Pseudo Rehearsal using non photo-realistic images

2020-04-28 · Bhasker Sri Harsha Suri, Kalidas Yeturu

Deep Neural networks forget previously learnt tasks when they are faced with learning new tasks. This is called catastrophic forgetting. Rehearsing the neural network with the training data of the previous task can protect the network from catastrophic forgetting. Since rehearsing requires the storage of entire previous data, Pseudo rehearsal was proposed, where samples belonging to the previous data are generated synthetically for rehearsal. In an image classification setting, while current techniques try to generate synthetic data that is photo-realistic, we demonstrated that Neural networks can be rehearsed on data that is not photo-realistic and still achieve good retention of the previous task. We also demonstrated that forgoing the constraint of having photo realism in the generated data can result in a significant reduction in the consumption of computational and memory resources for pseudo rehearsal.

📄 PDF Abstract BibTeX arXiv:2004.13414

Code (0)

등록된 구현이 없습니다.

Tasks

image-classification Image Classification

Pseudorehearsal in actor-critic agents

2017-04-17 · Marochko Vladimir, Leonard Johard, Manuel Mazzara

Catastrophic forgetting has a serious impact in reinforcement learning, as the data distribution is generally sparse and non-stationary over time. The purpose of this study is to investigate whether pseudorehearsal can i…

reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

Pseudorehearsal in actor-critic agents with neural network function approximation

2017-12-20 · Vladimir Marochko, Leonard Johard, Manuel Mazzara, Luca Longo

Catastrophic forgetting has a significant negative impact in reinforcement learning. The purpose of this study is to investigate how pseudorehearsal can change performance of an actor-critic agent with neural-network fun…

reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

Pseudorehearsal in value function approximation

2017-03-21 · Vladimir Marochko, Leonard Johard, Manuel Mazzara

Catastrophic forgetting is of special importance in reinforcement learning, as the data distribution is generally non-stationary over time. We study and compare several pseudorehearsal approaches for Q-learning with func…

Q-Learning reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

Pseudo-ISP: Learning Pseudo In-camera Signal Processing Pipeline from A Color Image Denoiser

2021-03-18 · Yue Cao, Xiaohe Wu, Shuran Qi, Xiao Liu 외

The success of deep denoisers on real-world color photographs usually relies on the modeling of sensor noise and in-camera signal processing (ISP) pipeline. Performance drop will inevitably happen when the sensor and ISP…

Denoising

Locally Weighted Regression Pseudo-Rehearsal for Online Learning of Vehicle Dynamics

2019-05-13 · Grady Williams, Brian Goldfain, James M. Rehg, Evangelos A. Theodorou

We consider the problem of online adaptation of a neural network designed to represent vehicle dynamics. The neural network model is intended to be used by an MPC control law to autonomously control the vehicle. This pro…

regression