B
Bharath Hariharan
Researcher at Facebook
Publications - 53
Citations - 35162
Bharath Hariharan is an academic researcher from Facebook. The author has contributed to research in topics: Computer science & Object detection. The author has an hindex of 29, co-authored 35 publications receiving 23703 citations. Previous affiliations of Bharath Hariharan include University of California, Berkeley & University of California.
Papers
More filters
Proceedings ArticleDOI
Feature Pyramid Networks for Object Detection
TL;DR: This paper exploits the inherent multi-scale, pyramidal hierarchy of deep convolutional networks to construct feature pyramids with marginal extra cost and achieves state-of-the-art single-model results on the COCO detection benchmark without bells and whistles.
Posted Content
Feature Pyramid Networks for Object Detection
TL;DR: Feature pyramid networks (FPNets) as mentioned in this paper exploit the inherent multi-scale, pyramidal hierarchy of deep convolutional networks to construct feature pyramids with marginal extra cost.
Proceedings ArticleDOI
Semantic contours from inverse detectors
TL;DR: A simple yet effective method for combining generic object detectors with bottom-up contours to identify object contours is presented and a principled way of combining information from different part detectors and across categories is provided.
Proceedings ArticleDOI
Hypercolumns for object segmentation and fine-grained localization
TL;DR: In this paper, the authors define the hypercolumn at a pixel as the vector of activations of all CNN units above that pixel, and use hypercolumns as pixel descriptors.
Book ChapterDOI
Simultaneous Detection and Segmentation
TL;DR: This work builds on recent work that uses convolutional neural networks to classify category-independent region proposals (R-CNN), introducing a novel architecture tailored for SDS, and uses category-specific, top-down figure-ground predictions to refine the bottom-up proposals.