F
Fuchun Sun
Researcher at Tsinghua University
Publications - 676
Citations - 15700
Fuchun Sun is an academic researcher from Tsinghua University. The author has contributed to research in topics: Computer science & Control theory. The author has an hindex of 54, co-authored 569 publications receiving 10923 citations. Previous affiliations of Fuchun Sun include Shenzhen University.
Papers
More filters
Book ChapterDOI
A Survey on Deep Transfer Learning
TL;DR: Deep transfer learning relaxes the hypothesis that the training data must be independent and identically distributed (i.i.d.) with the test data, which motivates researchers to use transfer learning to solve the problem of insufficient training data as mentioned in this paper.
Posted Content
A Survey on Deep Transfer Learning
TL;DR: This survey focuses on reviewing the current researches of transfer learning by using deep neural network and its applications and defined deep transfer learning, category and review the recent research works based on the techniques used inDeep transfer learning.
Journal ArticleDOI
FoveaBox: Beyound Anchor-Based Object Detection
TL;DR: Without bells and whistles, FoveaBox achieves state-of-the-art single model performance on the standard COCO and Pascal VOC object detection benchmark and avoids all computation and hyper-parameters related to anchor boxes, which are often sensitive to the final detection performance.
Proceedings ArticleDOI
HyperNet: Towards Accurate Region Proposal Generation and Joint Object Detection
TL;DR: HyperNet as discussed by the authors is based on an elaborately designed Hyper Feature which aggregates hierarchical feature maps first and then compresses them into a uniform space, thus enabling them to construct HyperNet by sharing them both in generating proposals and detecting objects via an end to end joint training strategy.
Proceedings ArticleDOI
RON: Reverse Connection with Objectness Prior Networks for Object Detection
TL;DR: RON as mentioned in this paper proposes a reverse connection to detect objects on multi-levels of CNNs, which reduces the searching space of objects by optimizing the reverse connection, objectness prior and object detector jointly by a multi-task loss function.