BAOD: Budget-Aware Object Detection

04/10/2019
by   Alejandro Pardo, et al.
0

We study the problem of object detection from a novel perspective in which annotation budget constraints are taken into consideration, appropriately coined Budget Aware Object Detection (BAOD). When provided with a fixed budget, we propose a strategy for building a diverse and informative dataset that can be used to optimally train a robust detector. We investigate both optimization and learning-based methods to sample which images to annotate and what type of annotation (strongly or weakly supervised) to annotate them with. We adopt a hybrid supervised learning framework to train the object detector from both these types of annotation. We conduct a comprehensive empirical study showing that a handcrafted optimization method outperforms other selection techniques including random sampling, uncertainty sampling and active learning. By combining an optimal image/annotation selection scheme with hybrid supervised learning to solve the BAOD problem, we show that one can achieve the performance of a strongly supervised detector on PASCAL-VOC 2007 while saving 12.8 budget is used, it surpasses this performance by 2.0 mAP percentage points.

READ FULL TEXT

page 5

page 7

page 8

page 16

page 17

page 18

page 19

page 20

research
11/21/2022

Plug and Play Active Learning for Object Detection

Annotating data for supervised learning is expensive and tedious, and we...
research
02/20/2020

Learning Object Scale With Click Supervision for Object Detection

Weakly-supervised object detection has recently attracted increasing att...
research
02/10/2018

Collaborative Learning for Weakly Supervised Object Detection

Weakly supervised object detection has recently received much attention,...
research
12/28/2020

Data-efficient Weakly-supervised Learning for On-line Object Detection under Domain Shift in Robotics

Several object detection methods have recently been proposed in the lite...
research
09/06/2022

MACAB: Model-Agnostic Clean-Annotation Backdoor to Object Detection with Natural Trigger in Real-World

Object detection is the foundation of various critical computer-vision t...
research
10/21/2020

UFO^2: A Unified Framework towards Omni-supervised Object Detection

Existing work on object detection often relies on a single form of annot...
research
11/25/2018

Dissimilarity Coefficient based Weakly Supervised Object Detection

We consider the problem of weakly supervised object detection, where the...

Please sign up or login with your details

Forgot password? Click here to reset