loading page

Binary Encoding for Label
  • Jinxin Wei ,
  • Zhe Hou
Jinxin Wei
Vocational School of Juancheng

Corresponding Author:[email protected]

Author Profile


In order to solve the large classes problem, binary encoding for label is proposed. Through test on mnist dataset for classification task, The classification accuracy with binary encoding is almost equal to one-hot encoding. Large classes can be solved by binary encoding. Lossy compression can be achieved by abstract network and concrete network with absolute function. With one-hot encoding, the compression ratio is 5.1% when decompression quality is good. With binary encoding, the compression ratio is 2% when decompression quality is ok. When jump connection and negative feedback are used, the decompression performance is good.