shifts instance

在LaneNet中，"shifts instance"指的是实例的偏移。这可能是由于分布的偏移导致的，这在现实世界的应用中是不可避免的。之前的方法中使用了固定的转换矩阵H，但是当地面发生变化时，即消失点上下移动时，这个转换矩阵也会发生变化。为了解决这个问题，LaneNet使用神经网络实时学习预测这个转换矩阵H，从而更好地适应不同环境下的实例偏移。<span class="em">1</span><span class="em">2</span><span class="em">3</span>
#### 引用[.reference_title]
- *1* *3* [车道线检测--Towards End-to-End Lane Detection: an Instance Segmentation Approach](https://blog.csdn.net/zhangjunhit/article/details/89531619)[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%"]
- *2* [CrossNorm and SelfNorm for Generalization under Distribution Shifts](https://blog.csdn.net/qq_43527694/article/details/124283034)[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 ]