Examining CNN Representations With Respect to Dataset Bias

Authors: Quanshi Zhang, Wenguan Wang, Song-Chun Zhu

AAAI 2018 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Experiments have demonstrated the effectiveness of our method. We tested the proposed method on the Largescale Celeb Faces Attributes (Celeb A) dataset (Liu et al. 2015) and the SUN Attribute database (Patterson et al. 2014). We trained two CNNs using images from the Celeb A dataset and those from the SUN dataset, respectively. Table 1: Average accuracy decrease caused by top-N failure modes...
Researcher Affiliation Academia University of California, Los Angeles Beijing Institute of Technology
Pseudocode No No, the paper contains a section titled 'Algorithm' but it describes the method in paragraph form rather than providing a structured pseudocode block or algorithm steps.
Open Source Code No No, the paper does not provide any statement or link regarding the availability of its source code.
Open Datasets Yes Dataset: We tested the proposed method on the Largescale Celeb Faces Attributes (Celeb A) dataset (Liu et al. 2015) and the SUN Attribute database (Patterson et al. 2014).
Dataset Splits No No, the paper mentions training and testing but does not explicitly provide details about training/validation/test dataset splits, such as percentages, absolute counts, or specific predefined split methodologies.
Hardware Specification No No, the paper does not provide specific hardware details such as GPU or CPU models, or memory specifications used for running the experiments.
Software Dependencies No No, the paper mentions using 'Alex Net' but does not specify any software dependencies with version numbers (e.g., Python, PyTorch, TensorFlow versions).
Experiment Setup No No, the paper does not explicitly provide details about the experimental setup such as hyperparameter values (e.g., learning rate, batch size) or specific optimizer settings.