
You Only Look One-level Feature
This paper revisits feature pyramids networks (FPN) for one-stage detectors and points out that the success of FPN is due to its divide-and-conquer solution to the optimization problem in object
Disentangled Image Matting
TLDR
This paper proposes AdaMatting, a new end-to-end matting framework that disentangles this problem into two sub-tasks: trimap adaptation and alpha estimation, which achieves the state-of-the-art performance on Adobe Composition-1k dataset both qualitatively and quantitatively.
OTA: Optimal Transport Assignment for Object Detection
TLDR
This paper innovatively revisit the label assignment from a global perspective and proposes to formulate the assigning procedure as an Optimal Transport (OT) problem – a well-studied topic in Optimization Theory.
...
...