$\color{black}\rule{365px}{3px}$

“Deep Residual Learning for Image Recognition” - 2015

Link to Paper:

arxiv.org

Table of Contents

1. Introduction

$\color{black}\rule{365px}{3px}$

Contributions

• Ensemble model won the 1st Place in classification task in ImageNet Large Scale Visual Recognition Challenge(LSVRC) in 2015 with 3.57% top-5 error.
• Also won ILSVRC & COCO 2015 competitions, where the model won the 1st places on the tasks of ImageNet detection, ImageNet localization, COCO detection, and COCO segmentation
• Can go VERY deep. 8 times more deeper than VGG19. (i.e. 152 layers)
• Introduces deep residual learning framework to address the degradation problem.

Motivation