From the 1 of 6k papers with an AI index.
7.9k citations
- Kavli Institute for Theoretical SciencesCN1.1k papers
- Chinese Academy of SciencesCN1k papers
- University of Chinese Academy of SciencesCN843 papers
- Institute of High Energy PhysicsCN726 papers
- Centre National de la Recherche ScientifiqueFR718 papers
- Tsinghua UniversityCN715 papers
- Istituto Nazionale di Fisica Nucleare, Laboratori Nazionali di FrascatiIT634 papers
- University of Science and Technology of ChinaCN596 papers
- State Key Laboratory of Nuclear Physics and Technology590 papers
- Beihang UniversityCN552 papers
- Carnegie Mellon UniversityUS550 papers
- University of Maryland, College ParkUS544 papers
35 papers · 2 filters
S2DNAS:Transforming Static CNN Model for Dynamic Inference via Neural Architecture Search
Zhihang Yuan, Bingzhe Wu, Zheng Liang +3
Recently, dynamic inference has emerged as a promising way to reduce the computational cost of deep convolutional neural network (CNN). In contrast to static methods (e.g. weight p…
FFA-Net: Feature Fusion Attention Network for Single Image Dehazing
Xu Qin, Zhilin Wang, Yuanchao Bai +2
In this paper, we propose an end-to-end feature fusion at-tention network (FFA-Net) to directly restore the haze-free image. The FFA-Net architecture consists of three key componen…
MSD: Multi-Self-Distillation Learning via Multi-classifiers within Deep Neural Networks
Yunteng Luan, Hanyu Zhao, Zhi Yang +1
As the development of neural networks, more and more deep neural networks are adopted in various tasks, such as image classification. However, as the huge computational overhead, t…
AutoRemover: Automatic Object Removal for Autonomous Driving Videos
Rong Zhang, Wei Li, Peng Wang +7
Motivated by the need for photo-realistic simulation in autonomous driving, in this paper we present a video inpainting algorithm \emph{AutoRemover}, designed specifically for gene…
Multi-Label Classification with Label Graph Superimposing
Ya Wang, Dongliang He, Fu Li +4
Images or videos always contain multiple objects or actions. Multi-label recognition has been witnessed to achieve pretty performance attribute to the rapid development of deep lea…
SOGNet: Scene Overlap Graph Network for Panoptic Segmentation
Yibo Yang, Hongyang Li, Xia Li +3
The panoptic segmentation task requires a unified result from semantic and instance segmentation outputs that may contain overlaps. However, current studies widely ignore modeling…