Steerable CNNs

Authors: Taco S. Cohen, Max Welling

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

Reproducibility Variable Result LLM Response
Research Type Experimental We implemented steerable CNNs in Chainer (Tokui et al., 2015) and performed experiments on the CIFAR10 dataset (Krizhevsky, 2009) to determine if steerability is a useful inductive bias, and to determine the relative merits of the various types of capsules.
Researcher Affiliation Academia Taco S. Cohen University of Amsterdam t.s.cohen@uva.nl Max Welling University of Amsterdam Canadian Institute for Advanced Research m.welling@uva.nl
Pseudocode No No structured pseudocode or algorithm blocks were found in the paper.
Open Source Code No The paper states 'We implemented steerable CNNs in Chainer (Tokui et al., 2015)' but does not provide a link or explicit statement about the availability of their own source code.
Open Datasets Yes We implemented steerable CNNs in Chainer (Tokui et al., 2015) and performed experiments on the CIFAR10 dataset (Krizhevsky, 2009)
Dataset Splits No The paper states 'we tuned the width (number of channels, K) using a validation set' but does not specify the size or percentage of the validation split (e.g., '80/10/10 split', 'X samples for validation').
Hardware Specification No The paper does not specify the exact hardware (e.g., GPU/CPU models, memory, or specific computing infrastructure) used for running the experiments.
Software Dependencies No The paper mentions 'Chainer (Tokui et al., 2015)' but does not provide specific version numbers for Chainer or any other software dependencies.
Experiment Setup No The paper mentions aspects of the network architecture (e.g., '20 layer architecture', 'various widths') and states 'The rest of the training procedure is identical to Cohen & Welling (2016)', but does not provide specific hyperparameter values (e.g., learning rate, batch size, epochs) within its own text.