Skip to content
  • Our Work
    • Fields
      • Cardiology
      • ENT
      • Gastro
      • Orthopedics
      • Ophthalmology
      • Pulmonology
      • Surgical Intelligence
      • Surgical Robotics
      • Urology
      • Other
    • Modalities
      • Endoscopy
      • Medical Segmentation
      • Microscopy
      • Ultrasound
  • Success Stories
  • Insights
    • Magazine
    • Upcoming Events
    • Webinars
    • Meetups
    • News
    • Blog
  • The company
    • About us
    • Careers
Menu
  • Our Work
    • Fields
      • Cardiology
      • ENT
      • Gastro
      • Orthopedics
      • Ophthalmology
      • Pulmonology
      • Surgical Intelligence
      • Surgical Robotics
      • Urology
      • Other
    • Modalities
      • Endoscopy
      • Medical Segmentation
      • Microscopy
      • Ultrasound
  • Success Stories
  • Insights
    • Magazine
    • Upcoming Events
    • Webinars
    • Meetups
    • News
    • Blog
  • The company
    • About us
    • Careers
Contact

Reflections on CVPR 2015

Reflections on CVPR 2015

One of our colleagues, Dr. Micha Feigin, presents his thoughts on this year’s Computer Vision & Pattern Recognition Conference:
Coming back from CVPR 2015, the main conclusion is that everyone (including us) is doing neural networks, preferably deep learning. Sparsity seems to have lost its glory in the imaging and vision community. It feels like at least 75% of the papers either utilized or were on the subject of neural networks. Quite often even if it seemed otherwise, a neural network ended up hiding somewhere in the bushes.
The interesting question that immediately comes to mind, how long until the next big thing and what is it going to be? We have seen the hype around SVMs, Bayesian methods, random forests, just to name a few, come and go. For the moment, it seems that neural networks are the new thrill and cannot be trumped, although history has shown otherwise time and time again. As usual, only time will tell.
The big change that finally gave neural networks the lead is the amount of data used to learn the network. The jump from tens of thousands to tens of millions of samples is what brought along the performance land slide. One notable example of this is of course face.com.
This would probably not be possible without the processing power provided by modern GPUs. No computer science researcher is complete today without a small super computer with a big GPU warming up the space under the desk.
This unfortunately also marks the downside of neural networks. Other than the fact that there are no clear techniques as to how to design a new network topology, aspiring scientists have to compete with Google who dedicated about 16,000 processors to the problem of learning new networks. Learning the weights for a new topology with large data sets can take days even on such a system. The end results is that most people tweak and relearn on top of existing networks rather than designing new ones. This leads us to the main problem. Neural networks can be fragile to changes and worse than that, it’s difficult to analyze what was learned and how decisions are made, they can essentially be a black box.
Finally, we’ll end with a bit of interesting history. Neural networks are actually the predecessor to probably all other machine learning techniques, dating back to the 1940s to the work of McCulloch and Pitts. This is work that actually led to von Neumann’s proposal for a programmable computer. A piece worth reading on the subject here.
How did you find CVPR 2015? What do you think of Micha’s view?

Share

Share on linkedin
Share on twitter
Share on facebook

More News

PR – Intra-op Virtual Measurements in Laparoscopic and Robotic-Assisted Surgeries

PR – Non-Invasive Planning of Coronary Intervention

PR – Bladder Panorama Generator and Sparse Reconstruction Tool

Intraoperative Registration Module for Orthopedic Surgery

PR – Registration Module for Orthopedic Surgery

Automated Assessment of Cartilage Damage

PR – Automated Assessment of Cartilage Damage

Real-Time Surgical Workflow Recognition

PR – Real-Time Surgical Workflow Recognition

PR – Intra-op Virtual Measurements in Laparoscopic and Robotic-Assisted Surgeries

PR – Non-Invasive Planning of Coronary Intervention

PR – Bladder Panorama Generator and Sparse Reconstruction Tool

Intraoperative Registration Module for Orthopedic Surgery

PR – Registration Module for Orthopedic Surgery

Automated Assessment of Cartilage Damage

PR – Automated Assessment of Cartilage Damage

Real-Time Surgical Workflow Recognition

PR – Real-Time Surgical Workflow Recognition

Show all

RSIP Vision

Field-tested software solutions and custom R&D, to power your next medical products with innovative AI and image analysis capabilities.

Read more about us

Get in touch

Please fill the following form and our experts will be happy to reply to you soon

Recent News

PR – Intra-op Virtual Measurements in Laparoscopic and Robotic-Assisted Surgeries

PR – Non-Invasive Planning of Coronary Intervention

PR – Bladder Panorama Generator and Sparse Reconstruction Tool

PR – Registration Module for Orthopedic Surgery

All news
Upcoming Events
Stay informed for our next events
Subscribe to Our Magazines

Subscribe now and receive the Computer Vision News Magazine every month to your mailbox

 
Subscribe for free
Follow us
Linkedin Twitter Facebook Youtube

contact@rsipvision.com

Terms of Use

Privacy Policy

© All rights reserved to RSIP Vision 2021

Created by Shmulik

  • Our Work
    • title-1
      • Ophthalmology
      • Uncategorized
      • Ophthalmology
      • Pulmonology
      • Cardiology
      • Orthopedics
    • Title-2
      • Orthopedics
  • Success Stories
  • Insights
  • The company