paper-with-me

홈 › Papers

Cross-Architecture Knowledge Distillation

2022-07-12 · Yufan Liu, Jiajiong Cao, Bing Li, Weiming Hu, Jingting Ding, Liang Li

Transformer attracts much attention because of its ability to learn global relations and superior performance. In order to achieve higher performance, it is natural to distill complementary knowledge from Transformer to convolutional neural network (CNN). However, most existing knowledge distillation methods only consider homologous-architecture distillation, such as distilling knowledge from CNN to CNN. They may not be suitable when applying to cross-architecture scenarios, such as from Transformer to CNN. To deal with this problem, a novel cross-architecture knowledge distillation method is proposed. Specifically, instead of directly mimicking output/intermediate features of the teacher, partially cross attention projector and group-wise linear projector are introduced to align the student features with the teacher's in two projected feature spaces. And a multi-view robust training scheme is further presented to improve the robustness and stability of the framework. Extensive experiments show that the proposed method outperforms 14 state-of-the-arts on both small-scale and large-scale datasets.

📄 PDF Abstract BibTeX arXiv:2207.05273

Code (0)

등록된 구현이 없습니다.

Tasks

Knowledge Distillation

Methods 이 논문이 사용한 방법론

Multi-Head Attention 설명 없음
Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
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 $x$…
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…
Absolute Position Encodings Absolute Position Encodings are a type of position embeddings for [Transformer-based models] where positional encodings are…
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…
BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…

Similar Papers 제목 키워드 기반

A Functional Perspective on Knowledge Distillation in Neural Networks

2025-10-14 · Israel Mason-Williams, Gabryel Mason-Williams, Helen Yannakoudakis arxiv

Knowledge distillation is considered a compression mechanism when judged on the resulting student's accuracy and loss, yet its functional impact is poorly understood. We quantify the compression capacity of knowledge dis…

Knowledge Distillation

RNAS-CL: Robust Neural Architecture Search by Cross-Layer Knowledge Distillation

2023-01-19 · Utkarsh Nath, Yancheng Wang, Yingzhen Yang

Deep Neural Networks are vulnerable to adversarial attacks. Neural Architecture Search (NAS), one of the driving tools of deep neural networks, demonstrates superior performance in prediction accuracy in various machine …

Knowledge DistillationNeural Architecture Search

Cross-Architecture Distillation Made Simple with Redundancy Suppression

2025-07-29 · Weijia Zhang, Yuehao Liu, Wu Ran, Chao Ma arxiv

We describe a simple method for cross-architecture knowledge distillation, where the knowledge transfer is cast into a redundant information suppression formulation. Existing methods introduce sophisticated modules, arch…

Knowledge Distillation

Teacher-Student Architecture for Knowledge Distillation: A Survey

2023-08-08 · Chengming Hu, Xuan Li, Dan Liu, Haolun Wu 외

Although Deep neural networks (DNNs) have shown a strong capacity to solve large-scale problems in many areas, such DNNs are hard to be deployed in real-world systems due to their voluminous parameters. To tackle this is…

Knowledge DistillationregressionSurvey

Cross Knowledge Distillation between Artificial and Spiking Neural Networks

2025-07-12 · Shuhan Ye, Yuanbin Qian, Chong Wang, Sunqi Lin 외 arxiv

Recently, Spiking Neural Networks (SNNs) have demonstrated rich potential in computer vision domain due to their high biological plausibility, event-driven characteristic and energy-saving efficiency. Still, limited anno…

Knowledge DistillationSemantic Similarity