CVAILGApr 8, 2021

HindSight: A Graph-Based Vision Model Architecture For Representing Part-Whole Hierarchies

arXiv:2104.03722v11 citations
Originality Incremental advance
AI Analysis

This addresses the challenge of encoding hierarchical visual information for computer vision applications, but it appears incremental as it builds on existing graph and self-supervised techniques.

The paper tackles the problem of representing part-whole hierarchies in images by proposing a graph-based model architecture that divides images into patches at different levels and uses a dynamic feature extraction module to learn rich graph representations. The result is a general-purpose vision encoder model that can be applied to various downstream tasks like image classification and object detection.

This paper presents a model architecture for encoding the representations of part-whole hierarchies in images in form of a graph. The idea is to divide the image into patches of different levels and then treat all of these patches as nodes for a fully connected graph. A dynamic feature extraction module is used to extract feature representations from these patches in each graph iteration. This enables us to learn a rich graph representation of the image that encompasses the inherent part-whole hierarchical information. Utilizing proper self-supervised training techniques, such a model can be trained as a general purpose vision encoder model which can then be used for various vision related downstream tasks (e.g., Image Classification, Object Detection, Image Captioning, etc.).

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes