ScratchDet:Exploring to Train Single-Shot Object Detectors from Scratch

10/19/2018
by   Rui Zhu, et al.
0

Current state-of-the-art object objectors are fine-tuned from the off-the-shelf networks pretrained on large-scale classification datasets like ImageNet, which incurs some accessory problems: 1) the domain gap between source and target datasets; 2) the learning objective bias between classification and detection; 3) the architecture limitations of the classification network for detection. In this paper, we design a new single-shot train-from-scratch object detector referring to the architectures of the ResNet and VGGNet based SSD models, called ScratchDet, to alleviate the aforementioned problems. Specifically, we study the impact of BatchNorm on training detectors from scratch, and find that using BatchNorm on the backbone and detection head subnetworks makes the detector converge well from scratch. After that, we explore the network architecture by analyzing the detection performance of ResNet and VGGNet, and introduce a new Root-ResNet backbone network to further improve the accuracy. Extensive experiments on PASCAL VOC 2007, 2012 and MS COCO datasets demonstrate that ScratchDet achieves the state-of-the-art performance among all the train-from-scratch detectors and even outperforms existing one-stage pretrained methods without bells and whistles. Codes will be made publicly available at https://github.com/KimSoybean/ScratchDet.

READ FULL TEXT

page 10

page 11

page 12

research
08/03/2017

DSOD: Learning Deeply Supervised Object Detectors from Scratch

We present Deeply Supervised Object Detector (DSOD), a framework that ca...
research
03/26/2019

DetNAS: Neural Architecture Search on Object Detection

Object detectors are usually equipped with networks designed for image c...
research
08/16/2021

Pixel Difference Networks for Efficient Edge Detection

Recently, deep Convolutional Neural Networks (CNNs) can achieve human-le...
research
09/25/2018

Object Detection from Scratch with Deep Supervision

We propose Deeply Supervised Object Detectors (DSOD), an object detectio...
research
07/29/2019

FSS-1000: A 1000-Class Dataset for Few-Shot Segmentation

Over the past few years, we have witnessed the success of deep learning ...
research
01/19/2019

Consistent Optimization for Single-Shot Object Detection

We present consistent optimization for single stage object detection. Pr...
research
08/14/2017

SSH: Single Stage Headless Face Detector

We introduce the Single Stage Headless (SSH) face detector. Unlike two s...

Please sign up or login with your details

Forgot password? Click here to reset