引导式测验 · 中等 等级
测试时间增强测验
检查测试时增强如何聚合固定模型预测(何时有帮助)、其计算成本和变换对齐要求。
问题 1 的 8
在推理时,测试时增强对单个输入有何作用?
预览每个问题8 问题
当您参加测验时,就会出现答案和解释。
- 在推理时,测试时增强对单个输入有何作用?
- 在输入的多个转换副本上运行固定模型并组合输出
- 每次查询时都根据增强数据重新训练模型
- 在每次预测之前向模型的权重添加噪声
- 压缩模型,使其推理运行得更快
- 何时通过对转换后的视图进行预测汇聚可以减少预测方差?
- When every view changes the true class
- When the transforms preserve the label and the view errors are at least partly uncorrelated
- When all predictions are identical by design
- When the model is retrained on each transformed copy
- 使用TTA的主要成本是什么?
- 它需要标记的测试数据
- 它永久改变训练的权重
- 它增加了推理计算,因为模型每个样本运行多次
- 它降低了干净输入的模型准确性
- 哪种增强选择实际上会损害数字分类器?
- 亮度变化小
- 微小的随机作物
- 添加一点高斯噪声
- 水平翻转“6”,使其看起来像“9”
- 在分割中,在平均 TTA 输出之前需要什么额外步骤?
- 反转每个几何变换,以便预测的掩模与原始像素重新对齐
- 为每个视图重新训练解码器
- 放弃所有翻转视图
- 将蒙版转换为边界框
- For a classification model, what may be aggregated across test-time views?
- The model’s training labels
- The predicted probabilities or logits from the views
- The input image file names
- The optimizer momentum buffers
- Does standard test-time augmentation require retraining the model on new labels?
- Yes; each view needs a newly trained model
- Yes; it requires extra class labels for every view
- No; it reuses fixed weights and evaluates transformed inputs at inference
- No; it replaces the model with a lookup table
- A segmentation model predicts masks on flipped and cropped views. What must happen before pixelwise pooling?
- Average masks before undoing the transforms
- Discard the original image coordinates
- Apply a different label to each pixel view
- Invert the geometric transforms so all masks align with the original image coordinates