用统一标签空间的蒸馏法，让小模型在自动驾驶图像分割上超越大模型。
Knowledge Distillation for Semantic Segmentation: A Label Space Unification Approach
- 通过映射不同数据集标签体系到统一标准，生成更准确的伪标签。
- 在城市与非公路场景中，学生模型性能均超过教师模型。
- 构建了迄今最大的自动驾驶图像分割数据集，覆盖12个城市场景和7个非公路数据集。
近年来，大量语义分割领域数据集相继发布，但因标签体系不一致，难以训练更优的大模型。为此，本文提出一种知识蒸馏方法，同时实现标签空间统一。具体地，先在源数据集上训练教师模型，再利用其对具有相关标签体系的数据进行伪标注；通过将相关标签体系映射至源标签体系，约束模型输出伪标签。基于修正后的伪标签，训练的学生模型在城市与非公路驾驶两大挑战性场景中表现均优于教师模型。最终生成的真值校正伪标签覆盖12个城市和7个非公路公开数据集，分别包含388.230万和18.558万张图像，成为当前自动驾驶领域规模最大的复合数据集。
原文摘要 · Abstract (English)
An increasing number of datasets sharing similar domains for semantic segmentation have been published over the past few years. But despite the growing amount of overall data, it is still difficult to train bigger and better models due to inconsistency in taxonomy and/or labeling policies of different datasets. To this end, we propose a knowledge distillation approach that also serves as a label space unification method for semantic segmentation. In short, a teacher model is trained on a source dataset with a given taxonomy, then used to pseudo-label additional data for which ground truth labels of a related label space exist. By mapping the related taxonomies to the source taxonomy, we create constraints within which the model can predict pseudo-labels. Using the improved pseudo-labels we train student models that consistently outperform their teachers in two challenging domains, namely urban and off-road driving. Our ground truth-corrected pseudo-labels span over 12 and 7 public datasets with 388.230 and 18.558 images for the urban and off-road domains, respectively, creating the largest compound datasets for autonomous driving to date.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。