Poly loss损失函数

PolyLoss是一种通过将损失函数设计为多项式函数的线性组合来逼近基于任务和数据集的最优损失函数的算法。它的灵活性使得可以根据具体的任务和数据集来调整多项式基的重要性，并且可以将Cross-entropy loss和Focal loss作为PolyLoss的特殊情况。实验结果表明，PolyLoss在二维图像分类、实例分割、目标检测和三维目标检测任务上都明显优于Cross-entropy loss和Focal loss。通过引入一个额外的超参数并添加一行代码，可以轻松地使用PolyLoss来提高模型的性能。<span class="em">1</span><span class="em">2</span><span class="em">3</span>
#### 引用[.reference_title]
- *1* *2* [【图像分类损失】PolyLoss：一个优于 Cross-entropy loss和Focal loss的分类损失](https://blog.csdn.net/Roaddd/article/details/128164945)[target="_blank" data-report-click={"spm":"1018.2226.3001.9630","extra":{"utm_source":"vip_chatgpt_common_search_pc_result","utm_medium":"distribute.pc_search_result.none-task-cask-2~all~insert_cask~default-1-null.142^v93^chatsearchT3_1"}}] [.reference_item style="max-width: 50%"]
- *3* [PolyLoss：一种将分类损失函数加入泰勒展开式的损失函数](https://blog.csdn.net/anshiquanshu/article/details/124784629)[target="_blank" data-report-click={"spm":"1018.2226.3001.9630","extra":{"utm_source":"vip_chatgpt_common_search_pc_result","utm_medium":"distribute.pc_search_result.none-task-cask-2~all~insert_cask~default-1-null.142^v93^chatsearchT3_1"}}] [.reference_item style="max-width: 50%"]
[ .reference_list ]