Notice: The reproducibility variables underlying each score are classified using an automated LLM-based pipeline, validated against a manually labeled dataset. LLM-based classification introduces uncertainty and potential bias; scores should be interpreted as estimates. Full accuracy metrics and methodology are described in Coakley et alK. L. Coakley, T. Snelleman, H. Hoos, and O. E. Gundersen, "The embrace of open science: An analysis of a decade of AI research and 56 800 conference papers," Under Review, 2026..
FOCUS: Familiar Objects in Common and Uncommon Settings
Authors: Priyatham Kattakinda, Soheil Feizi
ICML 2022 | Venue PDF | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | We present a detailed analysis of the performance of various popular image classifiers on our dataset and demonstrate a clear drop in accuracy when classifying images in uncommon settings. We also show that finetuning a model on our dataset drastically improves its ability to focus on the object of interest leading to better generalization. |
| Researcher Affiliation | Academia | 1University of Maryland, College Park, MD, USA. |
| Pseudocode | No | The paper does not contain any structured pseudocode or algorithm blocks. |
| Open Source Code | Yes | Our dataset and code for evaluating models on FOCUS are available at https://github.com/priyathamkat/focus. |
| Open Datasets | Yes | Our dataset and code for evaluating models on FOCUS are available at https://github.com/priyathamkat/focus. |
| Dataset Splits | No | We start by randomly splitting the dataset into train and test sets, which are 70% and 30% of the dataset in size, respectively. |
| Hardware Specification | No | The paper does not specify the hardware used for experiments, such as particular GPU or CPU models. |
| Software Dependencies | No | The paper mentions software like PyTorch, EfficientNet-PyTorch, CLIP, and timm, but does not provide specific version numbers for any of them. |
| Experiment Setup | Yes | We use SGD with a learning rate of 1e-4 to update the last layer (fully-connected layer) of each model for 10 epochs of the train split. |