AI Paper Atlas

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

Insect Identification in the Wild: The AMI Dataset

Aditya Jain, Fagner Cunha, Michael J Bunsen, Juan Sebastián Cañas, Léonard Pasi, Nathan Pinoy, Flemming Helsing, JoAnne Russo, Marc S Botham, Michael Sabourin, Jonathan Fréchette, Alexandre Anctil and 16 more

ECCV 2024 · Label-efficient and robust learning › Recognition and long-tail · approach: Dense features and foundation priors · 21 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 mixed-resolution (MixRes) augmentation on top of RandAugment and random resize crop (ablation)ResNet50 · AMI-Traps NE-America speciesmicro top-1 accuracy (%): 67.88 -> 71.86Improved
add MixRes without other augmentation (ablation)ResNet50 · AMI-Traps NE-America speciesmicro top-1 accuracy (%): 51.46 -> 58.41Improved
add MixRes (ablation)ResNet50 · AMI-GBIF NE-America testmicro accuracy (%): 89.71 -> 89.39Hurt
add RandAugment and random resize crop (ablation)ResNet50 · AMI-Traps NE-America speciesmicro top-1 accuracy (%): 51.46 -> 67.88Improved
raise input resolution from 128 to 224 (ablation)ResNet50 · AMI-Traps NE-America speciesmicro top-1 accuracy (%): 71.86 -> 68.41 (AMI-GBIF 89.39 -> 92.97)No clear effect
pretrain on all AMI-GBIF with ImageNet weights before regional fine-tuning (ablation)ResNet50 · AMI-Traps NE-America speciesmicro top-1 accuracy (%): 71.86 -> 75.06Improved
add square padding of crops at inference (ablation)ResNet50 · AMI-Traps binary (all crops)precision (%): 66.21 -> 68.31Improved
use ConvNeXt-B instead of ResNet50fine-grained classifier · AMI-GBIF NE-America few-shot speciesmicro accuracy (%): 34.03 -> 45.81Improved
use ViT-B/16 on C-America in-distributionfine-grained classifier · AMI-GBIF C-America species testmicro accuracy (%): 88.62 -> 79.80 (ConvNeXt-B vs ViT-B/16)Hurt
train region model with about 10 times fewer images (C-America)fine-grained classifier · AMI-Traps C-America genusmicro top-1 accuracy (%): 85.46 -> 51.92 (NE-America vs C-America ConvNeXt-B)Hurt

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