mlsanityData to 14 Oct 2026

A Fine-Grained Dataset and its Efficient Semantic Segmentation for Unstructured Driving Scenarios

arXiv 2103.13109 ↗First posted 24 Mar 2021cs.CV cs.LGcited by 18

Not on the map. Why?

Abstract (arXiv)

Research in autonomous driving for unstructured environments suffers from a lack of semantically labeled datasets compared to its urban counterpart. Urban and unstructured outdoor environments are challenging due to the varying lighting and weather conditions during a day and across seasons. In this paper, we introduce TAS500, a novel semantic segmentation dataset for autonomous driving in unstructured environments. TAS500 offers fine-grained vegetation and terrain classes to learn drivable surfaces and natural obstacles in outdoor scenes effectively. We evaluate the performance of modern semantic segmentation models with an additional focus on their efficiency. Our experiments demonstrate the advantages of fine-grained semantic classes to improve the overall prediction accuracy, especially along the class boundaries. The dataset and pretrained model are available at mucar3.de/icpr2020-tas500.

Key facts. Cited by 18 papers in the map (data through 14 Oct 2026). Builds on 25 of its 49 references that are in the map. First posted on arXiv 24 Mar 2021.

Builds on

25 of 49 references.

References · 25

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  3. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  4. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,364
  5. 2014Fully Convolutional Networks for Semantic Segmentationcited by 4,859
  6. 2016The Cityscapes Dataset for Semantic Urban Scene Understandingcited by 4,444
  7. 2016Pyramid Scene Parsing Networkcited by 2,479
  8. 2017Rethinking Atrous Convolution for Semantic Image Segmentationcited by 2,161
  9. 2016Identity Mappings in Deep Residual Networkscited by 1,965
  10. 2015SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentationcited by 1,487
  11. 2018BiSeNet: Bilateral Segmentation Network for Real-time Semantic Segmentationcited by 645
  12. 2016Training Region-based Object Detectors with Online Hard Example Miningcited by 579
13 more
  1. 2016ENet: A Deep Neural Network Architecture for Real-Time Semantic Segmentationcited by 291
  2. 2017ICNet for Real-Time Semantic Segmentation on High-Resolution Imagescited by 261
  3. 2017LinkNet: Exploiting Encoder Representations for Efficient Semantic Segmentationcited by 214
  4. 2019High-Resolution Representations for Labeling Pixels and Regionscited by 211
  5. 2020A2D2: Audi Autonomous Driving Datasetcited by 190
  6. 2018OCNet: Object Context Network for Scene Parsingcited by 140
  7. 2019Fast-SCNN: Fast Semantic Segmentation Networkcited by 125
  8. 2017Augmented Reality Meets Computer Vision : Efficient Data Generation for Urban Driving Scenescited by 122
  9. 20183D Point Capsule Networkscited by 106
  10. 20163D Shape Segmentation with Projective Convolutional Networkscited by 63
  11. 2019Attention Convolutional Binary Neural Tree for Fine-Grained Visual Categorizationcited by 51
  12. 2016Beyond Holistic Object Recognition: Enriching Image Understanding with Part Statescited by 13
  13. 2017FieldSAFE: Dataset for Obstacle Detection in Agriculturecited by 6

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 1; 2022: 4; 2023: 2; 2024: 6; 2025: 1; 2026: 4.

18 papers.

Sort:

By area:

  1. 2023The GOOSE Dataset for Perception in Unstructured Environmentscited by 37
  2. 2023WildScenes: A Benchmark for 2D and 3D Semantic Segmentation in Large-scale Natural Environmentscited by 17
  3. 2024Excavating in the Wild: The GOOSE-Ex Dataset for Semantic Segmentationcited by 13
  4. 2024Autonomous Driving in Unstructured Environments: How Far Have We Come?cited by 7
  5. 2026Vision as Unified Multimodal Generationcited by 7
  6. 2021Navigation-Oriented Scene Understanding for Robotic Autonomy: Learning to Segment Driveability in Egocentric Imagescited by 6
  7. 2022TAS-NIR: A VIS+NIR Dataset for Fine-grained Semantic Segmentation in Unstructured Outdoor Environmentscited by 5
  8. 2022Trans2k: Unlocking the Power of Deep Models for Transparent Object Trackingcited by 4
  9. 2024A New Dataset and a Distractor-Aware Architecture for Transparent Object Trackingcited by 4
  10. 2024Global-Local Similarity for Efficient Fine-Grained Image Recognition with Vision Transformerscited by 4
  11. 2024Survey on Datasets for Perception in Unstructured Outdoor Environmentscited by 3
  12. 2022Uncertainty-aware Perception Models for Off-road Autonomous Unmanned Ground Vehiclescited by 1
6 more
  1. 2026How to Relieve Distribution Shifts in Semantic Segmentation for Off-Road Environmentscited by 1
  2. 2022Leveraging Road Area Semantic Segmentation with Auxiliary Steering Taskcited by 0
  3. 2024A Performance Increment Strategy for Semantic Segmentation of Low-Resolution Images from Damaged Roadscited by 0
  4. 2025Knowledge Distillation for Semantic Segmentation: A Label Space Unification Approachcited by 0
  5. 2026ForestSim: A Synthetic Benchmark for Intelligent Vehicle Perception in Unstructured Forest Environmentscited by 0
  6. 2026Which Terrain Is Better? Preference Learning with VLM Prototypes for Off-Road Traversability Rankingcited by 0