Towards Accurate Binary Convolutional Neural Network

Authors: Xiaofan Lin, Cong Zhao, Wei Pan

NeurIPS 2017 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental The proposed ABC-Net was evaluated on the ILSVRC12 Image Net classification dataset [Deng et al., 2009], and visual perception of forest trails datasets for mobile robots [Giusti et al., 2016] in Section S6 of supplementary material. and 4 Experiment results
Researcher Affiliation Industry Xiaofan Lin Cong Zhao Wei Pan* DJI Innovations Inc, Shenzhen, China {xiaofan.lin, cong.zhao, wei.pan}@dji.com
Pseudocode No The paper states, 'The training procedure, i.e., ABC-Net, is summarized in Section S1 of the supplementary material.', but no pseudocode or algorithm blocks are present in the main document.
Open Source Code No The paper does not contain any explicit statement about making the source code for their methodology publicly available, nor does it provide a link to a code repository.
Open Datasets Yes The proposed ABC-Net was evaluated on the ILSVRC12 Image Net classification dataset [Deng et al., 2009], and visual perception of forest trails datasets for mobile robots [Giusti et al., 2016] in Section S6 of supplementary material.
Dataset Splits Yes The Image Net dataset contains about 1.2 million high-resolution natural images for training that spans 1000 categories of objects. The validation set contains 50k images.
Hardware Specification No The paper mentions GPUs in general terms and FPGA slices in an example, but does not provide specific hardware details (e.g., exact GPU/CPU models, memory amounts, or cloud instance types) used for running its experiments.
Software Dependencies No The paper does not provide specific software dependencies (e.g., library or framework names with version numbers) needed to replicate the experiments.
Experiment Setup No The paper states that 'The images are resized to 224x224 before fed into the network.' However, it defers detailed 'parameter settings for these experiments' and 'The training procedure' to supplementary material (Section S4 and S1 respectively), and does not provide specific hyperparameter values or optimizer settings in the main text.