Adaptive Object Detection Using Adjacency and Zoom Prediction

by   Yongxi Lu, et al.
University of Illinois at Urbana-Champaign
University of California, San Diego

State-of-the-art object detection systems rely on an accurate set of region proposals. Several recent methods use a neural network architecture to hypothesize promising object locations. While these approaches are computationally efficient, they rely on fixed image regions as anchors for predictions. In this paper we propose to use a search strategy that adaptively directs computational resources to sub-regions likely to contain objects. Compared to methods based on fixed anchor locations, our approach naturally adapts to cases where object instances are sparse and small. Our approach is comparable in terms of accuracy to the state-of-the-art Faster R-CNN approach while using two orders of magnitude fewer anchors on average. Code is publicly available.


page 2

page 6


Fast Efficient Object Detection Using Selective Attention

Deep learning object detectors achieve state-of-the-art accuracy at the ...

RRPN: Radar Region Proposal Network for Object Detection in Autonomous Vehicles

Region proposal algorithms play an important role in most state-of-the-a...

Dynamic Proposals for Efficient Object Detection

Object detection is a basic computer vision task to loccalize and catego...

CPM R-CNN: Calibrating Point-guided Misalignment in Object Detection

In object detection, offset-guided and point-guided regression dominate ...

Scale Normalized Image Pyramids with AutoFocus for Object Detection

We present an efficient foveal framework to perform object detection. A ...

It's All About The Scale -- Efficient Text Detection Using Adaptive Scaling

"Text can appear anywhere". This property requires us to carefully proce...

Localizing Grouped Instances for Efficient Detection in Low-Resource Scenarios

State-of-the-art detection systems are generally evaluated on their abil...

Please sign up or login with your details

Forgot password? Click here to reset