Kai Han, Yixing Xu, Chang Xu, Chunjing Xu, Yunhe Wang, Enhua Wu
We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
This paper formalizes the binarization operations over neural networks from a learning perspective. In contrast to classical hand crafted rules (e.g. hard thresholding) to binarize full-precision neurons, we propose to learn a mapping from fullprecision neurons to the target binary ones. Each individual weight entry will not be binarized independently. Instead, they are taken as a whole to accomplish the binarization, just as they work together in generating convolution features. To help the training of the binarization mapping, the full-precision neurons after taking sign operations is regarded as some auxiliary supervision signal, which is noisy but still has valuable guidance. An unbiased estimator is therefore introduced to mitigate the influence of the supervision noise. Experimental results on benchmark datasets indicate that the proposed binarization technique attains consistent improvements over baselines.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2010.04871")
get_code_for_paper("2010.04871")
have("2010.04871")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2010.04871.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2010.04871)
Connect an agent — have() is free.