Open AccessPosted Content
Learning without Forgetting
Zhizhong Li,Derek Hoiem +1 more
TL;DR: This work proposes the Learning without Forgetting method, which uses only new task data to train the network while preserving the original capabilities, and performs favorably compared to commonly used feature extraction and fine-tuning adaption techniques.
read more
Abstract: When building a unified vision system or gradually adding new capabilities to a system, the usual assumption is that training data for all tasks is always available. However, as the number of tasks grows, storing and retraining on such data becomes infeasible. A new problem arises where we add new capabilities to a Convolutional Neural Network (CNN), but the training data for its existing capabilities are unavailable. We propose our Learning without Forgetting method, which uses only new task data to train the network while preserving the original capabilities. Our method performs favorably compared to commonly used feature extraction and fine-tuning adaption techniques and performs similarly to multitask learning that uses original task data we assume unavailable. A more surprising observation is that Learning without Forgetting may be able to replace fine-tuning with similar old and new task datasets for improved new task performance.
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
Continual lifelong learning with neural networks: A review.
TL;DR: This review critically summarize the main challenges linked to lifelong learning for artificial learning systems and compare existing neural network approaches that alleviate, to different extents, catastrophic forgetting.
3.2K
Knowledge Distillation: A Survey
TL;DR: A comprehensive survey of knowledge distillation from the perspectives of knowledge categories, training schemes, teacher-student architecture, distillation algorithms, performance comparison and applications can be found in this paper.
2.4K
A continual learning survey: Defying forgetting in classification tasks.
Matthias Delange,Rahaf Aljundi,Marc Masana,Sarah Parisot,Xu Jia,Ales Leonardis,Greg Slabaugh,Tinne Tuytelaars +7 more
TL;DR: This work focuses on task incremental classification, where tasks arrive sequentially and are delineated by clear boundaries and study the influence of model capacity, weight decay and dropout regularization, and the order in which the tasks are presented, and qualitatively compare methods in terms of required memory, computation time and storage.
1.9K
•Proceedings Article
Continual Learning with Deep Generative Replay
Hanul Shin,Jung Kwon Lee,Jaehong Kim,Jiwon Kim +3 more
- 01 Jan 2017
TL;DR: The Deep Generative Replay is proposed, a novel framework with a cooperative dual model architecture consisting of a deep generative model ("generator") and a task solving model ("solver"), with only these two models, training data for previous tasks can easily be sampled and interleaved with those for a new task.
•Posted Content
Dota 2 with Large Scale Deep Reinforcement Learning
Christopher Berner,Greg Brockman,Brooke Chan,Vicki Cheung,Przemyslaw Debiak,Christy Dennison,David Farhi,Quirin Fischer,Shariq Hashme,Christopher Hesse,Rafal Jozefowicz,Scott Gray,Catherine Olsson,Jakub Pachocki,Michael Petrov,Henrique Ponde de Oliveira Pinto,Jonathan Raiman,Tim Salimans,Jeremy Schlatter,Jonas Schneider,Szymon Sidor,Ilya Sutskever,Jie Tang,Filip Wolski,Susan Zhang +24 more
TL;DR: By defeating the Dota 2 world champion (Team OG), OpenAI Five demonstrates that self-play reinforcement learning can achieve superhuman performance on a difficult task.
1.7K
References
•Posted Content
Neural Random Forest Imitation.
TL;DR: A new method for generating data from a random forest and learning a neural network that imitates it without any additional training data creates very efficient neural networks that learn the decision boundaries of a Random Forest Imitation.
•Posted Content
Adversarial Incremental Learning
TL;DR: In this article, the authors propose an adversarial discriminator based method that does not make use of old data at all while training on new tasks and achieves state-of-the-art performance on CIFAR-100, SVHN, and MNIST datasets.
2
•Posted Content
Continual Learning for Natural Language Generation in Task-oriented Dialog Systems
TL;DR: This paper proposed an adaptive regularization technique based on ElasticWeight Consolidation to avoid catastrophic forgetting in a continuous learning setting. But this method is not suitable for task-oriented dialog systems.
2
•Posted Content
iLGaCo: Incremental Learning of Gait Covariate Factors
TL;DR: iLGaCo is proposed, the first incremental learning approach of covariate factors for gait recognition, where the deep model can be updated with new information without re-training it from scratch by using the whole dataset.
2
Model Transfer with Explicit Knowledge of the Relation between Class Definitions.
Hiyori Yoshikawa,Tomoya Iwakura +1 more
- 01 Oct 2018
TL;DR: The proposed method converts the class label of each example on the support scheme into a set of candidate class labels on the target scheme via the class correspondence table, and then uses the candidate labels to learn the classification layer for the target schemes.