An evaluation of pre-trained models for feature extraction in image classification
This work provides guidance for selecting models in image classification tasks, but it is incremental as it evaluates existing methods without introducing new techniques.
The paper compared 16 pre-trained models for feature extraction on four image datasets, finding that CLIP-ViT-B and ViT-H-14 achieved the best overall performance, with CLIP-ResNet50 showing similar results but less variability.
In recent years, we have witnessed a considerable increase in performance in image classification tasks. This performance improvement is mainly due to the adoption of deep learning techniques. Generally, deep learning techniques demand a large set of annotated data, making it a challenge when applying it to small datasets. In this scenario, transfer learning strategies have become a promising alternative to overcome these issues. This work aims to compare the performance of different pre-trained neural networks for feature extraction in image classification tasks. We evaluated 16 different pre-trained models in four image datasets. Our results demonstrate that the best general performance along the datasets was achieved by CLIP-ViT-B and ViT-H-14, where the CLIP-ResNet50 model had similar performance but with less variability. Therefore, our study provides evidence supporting the choice of models for feature extraction in image classification tasks.