paper-with-me

Papers

Representation Consolidation from Multiple Expert Teachers

2021-09-29 · Zhizhong Li, Avinash Ravichandran, Charless Fowlkes, Marzia Polito, Rahul Bhotika, Stefano Soatto

A library of diverse expert models transfers better to a novel task than a single generalist model. However, growing such a library indefinitely is impractical. Hence, we explore the problem of learning a consolidated image feature representation from a collection of related task-specific teachers that transfer well on novel recognition tasks. This differs from traditional knowledge distillation in which a student model is trained to emulate the input/output functionality of a teacher. Indeed, we observe experimentally that standard distillation of task-specific teachers, or using these teacher representations directly, reduces downstream transferability compared to a task-agnostic generalist model. We show that a simple multi-head, multi-task distillation method using an unlabeled proxy dataset and adding a generalist teacher is sufficient to consolidate representations from task-specific teacher(s). We improve downstream performance, outperforming the teacher (or best of all teachers) as well as the strong baseline of ImageNet pre-trained features. Our method almost reaches the performance of a multi-task joint training oracle, reaping the benefit of the teachers without replaying their training data.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Knowledge Distillation

Methods 이 논문이 사용한 방법론

Knowledge Distillation A very simple way to improve the performance of almost any machine learning algorithm is to train many different models on the same data and then to average their predictions.…

Similar Papers 제목 키워드 기반

Representation Consolidation for Training Expert Students

2021-07-16 · Zhizhong Li, Avinash Ravichandran, Charless Fowlkes, Marzia Polito 외

Traditionally, distillation has been used to train a student model to emulate the input/output functionality of a teacher. A more useful goal than emulation, yet under-explored, is for the student to learn feature repres…

MTSS: Learn from Multiple Domain Teachers and Become a Multi-domain Dialogue Expert

2020-05-21 · Shuke Peng, Feng Ji, Zehao Lin, Shaobo Cui 외

How to build a high-quality multi-domain dialogue system is a challenging work due to its complicated and entangled dialogue state space among each domain, which seriously limits the quality of dialogue policy, and furth…

Batch Model Consolidation: A Multi-Task Model Consolidation Framework

2023-05-25 · CVPR 2023 1 · Iordanis Fostiropoulos, Jiaye Zhu, Laurent Itti

In Continual Learning (CL), a model is required to learn a stream of tasks sequentially without significant performance degradation on previously learned tasks. Current approaches fail for a long sequence of tasks from d…

Continual Learningimage-classificationImage Classificationmodel

Amalgamating Filtered Knowledge: Learning Task-customized Student from Multi-task Teachers

2019-05-28 · Jingwen Ye, Xinchao Wang, Yixin Ji, Kairi Ou 외

Many well-trained Convolutional Neural Network(CNN) models have now been released online by developers for the sake of effortless reproducing. In this paper, we treat such pre-trained networks as teachers and explore how…

The Expertise Problem: Learning from Specialized Feedback

2022-11-12 · Oliver Daniels-Koch, Rachel Freedman

Reinforcement learning from human feedback (RLHF) is a powerful technique for training agents to perform difficult-to-specify tasks. However, human feedback can be noisy, particularly when human teachers lack relevant kn…