Towards Understanding Deep Learning from Noisy Labels with Small-Loss Criterion
Authors: Xian-Jin Gui, Wei Wang, Zhang-Hao Tian
IJCAI 2021 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | In this section, we conduct experiments on synthetic and real-world datasets to verify our theoretical explanation and the reformalization of the small-loss criterion RSL and RSL WM. |
| Researcher Affiliation | Academia | Xian-Jin Gui , Wei Wang and Zhang-Hao Tian National Key Laboratory for Novel Software Technology Nanjing University, Nanjing 210023, China {guixj, wangw, tianzh}@lamda.nju.edu.cn |
| Pseudocode | Yes | Algorithm 1 RSL: Reformalization of Small-Loss criterion |
| Open Source Code | No | The paper does not contain any explicit statements about making its source code publicly available or provide a link to a code repository. |
| Open Datasets | Yes | The CIFAR-10/100 datasets contain 50K (10K) images for training (test). We retain 5K of the training set for validation following [Tanaka et al., 2018]. ... The Web Vision [Li et al., 2017] dataset contains 2.4M noisy labeled images crawled from Flickr and Google by using 1,000 concepts in ILSVRC-2012 [Deng et al., 2009] as queries and the overall noise rate is rough 20%. |
| Dataset Splits | Yes | The CIFAR-10/100 datasets contain 50K (10K) images for training (test). We retain 5K of the training set for validation following [Tanaka et al., 2018]. |
| Hardware Specification | No | The paper does not provide specific details about the hardware used for running the experiments (e.g., GPU models, CPU types, or memory specifications). |
| Software Dependencies | No | The paper mentions general software or frameworks used within the field (e.g., 'Mix Match'), but it does not specify any software names with version numbers that are critical for reproducibility (e.g., Python 3.x, PyTorch 1.x, or specific solver versions). |
| Experiment Setup | Yes | We use the default parameters β = 0.2, γ = (γ0+γ1)/2 and κ = log(0.7) in experiments. ... We adopt the default hyperparameters of standard Mix Match and additionally analyze the influence of κ in experiments. |