Context-aware Single-Shot Detector

07/27/2017
by   Wei Xiang, et al.
0

SSD is one of the state-of-the-art object detection algorithms, and it combines high detection accuracy with real-time speed. However, it is widely recognized that SSD is less accurate in detecting small objects compared to large objects, because it ignores the context from outside the proposal boxes. In this paper, we present CSSD--a shorthand for context-aware single-shot multibox object detector. CSSD is built on top of SSD, with additional layers modeling multi-scale contexts. We describe two variants of CSSD, which differ in their context layers, using dilated convolution layers (DiCSSD) and deconvolution layers (DeCSSD) respectively. The experimental results show that the multi-scale context modeling significantly improves the detection accuracy. In addition, we study the relationship between effective receptive fields (ERFs) and the theoretical receptive fields (TRFs), particularly on a VGGNet. The empirical results further strengthen our conclusion that SSD coupled with context layers achieves better detection results especially for small objects (+3.2% AP_@0.5 on MS-COCO compared to the newest SSD), while maintaining comparable runtime performance.

READ FULL TEXT

page 3

page 8

page 11

page 12

research
01/23/2017

DSSD : Deconvolutional Single Shot Detector

The main contribution of this paper is an approach for introducing addit...
research
10/01/2020

Multiscale Detection of Cancerous Tissue in High Resolution Slide Scans

We present an algorithm for multi-scale tumor (chimeric cell) detection ...
research
12/08/2017

Weaving Multi-scale Context for Single Shot Detector

Aggregating context information from multiple scales has been proved to ...
research
01/18/2020

NETNet: Neighbor Erasing and Transferring Network for Better Single Shot Object Detection

Due to the advantages of real-time detection and improved performance, s...
research
12/10/2019

MDFN: Multi-Scale Deep Feature Learning Network for Object Detection

This paper proposes an innovative object detector by leveraging deep fea...
research
12/14/2015

Inside-Outside Net: Detecting Objects in Context with Skip Pooling and Recurrent Neural Networks

It is well known that contextual and multi-scale representations are imp...
research
12/28/2016

FastMask: Segment Multi-scale Object Candidates in One Shot

Objects appear to scale differently in natural images. This fact require...

Please sign up or login with your details

Forgot password? Click here to reset