Learning Shared Knowledge for Deep Lifelong Learning using Deconvolutional Networks

Authors: Seungwon Lee, James Stokes, Eric Eaton

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

Reproducibility Variable Result LLM Response
Research Type Experimental Experiments on two computer vision data sets show that the DF-CNN achieves superior performance in challenging lifelong learning settings, resists catastrophic forgetting, and exhibits reverse transfer to improve previously learned tasks from subsequent experience without retraining.
Researcher Affiliation Collaboration 1University of Pennsylvania, Philadelphia, PA, USA 2Flatiron Institute, New York, NY, USA leeswon@seas.upenn.edu, jstokes@flatironinstitute.org, eeaton@cis.upenn.edu
Pseudocode Yes Algorithm 1 DF-CNN (λ, kb Size, transform Size)
Open Source Code No The paper mentions that 'The online appendix is available on the third author s website at http://www.seas.upenn.edu/ eeaton/papers/Lee2019Learning.pdf', which is a PDF document, not source code for the methodology.
Open Datasets Yes We generated two lifelong learning problems using the CIFAR-100 [Krizhevsky and Hinton, 2009] and Office-Home [Venkateswara et al., 2017] data sets.
Dataset Splits Yes For CIFAR-100, we created a series of 10 image classification tasks... and split it into training and validation sets in the ratio 5.6:1 (170 training and 30 validation instances per task). ... The Office-Home dataset... we randomly split the data into those with a 60%, 10%, and 30% ratio, respectively. This results in approximately 550 training, 90 validation, and 250 test instances.
Hardware Specification No The paper does not provide specific details on the hardware used, such as GPU models, CPU types, or memory.
Software Dependencies No The paper does not specify software dependencies with version numbers.
Experiment Setup No Details of training process, architecture of the networks and hyper-parameters used for each data set are described in Appendix B. Since these details are in an appendix, they are not presented in the main text of the paper.