Very Deep Convolutional Networks for Large-Scale Image Recognition
Karen Simonyan, Andrew Zisserman
TLDR
This paper demonstrates that increasing the depth of convolutional neural networks with small 3x3 filters significantly improves large-scale image recognition accuracy.
Key contributions
- Systematic evaluation of very deep ConvNets (16-19 layers) showing improved performance over prior architectures.
- Achieved top results in ImageNet Challenge 2014 for both classification and localization tasks.
- Released best-performing models publicly, enabling further research and transfer learning on other datasets.
Why it matters
By rigorously analyzing the impact of network depth and introducing very deep architectures with small convolutional filters, this work set new performance standards in image recognition. It not only advanced the state-of-the-art on a major benchmark but also provided models that generalize well across tasks, influencing subsequent research and practical applications in computer vision.
Original Abstract
In this work we investigate the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting. Our main contribution is a thorough evaluation of networks of increasing depth using an architecture with very small (3x3) convolution filters, which shows that a significant improvement on the prior-art configurations can be achieved by pushing the depth to 16-19 weight layers. These findings were the basis of our ImageNet Challenge 2014 submission, where our team secured the first and the second places in the localisation and classification tracks respectively. We also show that our representations generalise well to other datasets, where they achieve state-of-the-art results. We have made our two best-performing ConvNet models publicly available to facilitate further research on the use of deep visual representations in computer vision.
📬 Weekly AI Paper Digest
Get the top 10 AI/ML arXiv papers from the week — summarized, scored, and delivered to your inbox every Monday.