Do Better ImageNet Models Transfer Better?
원문 초록
Transfer learning is a cornerstone of computer vision, yet little work has been done to evaluate the relationship between architecture and transfer. An implicit hypothesis in modern computer vision research is that models that perform better on ImageNet necessarily perform better on other vision tasks. However, this hypothesis has never been systematically tested. Here, we compare the performance of 16 classification networks on 12 image classification datasets. We find that, when networks are used as fixed feature extractors or fine-tuned, there is a strong correlation between ImageNet accuracy and transfer accuracy ($r = 0.99$ and $0.96$, respectively). In the former setting, we find that this relationship is very sensitive to the way in which networks are trained on ImageNet; many common forms of regularization slightly improve ImageNet accuracy but yield penultimate layer features that are much worse for transfer learning. Additionally, we find that, on two small fine-grained image classification datasets, pretraining on ImageNet provides minimal benefits, indicating the learned features from ImageNet do not transfer well to fine-grained tasks. Together, our results show that ImageNet architectures generalize well across datasets, but ImageNet features are less general than previously suggested.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Beyond the Attention: Distinguish the Discriminative and Confusable Features For Fine-grained Image Classification
Performing Image Classification for 10 Different Monkey Species using CNN
FrImCla: A Framework for Image Classification Using Traditional and Transfer Learning Techniques
Are These Birds Similar: Learning Branched Networks for Fine-grained Representations
Hierarchical Mask-Enhanced Dual Reconstruction Network for Few-Shot Fine-Grained Image Classification
DocXClassifier: High Performance Explainable Deep Network for Document Image Classification
토론
이 논문과 연결된 포럼 글이 아직 없습니다.