J
Jiashi Feng
Researcher at National University of Singapore
Publications - 48
Citations - 4490
Jiashi Feng is an academic researcher from National University of Singapore. The author has contributed to research in topics: Feature (computer vision) & Computer science. The author has an hindex of 16, co-authored 48 publications receiving 1363 citations.
Papers
More filters
Proceedings ArticleDOI
Coordinate Attention for Efficient Mobile Network Design
TL;DR: CoordAttention as mentioned in this paper embeds positional information into channel attention to capture long-range dependencies along one spatial direction and meanwhile precise positional information can be preserved along the other spatial direction.
Proceedings Article
Decoupling Representation and Classifier for Long-Tailed Recognition
Bingyi Kang,Saining Xie,Marcus Rohrbach,Zhicheng Yan,Albert Gordo,Jiashi Feng,Yannis Kalantidis +6 more
TL;DR: It is shown that it is possible to outperform carefully designed losses, sampling strategies, even complex modules with memory, by using a straightforward approach that decouples representation and classification.
Proceedings ArticleDOI
Few-Shot Object Detection via Feature Reweighting
TL;DR: In this article, a few-shot object detector is proposed that can learn to detect novel objects from only a few annotated examples, using a meta feature learner and a reweighting module within a one-stage detection architecture.
Proceedings ArticleDOI
Strip Pooling: Rethinking Spatial Pooling for Scene Parsing
TL;DR: Qibin et al. as mentioned in this paper proposed a strip pooling strategy, which considers a long but narrow kernel, i.e., 1xN or Nx1, to capture long-range contextual information for pixel-wise prediction tasks.
Posted Content
$A^2$-Nets: Double Attention Networks
TL;DR: This work proposes the "double attention block", a novel component that aggregates and propagates informative global features from the entire spatio-temporal space of input images/videos, enabling subsequent convolution layers to access featuresFrom the entire space efficiently.