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..
A Baseline for Few-Shot Image Classification
Authors: Guneet Singh Dhillon, Pratik Chaudhari, Avinash Ravichandran, Stefano Soatto
ICLR 2020 | Venue PDF | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | We show results of transductive ο¬ne-tuning on benchmark datasets in few-shot learning, namely Mini-Image Net (Vinyals et al., 2016), Tiered-Image Net (Ren et al., 2018), CIFAR-FS (Bertinetto et al., 2018) and FC-100 (Oreshkin et al., 2018), in Section 4.1. |
| Researcher Affiliation | Collaboration | Guneet S. Dhillon1, Pratik Chaudhari2 , Avinash Ravichandran1, Stefano Soatto1,3 1Amazon Web Services, 2University of Pennsylvania, 3University of California, Los Angeles |
| Pseudocode | No | The paper describes methods through text and mathematical equations, but does not include any formally labeled pseudocode or algorithm blocks. |
| Open Source Code | No | The paper does not provide an explicit statement or link indicating that the source code for their described methodology is open-source. |
| Open Datasets | Yes | The Mini-Image Net dataset (Vinyals et al., 2016)...we obtained the dataset from the authors of Gidaris & Komodakis (2018)3 https://github.com/gidariss/Few Shot Without Forgetting |
| Dataset Splits | Yes | Each dataset has a training, validation and test set consisting of disjoint sets of classes. |
| Hardware Specification | Yes | We use data parallelism across 8 Nvidia V100 GPUs and half-precision training using techniques from Micikevicius et al. (2017); Howard et al. (2018). |
| Software Dependencies | No | The paper mentions various software components and techniques (e.g., SGD, Adam, batch-normalization), but does not provide specific version numbers for the software dependencies needed for replication. |
| Experiment Setup | Yes | We pre-train using standard data augmentation, cross-entropy loss with label smoothing (Szegedy et al., 2016) of Ο΅=0.1, mixup regularization (Zhang et al., 2017) of Ξ±=0.25, SGD with batch-size of 256, Nesterov s momentum of 0.9, weight-decay of 10 4 and no dropout. |