Equal Bits: Enforcing Equally Distributed Binary Network Weights

2 Dec 2021  ·  Yunqiang Li, Silvia L. Pintea, Jan C. van Gemert ·

Binary networks are extremely efficient as they use only two symbols to define the network: $\{+1,-1\}$. One can make the prior distribution of these symbols a design choice. The recent IR-Net of Qin et al. argues that imposing a Bernoulli distribution with equal priors (equal bit ratios) over the binary weights leads to maximum entropy and thus minimizes information loss. However, prior work cannot precisely control the binary weight distribution during training, and therefore cannot guarantee maximum entropy. Here, we show that quantizing using optimal transport can guarantee any bit ratio, including equal ratios. We investigate experimentally that equal bit ratios are indeed preferable and show that our method leads to optimization benefits. We show that our quantization method is effective when compared to state-of-the-art binarization methods, even when using binary weight pruning.

PDF Abstract

Results from the Paper

  Submit results from this paper to get state-of-the-art GitHub badges and help the community compare results to other papers.


No methods listed for this paper. Add relevant methods here