DINOSTAR: Deep Iterative Neural Object Detector Self-Supervised Training for Roadside LiDAR Applications

• URL: http://arxiv.org/abs/2501.17076v1
• Date: Tue, 28 Jan 2025 17:01:42 GMT
• Title: DINOSTAR: Deep Iterative Neural Object Detector Self-Supervised Training for Roadside LiDAR Applications
• Authors: Muhammad Shahbaz, Shaurya Agarwal,
• Abstract summary: This paper develops an end-to-end, scalable, and self-supervised framework for training deep object detectors tailored for roadside point-cloud data. It is presented that by training the student model over the combined noisy annotations from multitude of teachers, it enhances its capacity to discern background/foreground more effectively. The evaluations, involving publicly available roadside datasets and state-of-art deep object detectors, demonstrate that the proposed framework achieves comparable performance to deep object detectors trained on human-annotated labels.
• Score: 1.675857332621569
• License:
• Abstract: Recent advancements in deep-learning methods for object detection in point-cloud data have enabled numerous roadside applications, fostering improvements in transportation safety and management. However, the intricate nature of point-cloud data poses significant challenges for human-supervised labeling, resulting in substantial expenditures of time and capital. This paper addresses the issue by developing an end-to-end, scalable, and self-supervised framework for training deep object detectors tailored for roadside point-cloud data. The proposed framework leverages self-supervised, statistically modeled teachers to train off-the-shelf deep object detectors, thus circumventing the need for human supervision. The teacher models follow fine-tuned set standard practices of background filtering, object clustering, bounding-box fitting, and classification to generate noisy labels. It is presented that by training the student model over the combined noisy annotations from multitude of teachers enhances its capacity to discern background/foreground more effectively and forces it to learn diverse point-cloud-representations for object categories of interest. The evaluations, involving publicly available roadside datasets and state-of-art deep object detectors, demonstrate that the proposed framework achieves comparable performance to deep object detectors trained on human-annotated labels, despite not utilizing such human-annotations in its training process.

Related papers

• Exploiting Unlabeled Data with Multiple Expert Teachers for Open Vocabulary Aerial Object Detection and Its Orientation Adaptation [58.37525311718006]
  We put forth a novel formulation of the aerial object detection problem, namely open-vocabulary aerial object detection (OVAD) We propose CastDet, a CLIP-activated student-teacher detection framework that serves as the first OVAD detector specifically designed for the challenging aerial scenario. Our framework integrates a robust localization teacher along with several box selection strategies to generate high-quality proposals for novel objects.
  arXiv  Detail & Related papers  (2024-11-04T12:59:13Z)
• Deep Learning-Based Object Pose Estimation: A Comprehensive Survey [73.74933379151419]
  We discuss the recent advances in deep learning-based object pose estimation. Our survey also covers multiple input data modalities, degrees-of-freedom of output poses, object properties, and downstream tasks.
  arXiv  Detail & Related papers  (2024-05-13T14:44:22Z)
• Label-Efficient 3D Object Detection For Road-Side Units [10.663986706501188]
  Collaborative perception can enhance the perception of autonomous vehicles via deep information fusion with intelligent roadside units (RSU) The data-hungry nature of these methods creates a major hurdle for their real-world deployment, particularly due to the need for annotated RSU data. We devise a label-efficient object detection method for RSU based on unsupervised object discovery.
  arXiv  Detail & Related papers  (2024-04-09T12:29:16Z)
• Proposal-Contrastive Pretraining for Object Detection from Fewer Data [11.416621957617334]
  We present Proposal Selection Contrast (ProSeCo), a novel unsupervised overall pretraining approach. ProSeCo uses the large number of object proposals generated by the detector for contrastive learning. We show that our method outperforms state of the art in unsupervised pretraining for object detection on standard and novel benchmarks.
  arXiv  Detail & Related papers  (2023-10-25T17:59:26Z)
• Towards End-to-End Unsupervised Saliency Detection with Self-Supervised Top-Down Context [25.85453873366275]
  We propose a self-supervised end-to-end salient object detection framework via top-down context. We exploit the self-localization from the deepest feature to construct the location maps which are then leveraged to learn the most instructive segmentation guidance. Our method achieves leading performance among the recent end-to-end methods and most of the multi-stage solutions.
  arXiv  Detail & Related papers  (2023-10-14T08:43:22Z)
• Improved Region Proposal Network for Enhanced Few-Shot Object Detection [23.871860648919593]
  Few-shot object detection (FSOD) methods have emerged as a solution to the limitations of classic object detection approaches. We develop a semi-supervised algorithm to detect and then utilize unlabeled novel objects as positive samples during the FSOD training stage. Our improved hierarchical sampling strategy for the region proposal network (RPN) also boosts the perception of the object detection model for large objects.
  arXiv  Detail & Related papers  (2023-08-15T02:35:59Z)
• Weakly-supervised Contrastive Learning for Unsupervised Object Discovery [52.696041556640516]
  Unsupervised object discovery is promising due to its ability to discover objects in a generic manner. We design a semantic-guided self-supervised learning model to extract high-level semantic features from images. We introduce Principal Component Analysis (PCA) to localize object regions.
  arXiv  Detail & Related papers  (2023-07-07T04:03:48Z)
• A Survey of Label-Efficient Deep Learning for 3D Point Clouds [109.07889215814589]
  This paper presents the first comprehensive survey of label-efficient learning of point clouds. We propose a taxonomy that organizes label-efficient learning methods based on the data prerequisites provided by different types of labels. For each approach, we outline the problem setup and provide an extensive literature review that showcases relevant progress and challenges.
  arXiv  Detail & Related papers  (2023-05-31T12:54:51Z)
• Incremental-DETR: Incremental Few-Shot Object Detection via Self-Supervised Learning [60.64535309016623]
  We propose the Incremental-DETR that does incremental few-shot object detection via fine-tuning and self-supervised learning on the DETR object detector. To alleviate severe over-fitting with few novel class data, we first fine-tune the class-specific components of DETR with self-supervision. We further introduce a incremental few-shot fine-tuning strategy with knowledge distillation on the class-specific components of DETR to encourage the network in detecting novel classes without catastrophic forgetting.
  arXiv  Detail & Related papers  (2022-05-09T05:08:08Z)
• Few-Cost Salient Object Detection with Adversarial-Paced Learning [95.0220555274653]
  This paper proposes to learn the effective salient object detection model based on the manual annotation on a few training images only. We name this task as the few-cost salient object detection and propose an adversarial-paced learning (APL)-based framework to facilitate the few-cost learning scenario.
  arXiv  Detail & Related papers  (2021-04-05T14:15:49Z)
• Co-training for On-board Deep Object Detection [0.0]
  Best performing deep vision-based object detectors are trained in a supervised manner by relying on human-labeled bounding boxes. Co-training is a semi-supervised learning method for self-labeling objects in unlabeled images. We show how co-training is a paradigm worth to pursue for alleviating object labeling, working both alone and together with task-agnostic domain adaptation.
  arXiv  Detail & Related papers  (2020-08-12T19:08:59Z)

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.