paper-with-me

홈 › Papers

Distilling Knowledge From a Deep Pose Regressor Network

2019-08-02 · ICCV 2019 10 · Muhamad Risqi U. Saputra, Pedro P. B. de Gusmao, Yasin Almalioglu, Andrew Markham, Niki Trigoni

This paper presents a novel method to distill knowledge from a deep pose regressor network for efficient Visual Odometry (VO). Standard distillation relies on "dark knowledge" for successful knowledge transfer. As this knowledge is not available in pose regression and the teacher prediction is not always accurate, we propose to emphasize the knowledge transfer only when we trust the teacher. We achieve this by using teacher loss as a confidence score which places variable relative importance on the teacher prediction. We inject this confidence score to the main training task via Attentive Imitation Loss (AIL) and when learning the intermediate representation of the teacher through Attentive Hint Training (AHT) approach. To the best of our knowledge, this is the first work which successfully distill the knowledge from a deep pose regression network. Our evaluation on the KITTI and Malaga dataset shows that we can keep the student prediction close to the teacher with up to 92.95% parameter reduction and 2.12x faster in computation time.

📄 PDF Abstract BibTeX arXiv:1908.00858

Code (0)

등록된 구현이 없습니다.

Tasks

PredictionregressionTransfer LearningVisual Odometry

Similar Papers 제목 키워드 기반

Distilling Word Embeddings: An Encoding Approach

2015-06-15 · Lili Mou, Ran Jia, Yan Xu, Ge Li 외

Distilling knowledge from a well-trained cumbersome network to a small one has recently become a new research topic, as lightweight neural networks with high performance are particularly in need in various resource-restr…

Word Embeddings

Distilling HuBERT with LSTMs via Decoupled Knowledge Distillation

2023-09-18 · Danilo de Oliveira, Timo Gerkmann

Much research effort is being applied to the task of compressing the knowledge of self-supervised models, which are powerful, yet large and memory consuming. In this work, we show that the original method of knowledge di…

Automatic Speech RecognitionKnowledge Distillationspeech-recognitionSpeech Recognition

Masked Autoencoders Enable Efficient Knowledge Distillers

2022-08-25 · CVPR 2023 1 · Yutong Bai, Zeyu Wang, Junfei Xiao, Chen Wei 외

This paper studies the potential of distilling knowledge from pre-trained models, especially Masked Autoencoders. Our approach is simple: in addition to optimizing the pixel reconstruction loss on masked inputs, we minim…

Knowledge Distillation

I-DREM MRAC with Time-Varying Adaptation Rate & No A Priori Knowledge of Control Input Matrix Sign to Relax PE Condition

2021-02-22 · Anton Glushchenko, Vladislav Petrov, Konstantin Lastochkin

The known dynamic regressor extension and mixing method (DREM) is combined with the proposed filter of a new type, which uses the integration operation with forgetting, and the recursive least-squares method to develop t…

Adversarial Bi-Regressor Network for Domain Adaptive Regression

2022-09-20 · Haifeng Xia, Pu Perry Wang, Toshiaki Koike-Akino, Ye Wang 외

Domain adaptation (DA) aims to transfer the knowledge of a well-labeled source domain to facilitate unlabeled target learning. When turning to specific tasks such as indoor (Wi-Fi) localization, it is essential to learn …

Domain Adaptationregression