SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2312.12222 · 2023

EarthVQA: Towards Queryable Earth via Relational Reasoning-Based Remote Sensing Visual Question Answering

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 6 functions out of this paper's own repositories and ran 6 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.

RepositoryRoleRan
Junjue-Wang/EarthVQA canonical 6 of 6
FunctionStatusWhere it lives
conv_with_kaiming_uniform Ran Junjue-Wang/EarthVQA/module/seg_base.py
pointer only (licence: NONE) · get_code("6ec207a34e2ddbe3")
cross_entropy_loss Ran Junjue-Wang/EarthVQA/module/loss.py
pointer only (licence: NONE) · get_code("4133a26ae05f4dd9")
ohem_cross_entropy Ran Junjue-Wang/EarthVQA/module/loss.py
pointer only (licence: NONE) · get_code("f9f989173c2cfffe")
positionalencoding1d Ran Junjue-Wang/EarthVQA/module/position_emb.py
pointer only (licence: NONE) · get_code("8b71e70e06f0cfbd")
positionalencoding2d Ran Junjue-Wang/EarthVQA/module/position_emb.py
pointer only (licence: NONE) · get_code("37d52453adf46f82")
som Ran Junjue-Wang/EarthVQA/module/loss.py
pointer only (licence: NONE) · get_code("c3ab88bb5ff98da6")

Repositories linked to this paper

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

Abstract

Earth vision research typically focuses on extracting geospatial object locations and categories but neglects the exploration of relations between objects and comprehensive reasoning. Based on city planning needs, we develop a multi-modal multi-task VQA dataset (EarthVQA) to advance relational reasoning-based judging, counting, and comprehensive analysis. The EarthVQA dataset contains 6000 images, corresponding semantic masks, and 208,593 QA pairs with urban and rural governance requirements embedded. As objects are the basis for complex relational reasoning, we propose a Semantic OBject Awareness framework (SOBA) to advance VQA in an object-centric way. To preserve refined spatial locations and semantics, SOBA leverages a segmentation network for object semantics generation. The object-guided attention aggregates object interior features via pseudo masks, and bidirectional cross-attention further models object external relations hierarchically. To optimize object counting, we propose a numerical difference loss that dynamically adds difference penalties, unifying the classification and regression tasks. Experimental results show that SOBA outperforms both advanced general and remote sensing methods. We believe this dataset and framework provide a strong benchmark for Earth vision's complex analysis. The project page is at https://Junjue-Wang.github.io/homepage/EarthVQA.

For agents

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

get_harvested_code_for_paper("2312.12222")
get_code_for_paper("2312.12222")
have("2312.12222")

Connect an agent — have() is free.