SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2104.04323 · ICML · 2021

Towards Fine-grained Visual Representations by Combining Contrastive Learning with Image Reconstruction and Attention-weighted Pooling

Berlin, Jonas Dippel, Steffen Vogler, Johannes Höhne, A Bayer

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

This paper presents Contrastive Reconstruction, ConRec -a self-supervised learning algorithm that obtains image representations by jointly optimizing a contrastive and a self-reconstruction loss. We showcase that state-of-the-art contrastive learning methods (e.g. SimCLR) have shortcomings to capture fine-grained visual features in their representations. ConRec extends the SimCLR framework by adding (1) a self-reconstruction task and (2) an attention mechanism within the contrastive learning task. This is accomplished by applying a simple encoder-decoder architecture with two heads. We show that both extensions contribute towards an improved vector representation for images with fine-grained visual features. Combining those concepts, ConRec outperforms SimCLR and SimCLR with Attention-Pooling on finegrained classification datasets.

For agents

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

get_harvested_code_for_paper("2104.04323")
get_code_for_paper("2104.04323")
have("2104.04323")

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

curl https://syntology.ai/api/ran/2104.04323.json

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

[![Syntology run record](https://syntology.ai/api/ran/2104.04323.svg)](https://syntology.ai/paper/2104.04323)

Connect an agent — have() is free.