为立体匹配模型的鲁棒性设计了首个系统化评测基准。
DispBench: Benchmarking Disparity Estimation to Synthetic Corruptions
- 构建合成噪声与对抗攻击的综合评测框架
- 发现精度与泛化能力存在显著相关性
- 适合关注模型可靠性与安全性的研究者
深度学习在标准基准上已超越人类表现，广泛应用于计算机视觉任务。其中，立体匹配（disparity estimation）通过估计双目图像中对应像素的视差，对医疗手术和自动驾驶等安全关键应用至关重要。然而，基于深度学习的立体匹配方法极易受分布偏移和对抗攻击影响，引发对其可靠性和泛化能力的担忧。尽管如此，当前仍缺乏标准化的鲁棒性评测基准，制约了该领域进展。为此，本文提出DispBench，一个系统评估立体匹配方法可靠性的综合性基准工具。它在多个数据集上针对2D通用噪声、对抗攻击及分布外变化等多样场景，全面评测模型鲁棒性。我们进行了迄今为止最广泛的性能与鲁棒性分析，揭示了准确性、可靠性与泛化能力之间的关键关联。代码开源：https://github.com/shashankskagnihotri/benchmarking_robustness/tree/disparity_estimation/final/disparity_estimation
原文摘要 · Abstract (English)
Deep learning (DL) has surpassed human performance on standard benchmarks, driving its widespread adoption in computer vision tasks. One such task is disparity estimation, estimating the disparity between matching pixels in stereo image pairs, which is crucial for safety-critical applications like medical surgeries and autonomous navigation. However, DL-based disparity estimation methods are highly susceptible to distribution shifts and adversarial attacks, raising concerns about their reliability and generalization. Despite these concerns, a standardized benchmark for evaluating the robustness of disparity estimation methods remains absent, hindering progress in the field. To address this gap, we introduce DispBench, a comprehensive benchmarking tool for systematically assessing the reliability of disparity estimation methods. DispBench evaluates robustness against synthetic image corruptions such as adversarial attacks and out-of-distribution shifts caused by 2D Common Corruptions across multiple datasets and diverse corruption scenarios. We conduct the most extensive performance and robustness analysis of disparity estimation methods to date, uncovering key correlations between accuracy, reliability, and generalization. Open-source code for DispBench: https://github.com/shashankskagnihotri/benchmarking_robustness/tree/disparity_estimation/final/disparity_estimation
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。