paper-with-me

Papers

Densely Guided Knowledge Distillation using Multiple Teacher Assistants

2020-09-18 · ICCV 2021 10 · Wonchul Son, Jaemin Na, Junyong Choi, Wonjun Hwang

With the success of deep neural networks, knowledge distillation which guides the learning of a small student network from a large teacher network is being actively studied for model compression and transfer learning. However, few studies have been performed to resolve the poor learning issue of the student network when the student and teacher model sizes significantly differ. In this paper, we propose a densely guided knowledge distillation using multiple teacher assistants that gradually decreases the model size to efficiently bridge the large gap between the teacher and student networks. To stimulate more efficient learning of the student network, we guide each teacher assistant to every other smaller teacher assistants iteratively. Specifically, when teaching a smaller teacher assistant at the next step, the existing larger teacher assistants from the previous step are used as well as the teacher network. Moreover, we design stochastic teaching where, for each mini-batch, a teacher or teacher assistants are randomly dropped. This acts as a regularizer to improve the efficiency of teaching of the student network. Thus, the student can always learn salient distilled knowledge from the multiple sources. We verified the effectiveness of the proposed method for a classification task using CIFAR-10, CIFAR-100, and ImageNet. We also achieved significant performance improvements with various backbone architectures such as ResNet, WideResNet, and VGG.

📄 PDF Abstract BibTeX arXiv:2009.08825

Code (1)

wonchulSon/DGKD 공식 구현 pytorch

Tasks

Knowledge DistillationModel CompressionTransfer Learning

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.…
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
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 $x$…
1x1 Convolution A 1 x 1 Convolution is a convolution with some special properties in that it can be used for dimensionality reduction,…
Batch Normalization 설명 없음
Residual Connection 설명 없음
ReLU How Do I Communicate to Expedia? How Do I Communicate to Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Live Support & Special Travel…
Max Pooling Max Pooling is a pooling operation that calculates the maximum value for patches of a feature map, and uses it to create a downsampled (pooled) feature map. It is usually…

Similar Papers 제목 키워드 기반

Powerful Teachers Matter: Text-Guided Multi-view Knowledge Distillation with Visual Prior Enhancement

2026-03-25 · Xin Zhang, Jianyang Xu, Hao Peng, Dongjing Wang 외 arxiv

Knowledge distillation transfers knowledge from large teacher models to smaller students for efficient inference. While existing methods primarily focus on distillation strategies, they often overlook the importance of e…

Knowledge Distillation

Teacher-Guided Student Self-Knowledge Distillation Using Diffusion Model

2026-02-02 · Yu Wang, Chuanguang Yang, Zhulin An, Weilun Feng 외 arxiv

Existing Knowledge Distillation (KD) methods often align feature information between teacher and student by exploring meaningful feature processing and loss functions. However, due to the difference in feature distributi…

Knowledge Distillation

CES-KD: Curriculum-based Expert Selection for Guided Knowledge Distillation

2022-09-15 · Ibtihel Amara, Maryam Ziaeefard, Brett H. Meyer, Warren Gross 외

Knowledge distillation (KD) is an effective tool for compressing deep classification models for edge devices. However, the performance of KD is affected by the large capacity gap between the teacher and student networks.…

Knowledge Distillation

Curriculum Learning-Guided Progressive Distillation in Large Language Models

2026-05-11 · Jincheng Cao, Fanzhi Zeng, Leqi Liu, Aryan Mokhtari arxiv

Knowledge distillation is a key technique for transferring the capabilities of large language models (LLMs) into smaller, more efficient student models. Existing distillation approaches often overlook two critical factor…

Knowledge Distillation

Intra-class Feature Variation Distillation for Semantic Segmentation

2020-08-01 · ECCV 2020 8 · Yukang Wang, Wei Zhou, Tao Jiang, Xiang Bai 외

Current state-of-the-art semantic segmentation methods usually require high computational resources for accurate segmentation. One promising way to achieve a good trade-off between segmentation accuracy and efficiency is…

Knowledge DistillationSegmentationSemantic Segmentation