Two Heads are Better Than One: Neural Networks Quantization with 2D Hilbert Curve-based Output Representation
Uss, Mykhailo, Yermolenko, Ruslan, Kolodiazhna, Olena, Shashko, Oleksii, Safonov, Ivan, Savin, Volodymyr, Yeo, Yoonjae, Ji, Seowon, Jeong, Jaeyun
–arXiv.org Artificial Intelligence
Quantization is widely used to increase deep neural networks' (DNN) memory, computation, and power efficiency. Various techniques, such as post-training quantization and quantization-aware training, have been proposed to improve quantization quality. We introduce a novel approach for DNN quantization that uses a redundant representation of DNN's output. We represent the target quantity as a point on a 2D parametric curve. The DNN model is modified to predict 2D points that are mapped back to the target quantity at a post-processing stage. We demonstrate that this mapping can reduce quantization error. For the low-order parametric Hilbert curve, Depth-From-Stereo task, and two models represented by U-Net architecture and vision transformer, we achieved a quantization error reduction by about 5 times for the INT8 model at both CPU and DSP delegates. This gain comes with a minimal inference time increase (less than 7%). Our approach can be applied to other tasks, including segmentation, object detection, and key-points prediction.
arXiv.org Artificial Intelligence
May-22-2024
- Country:
- North America > United States
- New York > New York County
- New York City (0.04)
- Illinois > Champaign County
- Urbana (0.04)
- New York > New York County
- Europe > Ukraine
- Kyiv Oblast > Kyiv (0.05)
- Kharkiv Oblast > Kharkiv (0.04)
- Asia > South Korea
- North America > United States
- Genre:
- Research Report > Promising Solution (0.34)
- Technology: