ASSD: Attentive Single Shot Multibox Detector

09/27/2019
by   Jingru Yi, et al.
12

This paper proposes a new deep neural network for object detection. The proposed network, termed ASSD, builds feature relations in the spatial space of the feature map. With the global relation information, ASSD learns to highlight useful regions on the feature maps while suppressing the irrelevant information, thereby providing reliable guidance for object detection. Compared to methods that rely on complicated CNN layers to refine the feature maps, ASSD is simple in design and is computationally efficient. Experimental results show that ASSD competes favorably with the state-of-the-arts, including SSD, DSSD, FSSD and RetinaNet.

READ FULL TEXT

page 3

page 7

research
05/26/2017

Enhancement of SSD by concatenating feature maps for object detection

We propose an object detection method that improves the accuracy of the ...
research
08/01/2019

ScarfNet: Multi-scale Features with Deeply Fused and Redistributed Semantics for Enhanced Object Detection

Convolutional neural network (CNN) has led to significant progress in ob...
research
02/01/2022

Access Control of Object Detection Models Using Encrypted Feature Maps

In this paper, we propose an access control method for object detection ...
research
09/06/2018

MDCN: Multi-Scale, Deep Inception Convolutional Neural Networks for Efficient Object Detection

Object detection in challenging situations such as scale variation, occl...
research
02/11/2019

S-DOD-CNN: Doubly Injecting Spatially-Preserved Object Information for Event Recognition

We present a novel event recognition approach called Spatially-preserved...
research
03/28/2019

Improving Object Detection with Inverted Attention

Improving object detectors against occlusion, blur and noise is a critic...
research
12/16/2022

DQnet: Cross-Model Detail Querying for Camouflaged Object Detection

Camouflaged objects are seamlessly blended in with their surroundings, w...

Please sign up or login with your details

Forgot password? Click here to reset