1. MCUNetV2: Memory-efficient patch-based inference for tiny deep learning;lin,0
2. MCUNet: Tiny deep learning on IoT devices;lin,0
3. On-Device Image Classification with Proxyless Neural Architecture Search and Quantization-Aware Fine-Tuning
4. Once-for-all: Train one network and specialize it for efficient deployment;cai,0
5. Deep compression: Compressing deep neural networks with pruning, trained quantization and huffman coding;han,0