Adversarial Fisher Vectors for Unsupervised Representation Learning

Authors: Shuangfei Zhai, Walter Talbott, Carlos Guestrin, Joshua Susskind

NeurIPS 2019 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental We conduct experiments showing that the GAN-induced Fisher Vectors demonstrate competitive performance as unsupervised feature extractors for classification and perceptual similarity tasks. Code is available at https://github.com/apple/ml-afv.
Researcher Affiliation Industry Shuangfei Zhai Walter Talbott Carlos Guestrin Joshua M. Susskind Apple Inc. {szhai, wtalbott, guestrin, jsusskind}@apple.com
Pseudocode No The paper does not contain any structured pseudocode or algorithm blocks.
Open Source Code Yes Code is available at https://github.com/apple/ml-afv.
Open Datasets Yes We conduct our experiments on images of size 32 × 32, using CIFAR10 and CIFAR100 [33], Celeb A [34] and Image Net [35].
Dataset Splits No The paper refers to 'validation examples' and 'validation Fisher Similarity' but does not provide specific percentages or counts for training, validation, or test dataset splits.
Hardware Specification No The paper does not provide specific hardware details such as GPU models, CPU types, or memory used for running the experiments.
Software Dependencies No The paper mentions optimizers and normalization techniques, but it does not provide specific version numbers for any software dependencies, libraries, or frameworks used in the experiments.
Experiment Setup Yes Unless otherwise mentioned, the channel size for convolutional layers is 128. All experiments use batch size 64, ADAM optimizer [37] with β1 = 0, β2 = .999, learning rate for G = 2 × 10−4, and learning rate for D = 4 × 10−4. By default we train our model with a fixed number of iterations (800K) and obtain the last checkpoint for evaluation, unless otherwise mentioned.