The Binary Quantized Neural Network for Dense Prediction via Specially Designed Upsampling and Attention

TL;DR

This paper introduces a binary neural network approach for dense prediction tasks, utilizing specially designed upsampling and attention strategies to improve accuracy and efficiency in tasks like segmentation.

Contribution

It presents a novel multi-branch upsampling method and an optimized attention mechanism that significantly reduce computation while maintaining high accuracy in binary neural networks for dense prediction.

Findings

Achieved high accuracy with binary neural networks on dense prediction tasks.

Reduced attention computation complexity by a factor of 100.

Validated effectiveness on Cityscapes, KITTI, and ECSSD datasets.

Abstract

Deep learning-based information processing consumes long time and requires huge computing resources, especially for dense prediction tasks which require an output for each pixel, like semantic segmentation and salient object detection. There are mainly two challenges for quantization of dense prediction tasks. Firstly, directly applying the upsampling operation that dense prediction tasks require is extremely crude and causes unacceptable accuracy reduction. Secondly, the complex structure of dense prediction networks means it is difficult to maintain a fast speed as well as a high accuracy when performing quantization. In this paper, we propose an effective upsampling method and an efficient attention computation strategy to transfer the success of the binary neural networks (BNN) from single prediction tasks to dense prediction tasks. Firstly, we design a simple and robust multi-branch parallel upsampling structure to achieve the high accuracy. Then we further optimize the attention method which plays an important role in segmentation but has huge computation complexity. Our attention method can reduce the computational complexity by a factor of one hundred times but retain the original effect. Experiments on Cityscapes, KITTI road, and ECSSD fully show the effectiveness of our work.