Hidden Biases of End-to-End Driving Datasets

• URL: http://arxiv.org/abs/2412.09602v2
• Date: Fri, 13 Dec 2024 09:51:22 GMT
• Title: Hidden Biases of End-to-End Driving Datasets
• Authors: Julian Zimmerlin, Jens Beißwenger, Bernhard Jaeger, Andreas Geiger, Kashyap Chitta,
• Abstract summary: We make a first attempt at end-to-end driving for CARLA Leaderboard 2.0. We systematically analyze the training dataset, leading to new insights. Our model ranks first and second respectively on the map and sensors tracks of the 2024 CARLA Challenge.
• Score: 25.931831743383782
• License:
• Abstract: End-to-end driving systems have made rapid progress, but have so far not been applied to the challenging new CARLA Leaderboard 2.0. Further, while there is a large body of literature on end-to-end architectures and training strategies, the impact of the training dataset is often overlooked. In this work, we make a first attempt at end-to-end driving for Leaderboard 2.0. Instead of investigating architectures, we systematically analyze the training dataset, leading to new insights: (1) Expert style significantly affects downstream policy performance. (2) In complex data sets, the frames should not be weighted on the basis of simplistic criteria such as class frequencies. (3) Instead, estimating whether a frame changes the target labels compared to previous frames can reduce the size of the dataset without removing important information. By incorporating these findings, our model ranks first and second respectively on the map and sensors tracks of the 2024 CARLA Challenge, and sets a new state-of-the-art on the Bench2Drive test routes. Finally, we uncover a design flaw in the current evaluation metrics and propose a modification for future challenges. Our dataset, code, and pre-trained models are publicly available at https://github.com/autonomousvision/carla_garage.

Related papers

• TARGO: Benchmarking Target-driven Object Grasping under Occlusions [39.970680093124145]
  We first establish a new benchmark dataset for TARget-driven Grasping under Occlusions, named TARGO. We evaluate five grasp models and found that even the current SOTA model suffers when the occlusion level increases. We propose a transformer-based grasping model involving a shape completion module, termed TARGO-Net.
  arXiv  Detail & Related papers  (2024-07-08T17:47:45Z)
• A Data-Centric Perspective on Evaluating Machine Learning Models for Tabular Data [9.57464542357693]
  This paper demonstrates that model-centric evaluations are biased, as real-world modeling pipelines often require dataset-specific preprocessing and feature engineering. We select 10 relevant datasets from Kaggle competitions and implement expert-level preprocessing pipelines for each dataset. After dataset-specific feature engineering, model rankings change considerably, performance differences decrease, and the importance of model selection reduces.
  arXiv  Detail & Related papers  (2024-07-02T09:54:39Z)
• Kick Back & Relax++: Scaling Beyond Ground-Truth Depth with SlowTV & CribsTV [50.616892315086574]
  This paper proposes two novel datasets: SlowTV and CribsTV. These are large-scale datasets curated from publicly available YouTube videos, containing a total of 2M training frames. We leverage these datasets to tackle the challenging task of zero-shot generalization.
  arXiv  Detail & Related papers  (2024-03-03T17:29:03Z)
• Is Ego Status All You Need for Open-Loop End-to-End Autonomous Driving? [84.17711168595311]
  End-to-end autonomous driving has emerged as a promising research direction to target autonomy from a full-stack perspective. nuScenes dataset, characterized by relatively simple driving scenarios, leads to an under-utilization of perception information in end-to-end models. We introduce a new metric to evaluate whether the predicted trajectories adhere to the road.
  arXiv  Detail & Related papers  (2023-12-05T11:32:31Z)
• Transfer Learning between Motor Imagery Datasets using Deep Learning -- Validation of Framework and Comparison of Datasets [0.0]
  We present a simple deep learning-based framework commonly used in computer vision. We demonstrate its effectiveness for cross-dataset transfer learning in mental imagery decoding tasks.
  arXiv  Detail & Related papers  (2023-09-04T20:58:57Z)
• Deconstructing Self-Supervised Monocular Reconstruction: The Design Decisions that Matter [63.5550818034739]
  This paper presents a framework to evaluate state-of-the-art contributions to self-supervised monocular depth estimation. It includes pretraining, backbone, architectural design choices and loss functions. We re-implement, validate and re-evaluate 16 state-of-the-art contributions and introduce a new dataset.
  arXiv  Detail & Related papers  (2022-08-02T14:38:53Z)
• Learning from Temporal Spatial Cubism for Cross-Dataset Skeleton-based Action Recognition [88.34182299496074]
  Action labels are only available on a source dataset, but unavailable on a target dataset in the training stage. We utilize a self-supervision scheme to reduce the domain shift between two skeleton-based action datasets. By segmenting and permuting temporal segments or human body parts, we design two self-supervised learning classification tasks.
  arXiv  Detail & Related papers  (2022-07-17T07:05:39Z)
• LID 2020: The Learning from Imperfect Data Challenge Results [242.86700551532272]
  Learning from Imperfect Data workshop aims to inspire and facilitate the research in developing novel approaches. We organize three challenges to find the state-of-the-art approaches in weakly supervised learning setting. This technical report summarizes the highlights from the challenge.
  arXiv  Detail & Related papers  (2020-10-17T13:06:12Z)
• 2nd Place Scheme on Action Recognition Track of ECCV 2020 VIPriors Challenges: An Efficient Optical Flow Stream Guided Framework [57.847010327319964]
  We propose a data-efficient framework that can train the model from scratch on small datasets. Specifically, by introducing a 3D central difference convolution operation, we proposed a novel C3D neural network-based two-stream framework. It is proved that our method can achieve a promising result even without a pre-trained model on large scale datasets.
  arXiv  Detail & Related papers  (2020-08-10T09:50:28Z)

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.