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..
Contrastive Learning for Image Captioning
Authors: Bo Dai, Dahua Lin
NeurIPS 2017 | Venue PDF | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | We tested our method on two challenging datasets, where it improves the baseline model by significant margins. |
| Researcher Affiliation | Academia | Bo Dai Dahua Lin Department of Information Engineering, The Chinese University of Hong Kong EMAIL EMAIL |
| Pseudocode | No | No structured pseudocode or algorithm blocks were found in the paper. |
| Open Source Code | No | No explicit statement about providing open-source code or a link to a code repository for the methodology was found. |
| Open Datasets | Yes | We use two large scale datasets to test our contrastive learning method. The first dataset is MSCOCO [13]... A more challenging dataset, Insta PIC-1.1M [18], is used as the second dataset... |
| Dataset Splits | Yes | The first dataset is MSCOCO [13], which contains 122, 585 images for training and validation. Following splits in [15], we reserved 2, 000 images for validation. ... In practice, we reserved 2, 000 images from the training set for validation. |
| Hardware Specification | No | No specific hardware details (e.g., GPU/CPU models, memory, or specific computing environments with specifications) used for running experiments were mentioned in the paper. |
| Software Dependencies | No | The paper mentions using "Adam optimizer" but does not specify any software versions for programming languages, libraries, or other dependencies. |
| Experiment Setup | Yes | In all our experiments, we fixed the learning rate to be 1e-6 for all components, and used Adam optimizer. |