Exploring Figure-Ground Assignment Mechanism in Perceptual Organization
Nov 28, 2022
Speakers
Jing Zhang
Speaker · 0 followers
Zheng-Jun Zha
Speaker · 0 followers
About
Perceptual organization is a challenging visual task that aims to perceive and group the individual visual element so that it is easy to understand the meaning of the scene as a whole. Most recent methods building upon advanced Convolutional Neural Network (CNN) come from learning discriminative representation and modeling context hierarchically. However, when the visual appearance difference between foreground and background is obscure, the performance of existing methods degrades significantly due to the visual ambiguity in the discrimination process. In this paper, we argue that the figure-ground assignment mechanism, which conforms to human vision cognitive theory, can be explored to empower CNN to achieve a robust perceptual organization despite visual ambiguity. Specifically, we present a novel Figure-Ground-Aided (FGA) module to learn the configural statistics of the visual scene and leverage it for the reduction of visual ambiguity. Particularly, we demonstrate the benefit of using stronger supervisory signals by teaching (FGA) module to perceive configural cues, i.e., convexity and lower region, that human deem important for the perceptual organization. Furthermore, an Interactive Enhancement Module (IEM) is devised to leverage such configural priors to assist representation learning, thereby achieving robust perception organization with complex visual ambiguities. In addition, a well-founded visual segregation test is designed to validate the capability of the proposed FGA mechanism explicitly. Comprehensive evaluation results demonstrate our proposed FGA mechanism can effectively enhance the capability of perception organization on various baseline models. Nevertheless, the model augmented via our proposed FGA mechanism also outperforms state-of-the-art approaches on four challenging real-world applications. The source code will be made available to the public.Perceptual organization is a challenging visual task that aims to perceive and group the individual visual element so that it is easy to understand the meaning of the scene as a whole. Most recent methods building upon advanced Convolutional Neural Network (CNN) come from learning discriminative representation and modeling context hierarchically. However, when the visual appearance difference between foreground and background is obscure, the performance of existing methods degrades significantly…
Organizer
NeurIPS 2022
Account · 961 followers
Like the format? Trust SlidesLive to capture your next event!
Professional recording and live streaming, delivered globally.
Sharing
Recommended Videos
Presentations on similar topic, category or speaker
Introduction and opening remarks
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
TaSIL: Taylor Series Imitation Learning
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Simplifying Model-based RL: Learning Representations, Latent-space Models, and Policies with One Objective
Watch later
Raj Ghugare, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
The Burer-Monteiro SDP method can fail even above the Barvinok-Pataki bound
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Mitigating Dataset Bias by Using Per-sample Gradient
Watch later
Sumyeong Ahn, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Online Frank-Wolfe with Arbitrary Delays
Watch later
Yuanyu Wan, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%