Learning De-biased Representations with Biased Representations
Authors: Hyojin Bahng, Sanghyuk Chun, Sangdoo Yun, Jaegul Choo, Seong Joon Oh
ICML 2020 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | In this section, we present experimental results of Re Bias. We first introduce the setup, including the biases tackled in the experiments, difficulties inherent to the cross-bias evaluation, and the implementation details ( 4.1). Results on Biased MNIST ( 4.2), Image Net ( 4.3) and action recognition ( 4.4) are shown afterwards. |
| Researcher Affiliation | Collaboration | Hyojin Bahng 1 Sanghyuk Chun 2 Sangdoo Yun 2 Jaegul Choo 3 Seong Joon Oh 2 1Korea University 2Clova AI Research, NAVER Corp. 3Graduate School of AI, KAIST. |
| Pseudocode | No | The paper describes methods through narrative text and mathematical formulas but does not include any explicit pseudocode or algorithm blocks. |
| Open Source Code | Yes | Source code is available at https: //github.com/clovaai/rebias. |
| Open Datasets | Yes | We construct a new dataset called Biased MNIST designed to measure the extent to which models generalise to bias shift. We modify MNIST (Le Cun et al., 1998)... In Image Net experiments... Image Net (Russakovsky et al., 2015)... We use the Kinetics dataset (Carreira & Zisserman, 2017)... |
| Dataset Splits | Yes | Most machine learning algorithms are trained and evaluated by randomly splitting a single source of data into training and test sets. ... For Image Net classification, on the other hand, we use clustering-based proxy ground truths for texture bias to measure the crossbias generalisability. For action recognition, we utilize the unbiased data that are publicly available (Mimetics), albeit in small quantity. We use the Mimetics dataset (Weinzaepfel & Rogez, 2019) for the unbiased test set accuracies, while using the biased Kinetics (Carreira & Zisserman, 2017) dataset for training. |
| Hardware Specification | No | The paper mentions 'Naver Smart Machine Learning (NSML) platform (Kim et al., 2018) has been used in the experiments.' but does not specify any hardware details such as GPU/CPU models, memory, or specific cloud instance types. |
| Software Dependencies | No | The paper does not provide specific software dependencies with version numbers (e.g., Python, PyTorch/TensorFlow versions, CUDA versions, or library versions). |
| Experiment Setup | Yes | We conduct experiments using the same batch size, learning rate, and epochs for fair comparison. We choose λ = λg = 1. For the Biased MNIST experiments, we set the kernel radius to one, while the median of distances is chosen for Image Net and action recognition experiments. More implementation details are provided in Appendix. |