SaccadeDet: A Novel Dual-Stage Architecture for Rapid and Accurate Detection in Gigapixel Images

TL;DR

SaccadeDet is a dual-stage architecture inspired by human eye movements that efficiently detects objects in gigapixel images by focusing on regions of interest, significantly reducing computational costs and increasing speed.

Contribution

It introduces a novel two-stage detection framework tailored for gigapixel images, combining region proposal and refinement inspired by saccadic eye movements.

Findings

Achieves 8x faster detection than existing methods

Effectively processes gigapixel images with reduced computational load

Demonstrates potential in medical pathology analysis

Abstract

The advancement of deep learning in object detection has predominantly focused on megapixel images, leaving a critical gap in the efficient processing of gigapixel images. These super high-resolution images present unique challenges due to their immense size and computational demands. To address this, we introduce 'SaccadeDet', an innovative architecture for gigapixel-level object detection, inspired by the human eye saccadic movement. The cornerstone of SaccadeDet is its ability to strategically select and process image regions, dramatically reducing computational load. This is achieved through a two-stage process: the 'saccade' stage, which identifies regions of probable interest, and the 'gaze' stage, which refines detection in these targeted areas. Our approach, evaluated on the PANDA dataset, not only achieves an 8x speed increase over the state-of-the-art methods but also demonstrates significant potential in gigapixel-level pathology analysis through its application to Whole Slide Imaging.