Breaking News

Lexar Introduces JumpDrive A50V and C50V Dashcam USB Drives Lexar ARES RGB 2nd Gen DDR5 Passes AMD EXPO Ultra Low Latency Certification Tests Thypoch Introduces New Sculptor AF Lens Series with 23mm f1.4 Prime for Fujifilm X-Mount ASUS Announces Availability of ProArt GR1X Xiaomi and Leica Present the Xiaomi 18 Pro Series

logo

  • Share Us
    • Facebook
    • Twitter
  • Home
  • Home
  • News
  • Reviews
  • Essays
  • About
    • Submit News

    • Contact Us
    • Privacy

    • Promotion
    • Advertise

    • RSS Feed

Search form

Kioxia Presented Image Classification System Deploying Memory-Centric AI with High-capacity Storage at ECCV 2022

Kioxia Presented Image Classification System Deploying Memory-Centric AI with High-capacity Storage at ECCV 2022

Enterprise & IT Nov 2,2022 0

Kioxia has developed an image classification system based on Memory-Centric AI, an AI technology that utilizes high-capacity storage. The system classifies images using a neural network that refers to knowledge stored in external high-capacity storage; this avoids "catastrophic forgetting," one of the major challenges of neural networks, and allows knowledge to be added or updated without the loss of current knowledge. This technology was presented on October 25 at the oral session of European Conference on Computer Vision 2022 (ECCV 2022) in Tel Aviv, one of the top conferences in the field of computer vision*1.

In conventional AI techniques, neural networks are trained to acquire knowledge by updating parameters called “weights.” Once fully trained, in order to acquire new knowledge a neural network must be either re-trained from the beginning or fine-tuned with new data. The former requires huge amounts of time and consumes significant energy costs, while the latter requires parameters to be updated and faces the catastrophic forgetting problem of losing the knowledge acquired in the past which leads to deterioration of classification accuracy.

To address the issues of cost and accuracy in neural network-based image classification systems, the new solution stores large amounts of image data, labels and image feature maps*2 as knowledge in a high-capacity storage. The neural network then classifies images by referring to that stored knowledge. Using this method, knowledge can be added or updated by adding newly obtained image labels and feature maps to the stored data. As there is no need to re-train or update weights, which may cause “catastrophic forgetting,” image classification can be maintained more accurately.

Furthermore, by using the data referred from the storage when the neural network classifies images, the basis for the classification results can be visualized, which is expected to improve the explainability of AI*3 and alleviate the black-box problem*4, in turn allowing the selective modification of knowledge sources. In addition, by analyzing the referred data, the contribution of each stored data can be evaluated according to the frequency of references.

Guided by its mission of "Uplifting the World with ‘Memory,’" Kioxia will continue to contribute to the development of AI and storage technologies by expanding Memory-Centric AI beyond image classification to other areas and promoting research and development of AI technology utilizing high-capacity storage.

About Memory-Centric AI: https://youtu.be/lw8XKhviGJc A
Memory-Centric AI, Part I: https://brand.kioxia.com/en-jp/articles/article25.html
Memory-Centric AI, Part II:https://brand.kioxia.com/en-jp/articles/article26.html A new window will open.

About ECCV
The European Conference on Computer Vision (ECCV) is one of the top conferences in the field of computer vision. In recent years, ECCV has established itself as a prime venue for the presentation of AI research papers including image classification, object detection, and other technologies using deep learning. The oral presentation acceptance rate was 2.7% in this year.

Tags: Kioxia
Previous Post
Nikon releases the NIKKOR Z 600mm f/4 TC VR S and MC-N10 Remote Grip for the Nikon Z mount system
Next Post
KLIPSCH INTRODUCES MCLAREN RACING INSPIRED PORTABLE SPEAKER

Related Posts

  • SSSTC Introduces PCIe Gen4 QLC SSDs for AI PCs and Industrial Applications

  • Kioxia Introduces Direct Liquid Cooling Support for Enterprise SSDs

  • Kioxia Introduces E1.L QLC-based SSDs for Hyperscale Data Centers

  • New 3D flash memory technology from KIOXIA and Sandisk achieves industry's highest bit density for QLC NAND

  • KIOXIA Exceria Pro G2 NVME 2TB

  • Kioxia Unveils New AI Infrastructure and Flash Memory Innovations at FMS 2026

  • Kioxia to Showcase CXL Compatible Memory Expansion Module KIOXIA XL1 Series for AI Workloads

  • KIOXIA unveils new AI storage lineup ahead of FMS 2026

Latest News

Lexar Introduces JumpDrive A50V and C50V Dashcam USB Drives
Consumer Electronics

Lexar Introduces JumpDrive A50V and C50V Dashcam USB Drives

Lexar ARES RGB 2nd Gen DDR5 Passes AMD EXPO Ultra Low Latency Certification Tests
PC components

Lexar ARES RGB 2nd Gen DDR5 Passes AMD EXPO Ultra Low Latency Certification Tests

Thypoch Introduces New Sculptor AF Lens Series with 23mm f1.4 Prime for Fujifilm X-Mount
Cameras

Thypoch Introduces New Sculptor AF Lens Series with 23mm f1.4 Prime for Fujifilm X-Mount

ASUS Announces Availability of ProArt GR1X
Enterprise & IT

ASUS Announces Availability of ProArt GR1X

Xiaomi and Leica Present the Xiaomi 18 Pro Series
Smartphones

Xiaomi and Leica Present the Xiaomi 18 Pro Series

Popular Reviews

Endorfy Thock V2 Wireless Keyboard

Endorfy Thock V2 Wireless Keyboard

SoundPeats Cove Pro

SoundPeats Cove Pro

The Quiet Technology Behind the Spin

The Quiet Technology Behind the Spin

Akaso Brave 8 Lite

Akaso Brave 8 Lite

SoundPeats C30

SoundPeats C30

Kioxia Exceria Plus G3 512GB microSD

Kioxia Exceria Plus G3 512GB microSD

be quiet! Dark Perk Mice

be quiet! Dark Perk Mice

XbotGo Chamaleon

XbotGo Chamaleon

Main menu

  • Home
  • News
  • Reviews
  • Essays
  • About
    • Submit News

    • Contact Us
    • Privacy

    • Promotion
    • Advertise

    • RSS Feed
  • About
  • Privacy
  • Contact Us
  • Promotional Opportunities @ CdrInfo.com
  • Advertise on out site
  • Submit your News to our site
  • RSS Feed