Universal Bounding Box Regression and Its Applications

04/15/2019
by   Seungkwan Lee, et al.
0

Bounding-box regression is a popular technique to refine or predict localization boxes in recent object detection approaches. Typically, bounding-box regressors are trained to regress from either region proposals or fixed anchor boxes to nearby bounding boxes of a pre-defined target object classes. This paper investigates whether the technique is generalizable to unseen classes and is transferable to other tasks beyond supervised object detection. To this end, we propose a class-agnostic and anchor-free box regressor, dubbed Universal Bounding-Box Regressor (UBBR), which predicts a bounding box of the nearest object from any given box. Trained on a relatively small set of annotated images, UBBR successfully generalizes to unseen classes, and can be used to improve localization in many vision problems. We demonstrate its effectivenss on weakly supervised object detection and object discovery.

READ FULL TEXT

page 4

page 5

page 8

page 9

page 12

research
08/03/2021

Boosting Weakly Supervised Object Detection via Learning Bounding Box Adjusters

Weakly-supervised object detection (WSOD) has emerged as an inspiring re...
research
06/21/2020

Semi-Supervised Object Detection with Sparsely Annotated Dataset

In training object detector based on convolutional neural networks, sele...
research
04/22/2022

Few-Shot Object Detection with Proposal Balance Refinement

Few-shot object detection has gained significant attention in recent yea...
research
11/01/2017

Single Multi-feature detector for Amodal 3D Object Detection in RGB-D Images

This paper aims at fast and high-accuracy amodal 3D object detections in...
research
06/14/2016

Attend Refine Repeat: Active Box Proposal Generation via In-Out Localization

The problem of computing category agnostic bounding box proposals is uti...
research
10/21/2021

Sequential Decision-Making for Active Object Detection from Hand

A key component of understanding hand-object interactions is the ability...
research
03/31/2022

ImpDet: Exploring Implicit Fields for 3D Object Detection

Conventional 3D object detection approaches concentrate on bounding boxe...

Please sign up or login with your details

Forgot password? Click here to reset