Papers › Investigating Transfer Learning Capabilities of Vision Transformers and CNNs by...

Investigating Transfer Learning Capabilities of Vision Transformers and CNNs by Fine-Tuning a Single Trainable Block

11 Oct 2021arXiv:2110.05270archive 2025-07-28

Durvesh Malpure, Onkar Litake, Rajesh Ingle

In recent developments in the field of Computer Vision, a rise is seen in the use of transformer-based architectures. They are surpassing the state-of-the-art set by CNN architectures in accuracy but on the other hand, they are computationally very expensive to train from scratch. As these models are quite recent in the Computer Vision field, there is a need to study it's transfer learning capabilities and compare it with CNNs so that we can understand which architecture is better when applied to real world problems with small data. In this work, we follow a simple yet restrictive method for fine-tuning both CNN and Transformer models pretrained on ImageNet1K on CIFAR-10 and compare them with each other. We only unfreeze the last transformer/encoder or last convolutional block of a model and freeze all the layers before it while adding a simple MLP at the end for classification. This simple modification lets us use the raw learned weights of both these neural networks. From our experiments, we find out that transformers-based architectures not only achieve higher accuracy than CNNs but some transformers even achieve this feat with around 4 times lesser number of parameters.

Paper PDF Code

Code

mmahdibarghi/Transfer-Learning-Capabilities-of-Vision-Transformers-and-CNNs report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Transfer Learning

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Absolute Position Encodings Adam Attention BPE Dense Connections Dropout Label Smoothing Layer Normalization Linear Layer Multi-Head Attention Position-Wise Feed-Forward Layer Residual Connection Softmax Transformer

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections