面向域增量式3D目标检测的基于梯度的最大干扰检索方法
Gradient-based Maximally Interfered Retrieval for Domain Incremental 3D Object Detection
AI总结：
针对自动驾驶3D目标检测在天气域增量场景下的灾难性遗忘与全量从头训练成本过高的问题，提出基于梯度的最大干扰检索回放策略GMIR，在STF数据集上实现了媲美全量从头训练的性能且训练时间减半。
摘要：
由于目前大多数研究都基于晴朗天气数据开展，实现全天候条件下的精准3D目标检测仍是推动自动驾驶大规模落地的核心挑战。为了让模型适配恶劣天气条件，监督式方法若在全天气数据上从头训练，效果会优于在晴朗天气预训练模型上进行微调。但随着数据集持续扩充、覆盖所有可能的天气类型，全量数据从头训练最终会出现计算成本过高、难以实现的问题。另一方面，直接在不同天气域的数据上进行简单微调，会导致模型对先前学习过的域产生灾难性遗忘。受基于回放的持续学习方法的成功启发，我们提出了基于梯度的最大干扰检索（Gradient-based Maximally Interfered Retrieval，GMIR），这是一种用于回放的基于梯度的采样策略。在微调过程中，GMIR会定期从先前域的数据集中检索样本，这些样本的梯度向量与当前更新的梯度向量存在最大干扰。我们在SeeingThroughFog（STF）数据集上开展的3D目标检测实验表明，GMIR不仅能克服遗忘问题，还能取得与全量数据从头训练相当的性能，同时总训练时间减少46.25%。
英文摘要：
Accurate 3D object detection in all weather conditions remains a key challenge to enable the widespread deployment of autonomous vehicles, as most work to date has been performed on clear weather data. In order to generalize to adverse weather conditions, supervised methods perform best if trained from scratch on all weather data instead of finetuning a model pretrained on clear weather data. Training from scratch on all data will eventually become computationally infeasible and expensive as datasets continue to grow and encompass the full extent of possible weather conditions. On the other hand, naive finetuning on data from a different weather domain can result in catastrophic forgetting of the previously learned domain. Inspired by the success of replay-based continual learning methods, we propose Gradient-based Maximally Interfered Retrieval (GMIR), a gradient based sampling strategy for replay. During finetuning, GMIR periodically retrieves samples from the previous domain dataset whose gradient vectors show maximal interference with the gradient vector of the current update. Our 3D object detection experiments on the SeeingThroughFog (STF) dataset show that GMIR not only overcomes forgetting but also offers competitive performance compared to scratch training on all data with a 46.25% reduction in total training time.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
