Action-Driven Object Detection with Top-Down Visual Attentions

12/20/2016
by   Donggeun Yoo, et al.
0

A dominant paradigm for deep learning based object detection relies on a "bottom-up" approach using "passive" scoring of class agnostic proposals. These approaches are efficient but lack of holistic analysis of scene-level context. In this paper, we present an "action-driven" detection mechanism using our "top-down" visual attention model. We localize an object by taking sequential actions that the attention model provides. The attention model conditioned with an image region provides required actions to get closer toward a target object. An action at each time step is weak itself but an ensemble of the sequential actions makes a bounding-box accurately converge to a target object boundary. This attention model we call AttentionNet is composed of a convolutional neural network. During our whole detection procedure, we only utilize the actions from a single AttentionNet without any modules for object proposals nor post bounding-box regression. We evaluate our top-down detection mechanism over the PASCAL VOC series and ILSVRC CLS-LOC dataset, and achieve state-of-the-art performances compared to the major bottom-up detection methods. In particular, our detection mechanism shows a strong advantage in elaborate localization by outperforming Faster R-CNN with a margin of +7.1 increase the IoU threshold for positive detection to 0.7.

READ FULL TEXT

page 2

page 4

page 5

page 6

page 7

page 14

research
06/25/2015

AttentionNet: Aggregating Weak Directions for Accurate Object Detection

We present a novel detection method using a deep convolutional neural ne...
research
04/25/2020

Detective: An Attentive Recurrent Model for Sparse Object Detection

In this work, we present Detective - an attentive object detector that i...
research
02/06/2017

Attentional Network for Visual Object Detection

We propose augmenting deep neural networks with an attention mechanism f...
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
10/13/2022

Application-Driven AI Paradigm for Hand-Held Action Detection

In practical applications especially with safety requirement, some hand-...
research
07/05/2018

Detecting Visual Relationships Using Box Attention

In this paper we propose a new model for detecting visual relationships....
research
08/03/2022

Statistical Attention Localization (SAL): Methodology and Application to Object Classification

A statistical attention localization (SAL) method is proposed to facilit...

Please sign up or login with your details

Forgot password? Click here to reset