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..
Combinatorial Inference against Label Noise
Authors: Paul Hongsuck Seo, Geeho Kim, Bohyung Han
NeurIPS 2019 | Venue PDF | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Our extensive experiments demonstrate outstanding performance in terms of accuracy and efficiency compared to the stateof-the-art methods under various synthetic noise configurations and in a real-world noisy dataset. |
| Researcher Affiliation | Academia | Paul Hongsuck Seo Computer Vision Lab. POSTECH EMAIL Geeho Kim Bohyung Han Computer Vision Lab. & ASRI Seoul National University EMAIL |
| Pseudocode | No | The paper describes algorithms and methods in detail using prose and mathematical equations, but it does not include any explicitly labeled 'Pseudocode' or 'Algorithm' blocks or figures. |
| Open Source Code | No | The paper does not provide any statements about open-sourcing the code for the described methodology or a link to a code repository. |
| Open Datasets | Yes | We conduct a set of experiments on Caltech-UCSD Birds-200-2011 (CUB200) dataset [39] with various noise settings... We also conduct experiments on a real-world noisy benchmark, Web Vision [4]. |
| Dataset Splits | Yes | CUB-200 is a fine-grained classification benchmark with 200 bird species and contains 30 images per class in the training and validation sets. |
| Hardware Specification | No | The paper does not specify the exact hardware used for experiments, such as GPU models, CPU types, or cloud computing instances. |
| Software Dependencies | No | The paper mentions using 'Res Net-50 as the backbone network' and 'deep neural network', but it does not provide specific software names with version numbers (e.g., Python, PyTorch, TensorFlow versions). |
| Experiment Setup | Yes | The entire network is fine-tuned for 40 epochs by a mini-batch stochastic gradient descent method with batch size of 32, momentum of 0.9 and weight decaying factor of 5 10 4. The initial learning rate is 0.01 and decayed by a factor of 0.1 at epoch 20 and 30. |