Binary Dense Predictors for Human Pose Estimation Based on Dynamic Thresholds and Filtering
Lists
Only you see this
Abstract
Binary neural networks (BNNs) contribute a lot to the efficiency of image classification models. However, in dense predication tasks such as human pose estimation, predictions in different locations are coupled and rely on the extraction of features across entire images. As a result, more robust and adaptive binarization is required to bridge the performance gap between binarized and full precision models. We propose two approaches to conduct image-aware and pixel-aware dynamic binarization in a model for human pose estimation. Firstly, a simplified dynamic thresholding is leveraged in the backbone to determine unique binarization thresholds for each image. Secondly, in the decoder, we decouple binarization for each pixel according to the activations surrounding the pixel. Dynamic filtering modules are proposed to determine a different binarization strategy for each pixel. Compared with the strong baselines, the proposed framework improves 5.2% and 3.6% mAP on the COCO test-dev benchmark for ResNet-18/34 architectures respectively.
BibTeX
@inproceedings{xing2022binary,
author = {Xingrun Xing and Yalong Jiang and Baochang Zhang and Wenrui Ding and Yangguang Li and Hongguang Li and Huan Peng},
title = {{Binary Dense Predictors for Human Pose Estimation Based on Dynamic Thresholds and Filtering}},
booktitle = {IEEE International Conference on Acoustics, Speech and Signal Processing},
year = {2022},
url = {https://openreview.net/forum?id=rZmsKrHgc1},
}Loading related content...