AI Paper Atlas

Research map / Architectures and efficiency / RNNs and normalization

[Re] Learning to count everything

Maša Kljun, Matija Teršek, Domen Vreš

NeurIPS 2022 · Architectures and efficiency › RNNs and normalization · approach: Dataset distillation and data-efficient training

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
Use 2 exemplars instead of 1 (ablation)FamNet · FSC-147 Val SetMAE: 26.55 -> 24.09Improved
Use 2 exemplars instead of 1 (ablation)FamNet · FSC-147 Val SetRMSE: 77.01 -> 72.37Improved
Use 3 exemplars instead of 2 (ablation)FamNet · FSC-147 Val SetMAE: 24.09 -> 23.75Improved
Use 3 exemplars instead of 2 (ablation)FamNet · FSC-147 Val SetRMSE: 72.37 -> 69.07Improved
Add multi-scale image feature (ablation)FamNet · FSC-147 Val SetMAE: 32.70 -> 27.80Improved
Add multi-scale image feature (ablation)FamNet · FSC-147 Val SetRMSE: 104.31 -> 93.53Improved
Add multi-scale exemplar feature (ablation)FamNet · FSC-147 Val SetMAE: 27.80 -> 24.32Improved
Add multi-scale exemplar feature (ablation)FamNet · FSC-147 Val SetRMSE: 93.53 -> 70.94Improved
Add test-time adaptation (ablation)FamNet with multi-scale image and exemplar features · FSC-147 Val SetMAE: 24.32 -> 23.75Improved
Add test-time adaptation (ablation)FamNet with multi-scale image and exemplar features · FSC-147 Val SetRMSE: 70.94 -> 69.07Improved
Train FamNet on CARPK dataFamNet-- on CARPK · CARPKMAE: 28.84 -> 18.19Improved
Train FamNet on CARPK dataFamNet-- on CARPK · CARPKRMSE: 44.47 -> 33.66Improved

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