paper-with-me

Papers

A Note on Knowledge Distillation Loss Function for Object Classification

2021-09-14 · Defang Chen

This research note provides a quick introduction to the knowledge distillation loss function used in object classification. In particular, we discuss its connection to a previously proposed logits matching loss function. We further treat knowledge distillation as a specific form of output regularization and demonstrate its connection to label smoothing and entropy-based regularization.

📄 PDF Abstract BibTeX arXiv:2109.06458

Code (0)

등록된 구현이 없습니다.

Tasks

Knowledge DistillationModel Compression

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.…
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…

Similar Papers 제목 키워드 기반

An Empirical Study of Uniform-Architecture Knowledge Distillation in Document Ranking

2023-02-08 · Xubo Qin, Xiyuan Liu, Xiongfeng Zheng, Jie Liu 외

Although BERT-based ranking models have been commonly used in commercial search engines, they are usually time-consuming for online ranking tasks. Knowledge distillation, which aims at learning a smaller model with compa…

Document RankingKnowledge Distillation

AdaKD: Dynamic Knowledge Distillation of ASR models using Adaptive Loss Weighting

2024-05-11 · Shreyan Ganguly, Roshan Nayak, Rakshith Rao, Ujan Deb 외

Knowledge distillation, a widely used model compression technique, works on the basis of transferring knowledge from a cumbersome teacher model to a lightweight student model. The technique involves jointly optimizing th…

Knowledge DistillationModel Compression

Object detection at 200 Frames Per Second

2018-05-16 · Rakesh Mehta, Cemalettin Ozturk

In this paper, we propose an efficient and fast object detector which can process hundreds of frames per second. To achieve this goal we investigate three main aspects of the object detection framework: network architect…

Objectobject-detectionObject Detection

Do Not Blindly Imitate the Teacher: Using Perturbed Loss for Knowledge Distillation

2023-05-08 · Rongzhi Zhang, Jiaming Shen, Tianqi Liu, Jialu Liu 외

Knowledge distillation is a popular technique to transfer knowledge from large teacher models to a small student model. Typically, the student learns to imitate the teacher by minimizing the KL divergence of its output d…

Knowledge Distillation

Feature Adversarial Distillation for Point Cloud Classification

2023-06-25 · YuXing Lee, Wei Wu

Due to the point cloud's irregular and unordered geometry structure, conventional knowledge distillation technology lost a lot of information when directly used on point cloud tasks. In this paper, we propose Feature Adv…

ClassificationFADKnowledge DistillationModel Compression+2