DeepAI AI Chat
Log In Sign Up

SaccadeNet: A Fast and Accurate Object Detector

by   Shiyi Lan, et al.
University of Maryland

Object detection is an essential step towards holistic scene understanding. Most existing object detection algorithms attend to certain object areas once and then predict the object locations. However, neuroscientists have revealed that humans do not look at the scene in fixed steadiness. Instead, human eyes move around, locating informative parts to understand the object location. This active perceiving movement process is called saccade. object detector called SaccadeNet. It contains four main modules, the , the , the , and the , which allows it to attend to different informative object keypoints, and predict object locations from coarse to fine. The  is used only during training to extract more informative corner features which brings free-lunch performance boost. On the MS COCO dataset, we achieve the performance of 40.4% mAP at 28 FPS and 30.5% mAP at 118 FPS. Among all the real-time object detectors, than 25 FPS, our SaccadeNet achieves the best detection performance, which demonstrates the effectiveness of the proposed detection mechanism.


Multiple receptive fields and small-object-focusing weakly-supervised segmentation network for fast object detection

Object detection plays an important role in various visual applications....

Object detection can be improved using human-derived contextual expectations

Each object in the world occurs in a specific context: cars are seen on ...

Context Forest for efficient object detection with large mixture models

We present Context Forest (ConF), a technique for predicting properties ...

Boosting in Location Space

The goal of object detection is to find objects in an image. An object d...

Semi-Anchored Detector for One-Stage Object Detection

A standard one-stage detector is comprised of two tasks: classification ...

Active Detection and Localization of Textureless Objects in Cluttered Environments

This paper introduces an active object detection and localization framew...

Selective Convolutional Network: An Efficient Object Detector with Ignoring Background

It is well known that attention mechanisms can effectively improve the p...