An Efficient Domain-Incremental Learning Approach to Drive in All Weather Conditions

• URL: http://arxiv.org/abs/2204.08817v2
• Date: Thu, 21 Apr 2022 14:16:52 GMT
• Title: An Efficient Domain-Incremental Learning Approach to Drive in All Weather Conditions
• Authors: M. Jehanzeb Mirza, Marc Masana, Horst Possegger, Horst Bischof
• Abstract summary: Deep neural networks enable impressive visual perception performance for autonomous driving. They are prone to forgetting previously learned information when adapting to different weather conditions. We propose DISC -- Domain Incremental through Statistical Correction -- a simple zero-forgetting approach which can incrementally learn new tasks.
• Score: 8.436505917796174
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Although deep neural networks enable impressive visual perception performance for autonomous driving, their robustness to varying weather conditions still requires attention. When adapting these models for changed environments, such as different weather conditions, they are prone to forgetting previously learned information. This catastrophic forgetting is typically addressed via incremental learning approaches which usually re-train the model by either keeping a memory bank of training samples or keeping a copy of the entire model or model parameters for each scenario. While these approaches show impressive results, they can be prone to scalability issues and their applicability for autonomous driving in all weather conditions has not been shown. In this paper we propose DISC -- Domain Incremental through Statistical Correction -- a simple online zero-forgetting approach which can incrementally learn new tasks (i.e weather conditions) without requiring re-training or expensive memory banks. The only information we store for each task are the statistical parameters as we categorize each domain by the change in first and second order statistics. Thus, as each task arrives, we simply 'plug and play' the statistical vectors for the corresponding task into the model and it immediately starts to perform well on that task. We show the efficacy of our approach by testing it for object detection in a challenging domain-incremental autonomous driving scenario where we encounter different adverse weather conditions, such as heavy rain, fog, and snow.

Related papers

• WeatherGFM: Learning A Weather Generalist Foundation Model via In-context Learning [69.82211470647349]
  We introduce the first generalist weather foundation model (WeatherGFM) It addresses a wide spectrum of weather understanding tasks in a unified manner. Our model can effectively handle up to ten weather understanding tasks, including weather forecasting, super-resolution, weather image translation, and post-processing.
  arXiv  Detail & Related papers  (2024-11-08T09:14:19Z)
• Robust Monocular Depth Estimation under Challenging Conditions [81.57697198031975]
  State-of-the-art monocular depth estimation approaches are highly unreliable under challenging illumination and weather conditions. We tackle these safety-critical issues with md4all: a simple and effective solution that works reliably under both adverse and ideal conditions.
  arXiv  Detail & Related papers  (2023-08-18T17:59:01Z)
• Sit Back and Relax: Learning to Drive Incrementally in All Weather Conditions [16.014293219912]
  In autonomous driving scenarios, current object detection models show strong performance when tested in clear weather. We propose Domain-Incremental Learning through Activation Matching (DILAM) to adapt only the affine parameters of a clear weather pre-trained network to different weather conditions. Our memory bank is extremely lightweight, since affine parameters account for less than 2% of a typical object detector.
  arXiv  Detail & Related papers  (2023-05-30T11:37:41Z)
• TrafficBots: Towards World Models for Autonomous Driving Simulation and Motion Prediction [149.5716746789134]
  We show data-driven traffic simulation can be formulated as a world model. We present TrafficBots, a multi-agent policy built upon motion prediction and end-to-end driving. Experiments on the open motion dataset show TrafficBots can simulate realistic multi-agent behaviors.
  arXiv  Detail & Related papers  (2023-03-07T18:28:41Z)
• ClimaX: A foundation model for weather and climate [51.208269971019504]
  ClimaX is a deep learning model for weather and climate science. It can be pre-trained with a self-supervised learning objective on climate datasets. It can be fine-tuned to address a breadth of climate and weather tasks.
  arXiv  Detail & Related papers  (2023-01-24T23:19:01Z)
• Domain Adaptive Object Detection for Autonomous Driving under Foggy Weather [25.964194141706923]
  This paper proposes a novel domain adaptive object detection framework for autonomous driving under foggy weather. Our method leverages both image-level and object-level adaptation to diminish the domain discrepancy in image style and object appearance. Experimental results on public benchmarks show the effectiveness and accuracy of the proposed method.
  arXiv  Detail & Related papers  (2022-10-27T05:09:10Z)
• Automatic extraction of similar traffic scenes from large naturalistic datasets using the Hausdorff distance [0.0]
  We present a four-step extraction method that uses the Hausdorff distance, a mathematical distance metric for sets. With this new method, the variability in operational and tactical human behavior can be investigated, without the need for costly and time-consuming driving-simulator experiments.
  arXiv  Detail & Related papers  (2022-06-17T06:59:51Z)
• SHIFT: A Synthetic Driving Dataset for Continuous Multi-Task Domain Adaptation [152.60469768559878]
  SHIFT is the largest multi-task synthetic dataset for autonomous driving. It presents discrete and continuous shifts in cloudiness, rain and fog intensity, time of day, and vehicle and pedestrian density. Our dataset and benchmark toolkit are publicly available at www.vis.xyz/shift.
  arXiv  Detail & Related papers  (2022-06-16T17:59:52Z)
• Towards Optimal Strategies for Training Self-Driving Perception Models in Simulation [98.51313127382937]
  We focus on the use of labels in the synthetic domain alone. Our approach introduces both a way to learn neural-invariant representations and a theoretically inspired view on how to sample the data from the simulator. We showcase our approach on the bird's-eye-view vehicle segmentation task with multi-sensor data.
  arXiv  Detail & Related papers  (2021-11-15T18:37:43Z)
• Dream to Explore: Adaptive Simulations for Autonomous Systems [3.0664963196464448]
  We tackle the problem of learning to control dynamical systems by applying Bayesian nonparametric methods. By employing Gaussian processes to discover latent world dynamics, we mitigate common data efficiency issues observed in reinforcement learning. Our algorithm jointly learns a world model and policy by optimizing a variational lower bound of a log-likelihood.
  arXiv  Detail & Related papers  (2021-10-27T04:27:28Z)
• Meta Reinforcement Learning-Based Lane Change Strategy for Autonomous Vehicles [11.180588185127892]
  Supervised learning algorithms can generalize to new environments by training on a large amount of labeled data. It can be often impractical or cost-prohibitive to obtain sufficient data for each new environment. We propose a meta reinforcement learning (MRL) method to improve the agent's generalization capabilities.
  arXiv  Detail & Related papers  (2020-08-28T02:57:11Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.