- Media recognition
- Media data analysis
Few-shot object detection
Image recognition AI detects new objects with unprecedented accuracy, quickly and easily, by registering a single image.
- Even with a change in the product or part handled in the manufacturing and logistics workplace, this technology detects the new object immediately just by registering a single image.
- In the past, it was necessary to prepare and learn from many images, creating extra work. The “Few-Shot Object Detection AI” is automatically pre-trained to recognize the shapes of non-target objects in the training images, a proprietary development in the training process that enables the AI to detect new objects with the registration of a single image and no retraining in the field.
Applications
- Factories: Check location of products and parts.
- Plants: Detect and track facilities.
- Logistics: Detect and track products.
Benchmarks, strengths, and track record
- Achieves unprecedented accuracy in Few-shot object detection, with no retraining.
- No need for retraining in the field
- Immediately detects new objects with the registration of a few target images
Inquiries
Contact the Toshiba Corporate Research & Development Center
Please include the title “Toshiba AI Technology Catalog: Few-shot object detection” or the URL in the inquiry text.
Please note that because this technology is currently the subject of R&D activities, immediate responses to inquiries may not be possible.
References:
- D. Kobayashi, Self-supervised Prototype Conditional Few-Shot Object Detection, Proc. ICIAP2021, pp.681-692, 2022.
- Toshiba Develops Image Recognition-Based Few-Shot Object Detection AI for Immediate Detection of a New Object with Unprecedented Accuracy by Registering a Single Image of the Object - Ease of incorporation and operation contributes to digitization and promotes digital transformation at factories and plants that handle many different parts and equipment - R&D Center; Toshiba (global.toshiba)