INTACT: Inducing Noise Tolerance through Adversarial Curriculum Training for LiDAR-based Safety-Critical Perception and Autonomy

• URL: http://arxiv.org/abs/2502.01896v1
• Date: Tue, 04 Feb 2025 00:02:16 GMT
• Title: INTACT: Inducing Noise Tolerance through Adversarial Curriculum Training for LiDAR-based Safety-Critical Perception and Autonomy
• Authors: Nastaran Darabi, Divake Kumar, Sina Tayebati, Amit Ranjan Trivedi,
• Abstract summary: We present a novel framework designed to enhance the robustness of deep neural networks (DNNs) against noisy LiDAR data. IntACT combines meta-learning with adversarial curriculum training (ACT) to address challenges posed by data corruption and sparsity in 3D point clouds. IntACT's effectiveness is demonstrated through comprehensive evaluations on object detection, tracking, and classification benchmarks.
• Score: 0.4124847249415279
• License:
• Abstract: In this work, we present INTACT, a novel two-phase framework designed to enhance the robustness of deep neural networks (DNNs) against noisy LiDAR data in safety-critical perception tasks. INTACT combines meta-learning with adversarial curriculum training (ACT) to systematically address challenges posed by data corruption and sparsity in 3D point clouds. The meta-learning phase equips a teacher network with task-agnostic priors, enabling it to generate robust saliency maps that identify critical data regions. The ACT phase leverages these saliency maps to progressively expose a student network to increasingly complex noise patterns, ensuring targeted perturbation and improved noise resilience. INTACT's effectiveness is demonstrated through comprehensive evaluations on object detection, tracking, and classification benchmarks using diverse datasets, including KITTI, Argoverse, and ModelNet40. Results indicate that INTACT improves model robustness by up to 20% across all tasks, outperforming standard adversarial and curriculum training methods. This framework not only addresses the limitations of conventional training strategies but also offers a scalable and efficient solution for real-world deployment in resource-constrained safety-critical systems. INTACT's principled integration of meta-learning and adversarial training establishes a new paradigm for noise-tolerant 3D perception in safety-critical applications. INTACT improved KITTI Multiple Object Tracking Accuracy (MOTA) by 9.6% (64.1% -> 75.1%) and by 12.4% under Gaussian noise (52.5% -> 73.7%). Similarly, KITTI mean Average Precision (mAP) rose from 59.8% to 69.8% (50% point drop) and 49.3% to 70.9% (Gaussian noise), highlighting the framework's ability to enhance deep learning model resilience in safety-critical object tracking scenarios.

Related papers

• Enhanced Intrusion Detection in IIoT Networks: A Lightweight Approach with Autoencoder-Based Feature Learning [0.0]
  Intrusion Detection Systems (IDS) are essential for identifying and preventing abnormal network behaviors and malicious activities. This research implements six innovative approaches to enhance IDS performance, including leveraging an autoencoder for dimensional reduction. We are the first to deploy our model on a Jetson Nano, achieving inference times of 0.185 ms for binary classification and 0.187 ms for multiclass classification.
  arXiv  Detail & Related papers  (2025-01-25T16:24:18Z)
• Enhancing IoT Network Security through Adaptive Curriculum Learning and XAI [0.3958317527488535]
  This study presents a scalable and lightweight curriculum learning framework enhanced with Explainable AI (XAI) techniques, including LIME. The proposed model employs novel neural network architecture utilized at every stage of Curriculum Learning to efficiently capture and focus on both short- and long-term temporal dependencies. Experimental results demonstrate 98% accuracy on CIC-IoV-2024 and CIC-APT-IIoT-2024 datasets and 97% on EDGE-IIoT.
  arXiv  Detail & Related papers  (2025-01-20T17:32:01Z)
• The Surprising Effectiveness of Test-Time Training for Abstract Reasoning [64.36534512742736]
  We investigate the effectiveness of test-time training (TTT) as a mechanism for improving models' reasoning capabilities. TTT significantly improves performance on ARC tasks, achieving up to 6x improvement in accuracy compared to base fine-tuned models. Our findings suggest that explicit symbolic search is not the only path to improved abstract reasoning in neural language models.
  arXiv  Detail & Related papers  (2024-11-11T18:59:45Z)
• A Scalable and Generalized Deep Learning Framework for Anomaly Detection in Surveillance Videos [0.47279903800557493]
  Anomaly detection in videos is challenging due to the complexity, noise, and diverse nature of activities such as violence, shoplifting, and vandalism. Existing approaches have struggled to apply deep learning models across different anomaly tasks without extensive retraining. A new DL framework is introduced in this study, consisting of three key components: transfer learning to enhance feature generalization, model fusion to improve feature representation, and multi-task classification. Empirical evaluations demonstrate the framework's effectiveness, achieving an accuracy of 97.99% on the RLVS dataset (violence detection), 83.59% on the UCF dataset (shoplifting detection
  arXiv  Detail & Related papers  (2024-07-17T22:41:12Z)
• Patch-Level Contrasting without Patch Correspondence for Accurate and Dense Contrastive Representation Learning [79.43940012723539]
  ADCLR is a self-supervised learning framework for learning accurate and dense vision representation. Our approach achieves new state-of-the-art performance for contrastive methods.
  arXiv  Detail & Related papers  (2023-06-23T07:38:09Z)
• Defense against adversarial attacks on deep convolutional neural networks through nonlocal denoising [1.3484794751207887]
  A nonlocal denoising method with different luminance values has been used to generate adversarial examples. Under perturbation, the method provided absolute accuracy improvements of up to 9.3% in the MNIST data set. We have shown that transfer learning is disadvantageous for adversarial machine learning.
  arXiv  Detail & Related papers  (2022-06-25T16:11:25Z)
• What Stops Learning-based 3D Registration from Working in the Real World? [53.68326201131434]
  This work identifies the sources of 3D point cloud registration failures, analyze the reasons behind them, and propose solutions. Ultimately, this translates to a best-practice 3D registration network (BPNet), constituting the first learning-based method able to handle previously-unseen objects in real-world data. Our model generalizes to real data without any fine-tuning, reaching an accuracy of up to 67% on point clouds of unseen objects obtained with a commercial sensor.
  arXiv  Detail & Related papers  (2021-11-19T19:24:27Z)
• G-DetKD: Towards General Distillation Framework for Object Detectors via Contrastive and Semantic-guided Feature Imitation [49.421099172544196]
  We propose a novel semantic-guided feature imitation technique, which automatically performs soft matching between feature pairs across all pyramid levels. We also introduce contrastive distillation to effectively capture the information encoded in the relationship between different feature regions. Our method consistently outperforms the existing detection KD techniques, and works when (1) components in the framework are used separately and in conjunction.
  arXiv  Detail & Related papers  (2021-08-17T07:44:27Z)
• Towards Reducing Labeling Cost in Deep Object Detection [61.010693873330446]
  We propose a unified framework for active learning, that considers both the uncertainty and the robustness of the detector. Our method is able to pseudo-label the very confident predictions, suppressing a potential distribution drift.
  arXiv  Detail & Related papers  (2021-06-22T16:53:09Z)
• Scalable End-to-End RF Classification: A Case Study on Undersized Dataset Regularization by Convolutional-MST [0.0]
  We present a new deep learning approach based on multistage training and demonstrate it on RF sensing signal classification. We consistently achieve over 99% accuracy for up to 17 diverse classes using only 11 samples per class for training, yielding up to 35% improvement in accuracy over standard DL approaches.
  arXiv  Detail & Related papers  (2021-04-25T08:41:52Z)
• How Robust are Randomized Smoothing based Defenses to Data Poisoning? [66.80663779176979]
  We present a previously unrecognized threat to robust machine learning models that highlights the importance of training-data quality. We propose a novel bilevel optimization-based data poisoning attack that degrades the robustness guarantees of certifiably robust classifiers. Our attack is effective even when the victim trains the models from scratch using state-of-the-art robust training methods.
  arXiv  Detail & Related papers  (2020-12-02T15:30:21Z)

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.