Efficient Transfer

Efficient transfer learning aims to leverage knowledge gained from solving one task to improve performance on a related but different task, minimizing the need for extensive retraining. Current research focuses on improving sample efficiency and few-shot learning capabilities, employing techniques like pre-trained models (e.g., EfficientNet), reward machine abstractions in reinforcement learning, and diverse ensemble methods. These advancements are crucial for addressing data scarcity in various domains, such as bioacoustic classification and material defect detection, leading to more efficient and robust machine learning applications.

Papers

March 6, 2024

On Transfer in Classification: How Well do Subsets of Classes Generalize?
Raphael Baena, Lucas Drumetz, Vincent Gripon
Classification Code Shot Learning Formality Transfer Task Transferability Model Generalization High Quality Subset Efficient Transfer

July 12, 2023

Global birdsong embeddings enable superior transfer learning for bioacoustic classification
Burooj Ghani, Tom Denton, Stefan Kahl, Holger Klinck
World Event Bird Sound Efficient Transfer

July 11, 2023

Contextual Pre-planning on Reward Machine Abstractions for Enhanced Transfer in Deep Reinforcement Learning
Guy Azran, Mohamad H. Danesh, Stefano V. Albrecht, Sarah Keren
Deep Reinforcement Learning Context Aware Unseen Task Symbolic Representation Reward Machine Efficient Transfer

May 20, 2023

Model-based adaptation for sample efficient transfer in reinforcement learning control of parameter-varying systems
Ibrahim Ahmed, Marcos Quinones-Grueiro, Gautam Biswas
Reinforcement Learning Model Predictive Control Model Based External Sample Model Transformation Efficient Transfer Model Based Adaptation

April 10, 2023

An Efficient Transfer Learning-based Approach for Apple Leaf Disease Classification
Md. Hamjajul Ashmafee, Tasnim Ahmed, Sabbir Ahmed, Md. Bakhtiar Hasan, Mst Nura Jahan, A. B. M. Ashikur Rahman
Transfer Learning Deep Learning Based Learning Based Approach Plant Disease Efficient Transfer Apple Leaf Disease

April 3, 2023

Adaptive Defective Area Identification in Material Surface Using Active Transfer Learning-based Level Set Estimation
Shota Hozumi, Kentaro Kutsukake, Kota Matsui, Syunya Kusakawa, Toru Ujihara, Ichiro Takeuchi
Defect Detection Object Surface Level Set Estimation Efficient Transfer

September 26, 2022

DEFT: Diverse Ensembles for Fast Transfer in Reinforcement Learning
Simeon Adebola, Satvik Sharma, Kaushik Shivakumar
Reinforcement Learning Policy Gradient Ensemble Learning Diverse Ensemble Deep Ensemble Actor Critic Transfer Reinforcement Learning Efficient Transfer

Efficient Transfer

Papers

On Transfer in Classification: How Well do Subsets of Classes Generalize?

Global birdsong embeddings enable superior transfer learning for bioacoustic classification

Contextual Pre-planning on Reward Machine Abstractions for Enhanced Transfer in Deep Reinforcement Learning

Model-based adaptation for sample efficient transfer in reinforcement learning control of parameter-varying systems

An Efficient Transfer Learning-based Approach for Apple Leaf Disease Classification

Adaptive Defective Area Identification in Material Surface Using Active Transfer Learning-based Level Set Estimation

DEFT: Diverse Ensembles for Fast Transfer in Reinforcement Learning