AI Paper Atlas

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

Focus on the Positives: Self-Supervised Learning for Biodiversity Monitoring

Omiros Pantazis, Gabriel J. Brostow, Kate E. Jones, Oisin Mac Aodha

ICCV 2021 · Label-efficient and robust learning › Self-supervised and contrastive · approach: Invariance-based self-supervised learning · 26 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
select positives by sequence (same location, within 5 s) instead of augmentationSimCLR · CCT20 (1% labels)top-1 accuracy: 65.75 -> 67.60Improved
select positives by context similarity instead of augmentationSimCLR · CCT20 (1% labels)top-1 accuracy: 65.75 -> 68.67Improved
select positives by sequence instead of augmentationTriplet · CCT20 (1% labels)top-1 accuracy: 59.13 -> 66.30Improved
select positives by context instead of augmentationSimSiam · CCT20 (1% labels)top-1 accuracy: 56.64 -> 59.93Improved
select positives by context instead of augmentationSimCLR · MMCT (1% labels, GT boxes)top-1 accuracy: 54.93 -> 64.01Improved
select positives by context instead of augmentationSimSiam · MMCT (1% labels, GT boxes)top-1 accuracy: 48.78 -> 61.66Improved
use context positives on a satellite datasetSimCLR · FMoW subset (1% labels)top-1 accuracy: 45.60 -> 45.93Improved
use sequence positives instead of standard on FMoWSimCLR · FMoW subset (100% labels)top-1 accuracy: 52.16 -> 50.85Hurt
initialize backbone with ImageNet instead of random weights (ablation)SimCLR Standard · CCT20 (1% labels)top-1 accuracy: 53.29 -> 65.75Improved
use context positives under random init (ablation)SimCLR · CCT20 (1% labels, random init)top-1 accuracy: 53.29 -> 58.86Improved
increase capacity to ResNet50 at 224px (ablation)SimCLR Standard · CCT20 (1% labels)top-1 accuracy: 65.75 -> 68.59Improved
fine-tune end-to-end after context SSL instead of linear eval (ablation)SimCLR Seq. Pos. · CCT20 (1% labels)top-1 accuracy: 67.60 -> 72.56Improved

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