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