|TREND||DATASET||BEST METHOD||PAPER TITLE||PAPER||CODE||COMPARE|
Recently, segmentation-based methods are quite popular in scene text detection, as the segmentation results can more accurately describe scene text of various shapes such as curve text.
Ranked #2 on Scene Text Detection on MSRA-TD500
In this paper, we attempt to maintain the information propagated in the forward process and propose a Balanced Binary Neural Networks with Gated Residual (BBG for short).
Ranked #178 on Image Classification on ImageNet
Our empirical study indicates that the quantization brings information loss in both forward and backward propagation, which is the bottleneck of training accurate binary neural networks.
We propose two efficient approximations to standard convolutional neural networks: Binary-Weight-Networks and XNOR-Networks.
To this end, we make the following contributions: (a) we are the first to study the effect of neural network binarization on localization tasks, namely human pose estimation and face alignment.
Well established text line segmentation evaluation schemes such as the Detection Rate or Recognition Accuracy demand for binarized data that is annotated on a pixel level.
(d) We present results for experiments on the most challenging datasets for human pose estimation and face alignment, reporting in many cases state-of-the-art performance.
Ranked #1 on Face Alignment on AFLW-Full
However, the binarization of weights and activations leads to feature maps of lower quality and lower capacity and thus a drop in accuracy compared to traditional networks.
In this work we present a new framework for neural networks compression with fine-tuning, which we called Neural Network Compression Framework (NNCF).
Ranked #1 on Binarization on ImageNet