AQD: Towards Accurate Fully-Quantized Object Detection
arXiv:2007.06919
Abstract
Network quantization allows inference to be conducted using low-precision arithmetic for improved inference efficiency of deep neural networks on edge devices. However, designing aggressively low-bit (e.g., 2-bit) quantization schemes on complex tasks, such as object detection, still remains challenging in terms of severe performance degradation and unverifiable efficiency on common hardware. In this paper, we propose an Accurate Quantized object Detection solution, termed AQD, to fully get rid of floating-point computation. To this end, we target using fixed-point operations in all kinds of layers, including the convolutional layers, normalization layers, and skip connections, allowing the inference to be executed using integer-only arithmetic. To demonstrate the improved latency-vs-accuracy trade-off, we apply the proposed methods on RetinaNet and FCOS. In particular, experimental results on MS-COCO dataset show that our AQD achieves comparable or even better performance compared with the full-precision counterpart under extremely low-bit schemes, which is of great practical value. Source code and models are available at: https://github.com/ziplab/QTool
CVPR 2021 Oral
References in corpus (14)
- Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
- MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications
- Binarized Neural Networks: Training Deep Neural Networks with Weights and Activations Constrained to +1 or -1
- Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation
- DoReFa-Net: Training Low Bitwidth Convolutional Neural Networks with Low Bitwidth Gradients
- Binarized Neural Networks
- PACT: Parameterized Clipping Activation for Quantized Neural Networks
- Convolutional Neural Networks using Logarithmic Data Representation
- Training Deep Neural Networks with 8-bit Floating Point Numbers
- Scalable Methods for 8-bit Training of Neural Networks
- Hierarchical binary CNNs for landmark localization with limited resources
- Automating Generation of Low Precision Deep Learning Operators
- Training Quantized Neural Networks with a Full-precision Auxiliary Module