RPR: Random Partition Relaxation for Training; Binary and Ternary Weight Neural Networks

TerViT: An Efficient Ternary Vision Transformer

Vision transformers (ViTs) have demonstrated great potential in various visual tasks, but suffer from expensive computational and memory cost problems when deployed on resource-constrained devices. In this paper, we introduce a ternary vision transformer (TerViT) to ternarize the weights in ViTs, which are challenged by the large loss surface gap between real-valued and ternary parameters. To address the issue, we introduce a progressive training scheme by first training 8-bit transformers and then TerViT, and achieve a better optimization than conventional methods. Furthermore, we introduce c…

无损 INR：无损体隐式神经表示

Lossless-INR: Lossless Volumetric Implicit Neural Representations

研究针对体数据的无损 INR 框架，核心方法是基于位平面分解，将重建转为逐位二进制分类，结合八叉树块分区与三元特征网格网络，实现零误码率和逐位精确重建，利于逼真渲染与下游分析。

Incremental Network Quantization: Towards Lossless CNNs with Low-Precision Weights

This paper presents incremental network quantization (INQ), a novel method, targeting to efficiently convert any pre-trained full-precision convolutional neural network (CNN) model into a low-precision version whose weights are constrained to be either powers of two or zero. Unlike existing methods which are struggled in noticeable accuracy loss, our INQ has the potential to resolve this issue, as benefiting from two innovations. On one hand, we introduce three interdependent operations, namely weight partition, group-wise quantization and re-training. A well-proven measure is employed to divi…