AI Paper Atlas

Research map / Label-efficient and robust learning / Self-supervised and contrastive

CSP: Self-Supervised Contrastive Spatial Pre-Training for Geospatial-Visual Representations

Gengchen Mai, Ni Lao, Yutong He, Jiaming Song, Stefano Ermon

ICML 2023 · Label-efficient and robust learning › Self-supervised and contrastive · approach: Contrastive versus non-contrastive theory · 14 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Add CSP-MC-BLD spatial contrastive pre-traininggeospatial-visual classification · iNat2018, labeled training ratios 5%, 10%, 20%, and 100%Top1 accuracy: Sup. Only (grid) to CSP-MC-BLD: 8.16 (0.01) -> 9.01 (0.02); 14.65 (0.03) -> 19.68 (0.05); 25.40 (0.05) -> 29.61 (0.03); Improved
Add CSP-MC-BLD spatial contrastive pre-traininggeospatial-visual classification · fMoW, labeled training ratios 5%, 10%, 20%, and 100%Top1 accuracy: Sup. Only (grid) to CSP-MC-BLD: 67.01 (0.02) -> 67.47 (0.02); 68.91 (0.04) -> 69.23 (0.03); 70.20 (0.03) -> 70.66 (0.03)Improved
Use the MC objective instead of NCECSP-BLD · iNat2018, all four training ratiosTop1 accuracy: 8.65 (0.02) -> 9.01 (0.02); 18.75 (0.12) -> 19.68 (0.05); 28.15 (0.07) -> 29.61 (0.03); 73.33 (0.01) -> 73.79 (0.02)Improved
Use the MC objective instead of NCECSP-BLD · fMoW, all four training ratiosTop1 accuracy: 67.29 (0.03) -> 67.47 (0.02); 69.20 (0.03) -> 69.23 (0.03); 70.65 (0.02) -> 70.66 (0.03); 70.89 (0.04) -> 71.00 (0.02)Improved
Add random negative location sampling (ablation)CSP-MC-BLD · iNat2018 validation, 5%Top1 accuracy: 8.63 -> 9.01Improved
Add SimCSE sampling (ablation)CSP-MC-BLD · iNat2018 validation, 5%Top1 accuracy: 8.40 -> 9.01Improved
Add random negative location and SimCSE sampling (ablation)CSP-MC-B · iNat2018 validation, 5%Top1 accuracy: 8.16 -> 9.01Improved
Set location embedding dimension to 256 (ablation)CSP-MC-BLD · iNat2018 validation, 5%, 10%, and 20%Top1 accuracy: d=256: 9.01, 19.68, 29.61; the paper reports these dimensions achieve the best performance at few-shot ratiosImproved
Set location embedding dimension to 1024 (ablation)CSP-MC-BLD · iNat2018 validation, 100%Top1 accuracy: 73.79Improved
Use ViT instead of InceptionV3 as the image encoder (ablation)CSP-MC-BLD · iNat2018 validation, 5%Top1 accuracy: 9.01 -> 20.78Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy