.png){kind=icon}
返回
Auto CNN classifier based on knowledge transferred from self-supervised model
.png){kind=icon}
PRE
AI
DOI：10.1007/s10489-023-04598-1.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Training with unlabeled datasets using self-supervised models has the edge over training with labeled datasets, reducing human effort, and no need for annotated data during training. The knowledge obtained from the pre-trained self-supervised model can be transferred to an image classifier as a target task. Transferring knowledge from source to target task requires tuning a large number of hyperparameters, such as number of CNN layers, number of filters in each CNN layer, kernel size, stride, number of fully connected (FC) layers, units in each FC layer, dropouts, learning rate, and many more. An efficient process is required to automatically tune these hyperparameters to reduce the manual efforts and enhance the performance of the self-supervised model. This paper uses a pre-trained self-supervised model to transfer knowledge for image classification. We propose an efficient Bayesian optimization-based method for automatically tuning (autotuning) the hyperparameters of the self-supervised model during the knowledge transfer. The proposed autotuned image classifier consists of a few CNN layers followed by an FC layer. Finally, we use a softmax layer to obtain the probability of classes for the images. To evaluate the performance of the proposed method, state-of-the-art self-supervised models such as SimClr, SWAV, and SWAV 2x are used to extract the learned features. According to our experiments on three benchmarked datasets (CIFAR-10, CIFAR-100, and Tiny Imagenet datasets), the proposed method not only enhances the performances of the self-supervised models, but also provides state-of-the-art results.
Keyword:
Neural architecture search
Autotuning
Self-supervised learning
Hyperparameter optimization
BO-TPE
期刊
IF:
3.5
论文数:
7.6K
被引数:
1.7W
机构
暂无机构信息
引用论文
Desempenho de crianças do ensino fundamental na solução de problemas aritméticos<A NAME="top"></A>问题的基本解决方案 
OAAI
OAAI分享收藏Enhancing multi-objective evolutionary neural architecture search with training-free Pareto local search.png)
APPLIED INTELLIGENCE
APPLIED INTELLIGENCEIF3.5
PREAI
分享收藏Approaching coupled cluster accuracy with a general-purpose neural network potential through transfer learning通过迁移学习接近具有通用神经网络潜力的耦合聚类精度NATURE COMMUNICATIONS
OAAI
NATURE COMMUNICATIONSIF15.7
OAAI分享收藏分享收藏Analysis and assessment of ship collision accidents using Fault Tree and Multiple Correspondence Analysis基于故障树和多重对应分析的船舶碰撞事故分析与评估
PREAI
分享收藏Taking the Human Out of the Loop: A Review of Bayesian Optimization将人类带出循环: 贝叶斯优化的回顾PROCEEDINGS OF THE IEEE
PROCEEDINGS OF THE IEEEIF25.9
PREAI
分享收藏A novel deep learning based framework for the detection and classification of breast cancer using transfer learning一种基于深度学习的新框架，用于使用迁移学习检测和分类乳腺癌
PREAI
分享收藏分享收藏
查看更多内容