YoloV8改进策略：Block改进|CBlock，Transformer式的卷积结构|即插即用

摘要

论文标题: SparseViT: Nonsemantics-Centered, Parameter-Efficient Image Manipulation Localization through Spare-Coding Transformer
论文链接: https://arxiv.org/pdf/2412.14598
官方GitHub: https://github.com/scu-zjz/SparseViT

这段代码出自SparseViT ，代码如下：

import torch
import torch.nn as nn

from timm.models