paper-with-me

홈 › Papers

ImageNot: A contrast with ImageNet preserves model rankings

2024-04-02 · Olawale Salaudeen, Moritz Hardt

We introduce ImageNot, a dataset designed to match the scale of ImageNet while differing drastically in other aspects. We show that key model architectures developed for ImageNet over the years rank identically when trained and evaluated on ImageNot to how they rank on ImageNet. This is true when training models from scratch or fine-tuning them. Moreover, the relative improvements of each model over earlier models strongly correlate in both datasets. We further give evidence that ImageNot has a similar utility as ImageNet for transfer learning purposes. Our work demonstrates a surprising degree of external validity in the relative performance of image classification models. This stands in contrast with absolute accuracy numbers that typically drop sharply even under small changes to a dataset.

📄 PDF Abstract BibTeX arXiv:2404.02112

Code (1)

olawalesalaudeen/imagenot 공식 구현

Tasks

image-classificationImage ClassificationTransfer Learning

Similar Papers 제목 키워드 기반

Feature Extraction for Generative Medical Imaging Evaluation: New Evidence Against an Evolving Trend

2023-11-22 · McKell Woodland, Austin Castelo, Mais Al Taie, Jessica Albuquerque Marques Silva 외

Fr\'echet Inception Distance (FID) is a widely used metric for assessing synthetic image quality. It relies on an ImageNet-based feature extractor, making its applicability to medical imaging unclear. A recent trend is t…

Data AugmentationMedical Image Generation

Anatomy-Aware Contrastive Representation Learning for Fetal Ultrasound

2022-08-22 · Zeyu Fu, Jianbo Jiao, Robail Yasrab, Lior Drukker 외

Self-supervised contrastive representation learning offers the advantage of learning meaningful visual representations from unlabeled medical datasets for transfer learning. However, applying current contrastive learning…

AnatomyContrastive LearningRepresentation LearningTransfer Learning

Chronological Contrastive Learning: Few-Shot Progression Assessment in Irreversible Diseases

2026-03-23 · Clemens Watzenböck, Daniel Aletaha, Michaël Deman, Thomas Deimel 외 arxiv

Quantitative disease severity scoring in medical imaging is costly, time-consuming, and subject to inter-reader variability. At the same time, clinical archives contain far more longitudinal imaging data than expert-anno…

Contrastive LearningFew-Shot Learning

Delta-Based Neural Architecture Search: LLM Fine-Tuning via Code Diffs

2026-05-06 · Santosh Premi Adhikari, Radu Timofte, Dmitry Ignatov arxiv

Large language models (LLMs) show strong potential for neural architecture generation, yet existing approaches produce complete model implementations from scratch -- computationally expensive and yielding verbose code. W…

Neural Architecture SearchCode Generation

A consensus set for the aggregation of partial rankings: the case of the Optimal Set of Bucket Orders Problem

2025-02-19 · Juan A. Aledo, José A. Gámez, Alejandro Rosete

In rank aggregation problems (RAP), the solution is usually a consensus ranking that generalizes a set of input orderings. There are different variants that differ not only in terms of the type of rankings that are used …

Subgroup Discovery