Bag of Freebies for Training Object Detection Neural Networks

02/11/2019
by   Zhi Zhang, et al.
2

Comparing with enormous research achievements targeting better image classification models, efforts applied to object detector training are dwarfed in terms of popularity and universality. Due to significantly more complex network structures and optimization targets, various training strategies and pipelines are specifically designed for certain detection algorithms and no other. In this work, we explore universal tweaks that help boosting the performance of state-of-the-art object detection models to a new level without sacrificing inference speed. Our experiments indicate that these freebies can be as much as 5 applying to object detection training to a certain degree.

READ FULL TEXT

page 3

page 4

page 6

research
04/07/2016

A Classification Leveraged Object Detector

Currently, the state-of-the-art image classification algorithms outperfo...
research
03/09/2022

Evaluation of YOLO Models with Sliced Inference for Small Object Detection

Small object detection has major applications in the fields of UAVs, sur...
research
04/09/2019

Towards Universal Object Detection by Domain Attention

Despite increasing efforts on universal representations for visual recog...
research
11/14/2022

Butterfly Effect Attack: Tiny and Seemingly Unrelated Perturbations for Object Detection

This work aims to explore and identify tiny and seemingly unrelated pert...
research
08/26/2020

Determinantal Point Process as an alternative to NMS

We present a determinantal point process (DPP) inspired alternative to n...
research
09/06/2019

Testing Deep Learning Models for Image Analysis Using Object-Relevant Metamorphic Relations

Deep learning models are widely used for image analysis. While they offe...
research
04/27/2015

Mid-level Elements for Object Detection

Building on the success of recent discriminative mid-level elements, we ...

Please sign up or login with your details

Forgot password? Click here to reset