Adaptive Binary-Ternary Quantization
원문 초록
Neural network models are resource hungry. It is difficult to deploy such deep networks on devices with limited resources, like smart wearables, cellphones, drones, and autonomous vehicles. Low bit quantization such as binary and ternary quantization is a common approach to alleviate this resource requirements. Ternary quantization provides a more flexible model and outperforms binary quantization in terms of accuracy, however doubles the memory footprint and increases the computational cost. Contrary to these approaches, mixed quantized models allow a trade-off between accuracy and memory footprint. In such models, quantization depth is often chosen manually, or is tuned using a separate optimization routine. The latter requires training a quantized network multiple times. Here, we propose an adaptive combination of binary and ternary quantization, namely Smart Quantization (SQ), in which the quantization depth is modified directly via a regularization function, so that the model is trained only once. Our experimental results show that the proposed method adapts quantization depth successfully while keeping the model accuracy high on MNIST and CIFAR10 benchmarks.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
J3DAI: A tiny DNN-Based Edge AI Accelerator for 3D-Stacked CMOS Image Sensor
Hashed Watermark as a Filter: Defeating Forging and Overwriting Attacks in Weight-based Neural Network Watermarking
MGVQ: Could VQ-VAE Beat VAE? A Generalizable Tokenizer with Multi-group Quantization
ViT-ProtoNet for Few-Shot Image Classification: A Multi-Benchmark Evaluation
Compress Any Segment Anything Model (SAM)
OpenDPDv2: A Unified Learning and Optimization Framework for Neural Network Digital Predistortion
토론
이 논문과 연결된 포럼 글이 아직 없습니다.