· 2015
Going deeper with convolutions
- 46,948citations
- 2015year
Short summary
A novel deep convolutional neural network architecture, Inception, has set a new state-of-the-art for image classification and detection on the ILSVRC14 challenge.
AI-generated from the title and abstract; the full text is not read.
Key points
- Introduced the Inception architecture for deep convolutional neural networks.
- Achieved new state-of-the-art results in ImageNet ILSVRC14 classification and detection.
- Improved computational resource utilization by increasing network depth and width.
- Architectural decisions were informed by Hebbian principles and multi-scale processing.
AI-generated from the title and abstract; the full text is not read.
Abstract
We propose a deep convolutional neural network architecture codenamed Inception that achieves the new state of the art for classification and detection in the ImageNet Large-Scale Visual Recognition Challenge 2014 (ILSVRC14). The main hallmark of this architecture is the improved utilization of the computing resources inside the network. By a carefully crafted design, we increased the depth and width of the network while keeping the computational budget constant. To optimize quality, the architectural decisions were based on the Hebbian principle and the intuition of multi-scale processing. One particular incarnation used in our submission for ILSVRC14 is called GoogLeNet, a 22 layers deep network, the quality of which is assessed in the context of classification and detection.
The authors' abstract, as published at the source., 2015 · DOI ↗
Continue with a free account
Ask the paper: 3 free questions a day about this paper; save it, get its citation, new summaries every day for your field. Takeaways are Premium.
Continue free on the webSign in with Google or Apple; no card needed. You come back to this paper.
On your phone:
Field: Computer Vision and Pattern Recognition
Computer Vision and Pattern RecognitionComputer Science