通过历史参数对比，让模型自适应抗恶劣天气，提升深度估计鲁棒性。
Learning Depth from Past Selves: Self-Evolution Contrast for Robust Depth Estimation
- 利用训练中生成的中间参数构建时序演化模型，实现动态优化状态捕捉。
- 设计自进化对比损失，用历史输出作负样本，自动感知天气退化程度。
- 可无缝接入多种基线模型，零样本测试下显著提升雨雾等恶劣条件表现。
自监督深度估计在自动驾驶与机器人领域受到广泛关注。然而，现有方法在雨、雾等恶劣天气条件下因能见度降低，深度预测性能显著下降。为此，本文提出一种新颖的自演化对比学习框架SEC-Depth，用于自监督鲁棒深度估计。该方法利用训练过程中生成的中间参数构建时序演化延迟模型，并设计自演化对比机制以缓解挑战性环境下的性能损失。具体而言，我们首先为深度估计任务设计动态更新策略，以捕捉训练各阶段的优化状态；进而引入自演化对比损失（SECL），将历史延迟模型的输出作为负样本，从而在不依赖人工干预的情况下，自适应调整学习目标并隐式感知天气退化严重程度。实验表明，本方法可无缝集成到多种基线模型中，在零样本评估中显著增强鲁棒性。
原文摘要 · Abstract (English)
Self-supervised depth estimation has gained significant attention in autonomous driving and robotics. However, existing methods exhibit substantial performance degradation under adverse weather conditions such as rain and fog, where reduced visibility critically impairs depth prediction. To address this issue, we propose a novel self-evolution contrastive learning framework called SEC-Depth for self-supervised robust depth estimation tasks. Our approach leverages intermediate parameters generated during training to construct temporally evolving latency models. Using these, we design a self-evolution contrastive scheme to mitigate performance loss under challenging conditions. Concretely, we first design a dynamic update strategy of latency models for the depth estimation task to capture optimization states across training stages. To effectively leverage latency models, we introduce a self-evolution contrastive Loss (SECL) that treats outputs from historical latency models as negative samples. This mechanism adaptively adjusts learning objectives while implicitly sensing weather degradation severity, reducing the needs for manual intervention. Experiments show that our method integrates seamlessly into diverse baseline models and significantly enhances robustness in zero-shot evaluations.
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。