DART Enables Real-Time SAM3 Detection with INT8 Quantization for Edge

rsasaki0109 · x · 2026-08-29

Mehmet Kerem Turkcan released DART, a training-free framework converting SAM3 into a real-time multi-class open-vocabulary detector. It achieves 15.8 FPS on an RTX 4080. The upgrade, DARTF, uses rotation-based quantization to enable INT8 inference for LayerNorm vision transformers. On Jetson AGX Orin, DARTF is 43% faster and uses 42% less energy than DART's FP16 engine while maintaining FP32-level quality (56.0 AP).

Related event: DART Turns SAM into a Real-Time Open-Vocabulary Detector Without Training(2 posts)→

Original post →

More from Infra

Infra channel →