Kioxia Develops Image-Recognition System For Logistics
Kioxia Corporation, with partners Tsubakimoto Chain and EAGLYS, has developed an AI-driven image-recognition system for logistics that uses KIOXIA AiSAQ and Memory-Centric AI, and will be demonstrated at the 2025 International Robot Exhibition on December 3–6 in Tokyo. The approach stores extensive product images and features in high-capacity storage and indexes them into SSDs to enable rapid classification of new SKUs without retraining, and AiSAQ is released open-source on GitHub.
Key Points
- 1Introduces AiSAQ image-recognition using memory-centric AI to classify conveyor-belt products without retraining models.
- 2Reduces operational cost and latency by indexing storage-resident features and moving indexes into SSDs.
- 3Enables logistics teams to onboard new SKUs quickly; software released open-source for practitioner adoption.
Scoring Rationale
Official open-source product release and practical demo, strong immediate applicability but represents incremental engineering rather than groundbreaking research.
Practice interview problems based on real data
1,625 SQL & Python problems across 15 industry datasets — the exact type of data you work with.
Try 250 free problems
