activity
20182021
most citedWIDER Face and Pedestrian Challenge 2018: Methods and Results

28 citations · 138 across the 14 of their papers we have counts for

collaborators

16 papers

cs.CV20215 cited

RefineMask: Towards High-Quality Instance Segmentation with Fine-Grained Features

Gang Zhang, Xin Lu, Jingru Tan +4

The two-stage methods for instance segmentation, e.g. Mask R-CNN, have achieved excellent performance recently. However, the segmented masks are still very coarse due to the downsa…

cs.CV20212 cited

Fixing the Teacher-Student Knowledge Discrepancy in Distillation

Jiangfan Han, Mengya Gao, Yujie Wang +3

Training a small student network with the guidance of a larger teacher network is an effective way to promote the performance of the student. Despite the different types, the guide…

cs.CV2021

Differentiable Network Adaption with Elastic Search Space

Shaopeng Guo, Yujie Wang, Kun Yuan +1

In this paper we propose a novel network adaption method called Differentiable Network Adaption (DNA), which can adapt an existing network to a specific computation budget by adjus…

cs.CV20209 cited

Equalization Loss v2: A New Gradient Balance Approach for Long-tailed Object Detection

Jingru Tan, Xin Lu, Gang Zhang +2

Recently proposed decoupled training methods emerge as a dominant paradigm for long-tailed object detection. But they require an extra fine-tuning stage, and the disjointed optimiz…

cs.CV20201 cited

Dynamic Graph: Learning Instance-aware Connectivity for Neural Networks

Kun Yuan, Quanquan Li, Dapeng Chen +2

One practice of employing deep neural networks is to apply the same architecture to all the input instances. However, a fixed architecture may not be representative enough for data…

cs.CV202012 cited

MimicDet: Bridging the Gap Between One-Stage and Two-Stage Object Detection

Xin Lu, Quanquan Li, Buyu Li +1

Modern object detection methods can be divided into one-stage approaches and two-stage ones. One-stage detectors are more efficient owing to straightforward architectures, but the…