Deep Value Networks Learn to Evaluate and Iteratively Refine Structured Outputs

Authors: Michael Gygli, Mohammad Norouzi, Anelia Angelova

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

Reproducibility Variable Result LLM Response
Research Type Experimental We evaluate the proposed Deep Value Networks on 3 tasks: multi-label classification, binary image segmentation, and a 3-class face segmentation task. Section 5.4 investigates the sampling mechanisms for DVN training, and Section 5.5 visualizes the learned models.
Researcher Affiliation Collaboration Michael Gygli 1 * Mohammad Norouzi 2 Anelia Angelova 2 ... 1ETH Z urich & gifs.com 2Google Brain, Mountain View, USA. Correspondence to: Michael Gygli <gygli@vision.ee.ethz.ch>, Mohammad Norouzi <mnorouzi@google.com>.
Pseudocode Yes Algorithm 1 Deep Value Network training
Open Source Code Yes Our source code based on Tensor Flow (Abadi et al., 2015) is available at https://github.com/gyglim/dvn.
Open Datasets Yes We use standard benchmarks in multi-label classification, namely Bibtex and Bookmarks, introduced in (Katakis et al., 2008).
Dataset Splits Yes We tune the hyperparameters of the model on a validation set and, once best hyper-parameters are found, fine-tune on the combination of training and validation sets.
Hardware Specification No The paper does not provide any specific hardware details such as GPU models, CPU types, or memory specifications used for running the experiments.
Software Dependencies No The paper mentions 'Tensor Flow (Abadi et al., 2015)' as the basis for the source code, but does not specify a version number for TensorFlow or any other software dependencies needed to replicate the experiment.
Experiment Setup Yes We use a learning rate of 0.01 and apply dropout on the first fully connected layer with the keeping probability 0.75 as determined on the validation set.