paper-with-me

홈 › Papers

Exploring the parameter reusability of CNN

2020-08-08 · Wei Wang, Lin Cheng, Yanjie Zhu, Dong Liang

In recent times, using small data to train networks has become a hot topic in the field of deep learning. Reusing pre-trained parameters is one of the most important strategies to address the issue of semi-supervised and transfer learning. However, the fundamental reason for the success of these methods is still unclear. In this paper, we propose a solution that can not only judge whether a given network is reusable or not based on the performance of reusing convolution kernels but also judge which layers' parameters of the given network can be reused, based on the performance of reusing corresponding parameters and, ultimately, judge whether those parameters are reusable or not in a target task based on the root mean square error (RMSE) of the corresponding convolution kernels. Specifically, we define that the success of a CNN's parameter reuse depends upon two conditions: first, the network is a reusable network; and second, the RMSE between the convolution kernels from the source domain and target domain is small enough. The experimental results demonstrate that the performance of reused parameters applied to target tasks, when these conditions are met, is significantly improved.

📄 PDF Abstract BibTeX arXiv:2008.03411

Code (0)

등록된 구현이 없습니다.

Tasks

Semantic SegmentationTransfer Learning

Methods 이 논문이 사용한 방법론

Average Pooling 설명 없음
1x1 Convolution A 1 x 1 Convolution is a convolution with some special properties in that it can be used for dimensionality reduction,…
Global Average Pooling Global Average Pooling is a pooling operation designed to replace fully connected layers in classical CNNs. The idea is to generate one feature map for each corresponding…
Batch Normalization 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…
Kaiming Initialization 설명 없음
Residual Connection 설명 없음
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

An Intermediate Data-driven Methodology for Scientific Workflow Management System to Support Reusability

2020-10-23 · Debasish Chakroborti

In this thesis first we propose an intermediate data management scheme for a SWfMS. In our second attempt, we explored the possibilities and introduced an automatic recommendation technique for a SWfMS from real-world wo…

Management

Using UNet and PSPNet to explore the reusability principle of CNN parameters

2020-08-08 · Wei Wang

How to reduce the requirement on training dataset size is a hot topic in deep learning community. One straightforward way is to reuse some pre-trained parameters. Some previous work like Deep transfer learning reuse the …

Transfer Learning

On the reusability of samples in active learning

2022-06-13 · Gijs van Tulder, Marco Loog

An interesting but not extensively studied question in active learning is that of sample reusability: to what extent can samples selected for one learner be reused by another? This paper explains why sample reusability i…

Active Learning

Reusability and Transferability of Macro Actions for Reinforcement Learning

2019-08-05 · Yi-Hsiang Chang, Kuan-Yu Chang, Henry Kuo, Chun-Yi Lee

Conventional reinforcement learning (RL) typically determines an appropriate primitive action at each timestep. However, by using a proper macro action, defined as a sequence of primitive actions, an agent is able to byp…

reinforcement-learningReinforcement LearningReinforcement Learning (RL)

Evaluating Chain-of-Thought Reasoning through Reusability and Verifiability

2026-02-19 · Shashank Aggarwal, Ram Vikas Mishra, Amit Awekar arxiv

In multi-agent IR pipelines for tasks such as search and ranking, LLM-based agents exchange intermediate reasoning in terms of Chain-of-Thought (CoT) with each other. Current CoT evaluation narrowly focuses on target tas…