AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

A Step Towards Worldwide Biodiversity Assessment: The BIOSCAN-1M Insect Dataset

NeurIPS 2023 · Label-efficient and robust learning › Recognition and long-tail · approach: Contrastive learning for imbalanced data · 9 citations (OpenAlex)

Read the paperCheck your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's title only (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
Use Cross-Entropy instead of Focal loss (ablation)BIOSCAN image-classification baseline · BIOSCAN-Order and BIOSCAN-Diptera validationmicro top-1 accuracy: 99.58$\pm$0.21 -> 99.62$\pm$0.06Helped
Use ViT-B/16 instead of ResNet-50 (ablation)BIOSCAN image-classification baseline · BIOSCAN-Order and BIOSCAN-Diptera validationmacro top-1 accuracy: 86.26$\pm$0.30 -> 87.36$\pm$1.20Mixed
Crop images before classification (ablation)ResNet-50 preliminary experiments · BIOSCAN insect imagesclassification performanceHelped
Use more training data, moving from Small to LargeViT-B/16 + Cross-Entropy baseline · BIOSCAN-Order testmicro top-1 accuracy: 97.86 -> 99.69Helped

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