SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1707.03017 · 2017

Learning Visual Reasoning Without Strong Priors

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

Achieving artificial visual reasoning - the ability to answer image-related questions which require a multi-step, high-level process - is an important step towards artificial general intelligence. This multi-modal task requires learning a question-dependent, structured reasoning process over images from language. Standard deep learning approaches tend to exploit biases in the data rather than learn this underlying structure, while leading methods learn to visually reason successfully but are hand-crafted for reasoning. We show that a general-purpose, Conditional Batch Normalization approach achieves state-of-the-art results on the CLEVR Visual Reasoning benchmark with a 2.4% error rate. We outperform the next best end-to-end method (4.5%) and even methods that use extra supervision (3.1%). We probe our model to shed light on how it reasons, showing it has learned a question-dependent, multi-step process. Previous work has operated under the assumption that visual reasoning calls for a specialized architecture, but we show that a general architecture with proper conditioning can learn to visually reason effectively.

For agents

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

get_harvested_code_for_paper("1707.03017")
get_code_for_paper("1707.03017")
have("1707.03017")

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

curl https://syntology.ai/api/ran/1707.03017.json

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

[![Syntology run record](https://syntology.ai/api/ran/1707.03017.svg)](https://syntology.ai/paper/1707.03017)

Connect an agent — have() is free.