SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2204.00484 · CVPR · 2022

Proper Reuse of Image Classification Features Improves Object Detection

Vincent Dumoulin, Vighnesh Birodkar, Cristina Vasconcelos

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

ResNet-101 FPN ResNet-101 NAS-FPN ResNet-101 Cascade NAS-FPN ResNet-50 Cascade NAS-FPN Freeze backbone Figure 1. Impact on object detection performance of preserving and not fine-tuning features learned on ImageNet. The arrows indicate impact on each model, when trained with frozen backbone weights. As long as the remaining detector components have enough capacity (left), freezing increases performance while significantly reducing resources used during training (right).

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2204.00484")
get_code_for_paper("2204.00484")
have("2204.00484")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2204.00484.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2204.00484.svg)](https://syntology.ai/paper/2204.00484)

Connect an agent — have() is free.