Semantic Segmentation based Scene Understanding in Autonomous Vehicles

• URL: http://arxiv.org/abs/2507.14303v1
• Date: Fri, 18 Jul 2025 18:21:47 GMT
• Title: Semantic Segmentation based Scene Understanding in Autonomous Vehicles
• Authors: Ehsan Rassekh,
• Abstract summary: We propose several efficient models to investigate scene understanding through semantic segmentation.<n>The obtained results show that choosing the appropriate backbone has a great effect on the performance of the model.<n>In the end, we analyze and evaluate the proposed models in terms of accuracy, mean IoU, and loss function, and the results show that these metrics are improved.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: In recent years, the concept of artificial intelligence (AI) has become a prominent keyword because it is promising in solving complex tasks. The need for human expertise in specific areas may no longer be needed because machines have achieved successful results using artificial intelligence and can make the right decisions in critical situations. This process is possible with the help of deep learning (DL), one of the most popular artificial intelligence technologies. One of the areas in which the use of DL is used is in the development of self-driving cars, which is very effective and important. In this work, we propose several efficient models to investigate scene understanding through semantic segmentation. We use the BDD100k dataset to investigate these models. Another contribution of this work is the usage of several Backbones as encoders for models. The obtained results show that choosing the appropriate backbone has a great effect on the performance of the model for semantic segmentation. Better performance in semantic segmentation allows us to understand better the scene and the environment around the agent. In the end, we analyze and evaluate the proposed models in terms of accuracy, mean IoU, and loss function, and the results show that these metrics are improved.

Related papers

• Efficient Machine Unlearning via Influence Approximation [75.31015485113993]
  Influence-based unlearning has emerged as a prominent approach to estimate the impact of individual training samples on model parameters without retraining.<n>This paper establishes a theoretical link between memorizing (incremental learning) and forgetting (unlearning)<n>We introduce the Influence Approximation Unlearning algorithm for efficient machine unlearning from the incremental perspective.
  arXiv  Detail & Related papers  (2025-07-31T05:34:27Z)
• A Data-Centric Revisit of Pre-Trained Vision Models for Robot Learning [67.72413262980272]
  Pre-trained vision models (PVMs) are fundamental to modern robotics, yet their optimal configuration remains unclear.<n>We develop SlotMIM, a method that induces object-centric representations by introducing a semantic bottleneck.<n>Our approach achieves significant improvements over prior work in image recognition, scene understanding, and robot learning evaluations.
  arXiv  Detail & Related papers  (2025-03-10T06:18:31Z)
• SegXAL: Explainable Active Learning for Semantic Segmentation in Driving Scene Scenarios [1.2172320168050466]
  We propose a novel Explainable Active Learning model, XAL-based semantic segmentation model "SegXAL" SegXAL can (i) effectively utilize the unlabeled data, (ii) facilitate the "Human-in-the-loop" paradigm, and (iii) augment the model decisions in an interpretable way. In particular, we investigate the application of the SegXAL model for semantic segmentation in driving scene scenarios.
  arXiv  Detail & Related papers  (2024-08-08T14:19:11Z)
• Explainable AI for Comparative Analysis of Intrusion Detection Models [20.683181384051395]
  This research analyzes various machine learning models to the tasks of binary and multi-class classification for intrusion detection from network traffic. We trained all models to the accuracy of 90% on the UNSW-NB15 dataset. We also discover that Random Forest provides the best performance in terms of accuracy, time efficiency and robustness.
  arXiv  Detail & Related papers  (2024-06-14T03:11:01Z)
• Towards Better Explanations for Object Detection [0.0]
  This paper proposes a method to explain the decision for any object detection model called D-CLOSE. We performed tests on the MS-COCO dataset with the YOLOX model, which shows that our method outperforms D-RISE.
  arXiv  Detail & Related papers  (2023-06-05T09:52:05Z)
• A Threefold Review on Deep Semantic Segmentation: Efficiency-oriented, Temporal and Depth-aware design [77.34726150561087]
  We conduct a survey on the most relevant and recent advances in Deep Semantic in the context of vision for autonomous vehicles. Our main objective is to provide a comprehensive discussion on the main methods, advantages, limitations, results and challenges faced from each perspective.
  arXiv  Detail & Related papers  (2023-03-08T01:29:55Z)
• Learning Action-Effect Dynamics for Hypothetical Vision-Language Reasoning Task [50.72283841720014]
  We propose a novel learning strategy that can improve reasoning about the effects of actions. We demonstrate the effectiveness of our proposed approach and discuss its advantages over previous baselines in terms of performance, data efficiency, and generalization capability.
  arXiv  Detail & Related papers  (2022-12-07T05:41:58Z)
• Goal-driven Self-Attentive Recurrent Networks for Trajectory Prediction [31.02081143697431]
  Human trajectory forecasting is a key component of autonomous vehicles, social-aware robots and video-surveillance applications. We propose a lightweight attention-based recurrent backbone that acts solely on past observed positions. We employ a common goal module, based on a U-Net architecture, which additionally extracts semantic information to predict scene-compliant destinations.
  arXiv  Detail & Related papers  (2022-04-25T11:12:37Z)
• 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)
• ALT-MAS: A Data-Efficient Framework for Active Testing of Machine Learning Algorithms [58.684954492439424]
  We propose a novel framework to efficiently test a machine learning model using only a small amount of labeled test data. The idea is to estimate the metrics of interest for a model-under-test using Bayesian neural network (BNN)
  arXiv  Detail & Related papers  (2021-04-11T12:14:04Z)
• Reducing DNN Labelling Cost using Surprise Adequacy: An Industrial Case Study for Autonomous Driving [23.054842564447895]
  Deep Neural Networks (DNNs) are rapidly being adopted by the automotive industry, due to their impressive performance in tasks that are essential for autonomous driving. This paper shows how development of a DNN based object segmentation can be improved by exploiting the correlation between Surprise Adequacy (SA) and model performance. In our industrial case study the technique allows cost savings of up to 50% with negligible evaluation inaccuracy.
  arXiv  Detail & Related papers  (2020-05-29T06:33:55Z)

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.