SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2410.01083 · ECCV · 2024

Deep Nets with Subsampling Layers Unwittingly Discard Useful Activations at Test-Time

Raymond Yeh, Ziwei Liu, Chiao-An Yang

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

Subsampling layers play a crucial role in deep nets by discarding a portion of an activation map to reduce its spatial dimensions. This encourages the deep net to learn higher-level representations. Contrary to this motivation, we hypothesize that the discarded activations are useful and can be incorporated on the fly to improve models' prediction. To validate our hypothesis, we propose a search and aggregate method to find useful activation maps to be used at test-time. We applied our approach to the task of image classification and semantic segmentation. Extensive experiments over nine different architectures on ImageNet, CityScapes, and ADE20K show that our method consistently improves model test-time performance. Additionally, it complements existing testtime augmentation techniques to provide further performance gains.

For agents

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

get_harvested_code_for_paper("2410.01083")
get_code_for_paper("2410.01083")
have("2410.01083")

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

curl https://syntology.ai/api/ran/2410.01083.json

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

[![Syntology run record](https://syntology.ai/api/ran/2410.01083.svg)](https://syntology.ai/paper/2410.01083)

Connect an agent — have() is free.