SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2102.02896 · 2021

Compressed Object Detection

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

Deep learning approaches have achieved unprecedented performance in visual recognition tasks such as object detection and pose estimation. However, state-of-the-art models have millions of parameters represented as floats which make them computationally expensive and constrain their deployment on hardware such as mobile phones and IoT nodes. Most commonly, activations of deep neural networks tend to be sparse thus proving that models are over parametrized with redundant neurons. Model compression techniques, such as pruning and quantization, have recently shown promising results by improving model complexity with little loss in performance. In this work, we extended pruning, a compression technique that discards unnecessary model connections, and weight sharing techniques for the task of object detection. With our approach, we are able to compress a state-of-the-art object detection model by 30.0% without a loss in performance. We also show that our compressed model can be easily initialized with existing pre-trained weights, and thus is able to fully utilize published state-of-the-art model zoos.

For agents

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

get_harvested_code_for_paper("2102.02896")
get_code_for_paper("2102.02896")
have("2102.02896")

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

curl https://syntology.ai/api/ran/2102.02896.json

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

[![Syntology run record](https://syntology.ai/api/ran/2102.02896.svg)](https://syntology.ai/paper/2102.02896)

Connect an agent — have() is free.