Learning Maritime Obstacle Detection from Weak Annotations by Scaffolding

• URL: http://arxiv.org/abs/2108.00564v1
• Date: Sun, 1 Aug 2021 23:37:57 GMT
• Title: Learning Maritime Obstacle Detection from Weak Annotations by Scaffolding
• Authors: Lojze \v{Z}ust, Matej Kristan
• Abstract summary: Coastal water autonomous boats rely on robust perception methods for obstacle detection and timely collision avoidance. Per-pixel ground truth labeling of such datasets is labor-intensive and expensive. We propose a new scaffolding learning regime that allows training obstacle detection segmentation networks only from such weak annotations.
• Score: 15.80122710743313
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Coastal water autonomous boats rely on robust perception methods for obstacle detection and timely collision avoidance. The current state-of-the-art is based on deep segmentation networks trained on large datasets. Per-pixel ground truth labeling of such datasets, however, is labor-intensive and expensive. We observe that far less information is required for practical obstacle avoidance - the location of water edge on static obstacles like shore and approximate location and bounds of dynamic obstacles in the water is sufficient to plan a reaction. We propose a new scaffolding learning regime (SLR) that allows training obstacle detection segmentation networks only from such weak annotations, thus significantly reducing the cost of ground-truth labeling. Experiments show that maritime obstacle segmentation networks trained using SLR substantially outperform the same networks trained with dense ground truth labels. Thus accuracy is not sacrificed for labelling simplicity but is in fact improved, which is a remarkable result.

Related papers

• A Universal Railway Obstacle Detection System based on Semi-supervised Segmentation And Optical Flow [1.450405446885067]
  We reformulate the task as a binary segmentation problem instead of the traditional object detection approach. To mitigate data shortages, we generate highly realistic synthetic images using Segment Anything (SAM) and YOLO. We leverage optical flow as prior knowledge to train the model effectively.
  arXiv  Detail & Related papers  (2024-06-27T05:48:26Z)
• 2D Feature Distillation for Weakly- and Semi-Supervised 3D Semantic Segmentation [92.17700318483745]
  We propose an image-guidance network (IGNet) which builds upon the idea of distilling high level feature information from a domain adapted synthetically trained 2D semantic segmentation network. IGNet achieves state-of-the-art results for weakly-supervised LiDAR semantic segmentation on ScribbleKITTI, boasting up to 98% relative performance to fully supervised training with only 8% labeled points.
  arXiv  Detail & Related papers  (2023-11-27T07:57:29Z)
• Leveraging point annotations in segmentation learning with boundary loss [2.7874893928375917]
  This paper investigates the combination of intensity-based distance maps with boundary loss for point-supervised semantic segmentation. By design the boundary loss imposes a stronger penalty on the false positives the farther away from the object they occur. We perform experiments on two multi-class datasets; ACDC (heart segmentation) and POEM (whole-body abdominal organ segmentation)
  arXiv  Detail & Related papers  (2023-11-06T21:18:39Z)
• Histogram Layer Time Delay Neural Networks for Passive Sonar Classification [58.720142291102135]
  A novel method combines a time delay neural network and histogram layer to incorporate statistical contexts for improved feature learning and underwater acoustic target classification. The proposed method outperforms the baseline model, demonstrating the utility in incorporating statistical contexts for passive sonar target recognition.
  arXiv  Detail & Related papers  (2023-07-25T19:47:26Z)
• Certified Interpretability Robustness for Class Activation Mapping [77.58769591550225]
  We present CORGI, short for Certifiably prOvable Robustness Guarantees for Interpretability mapping. CORGI is an algorithm that takes in an input image and gives a certifiable lower bound for the robustness of its CAM interpretability map. We show the effectiveness of CORGI via a case study on traffic sign data, certifying lower bounds on the minimum adversarial perturbation.
  arXiv  Detail & Related papers  (2023-01-26T18:58:11Z)
• Learning with Weak Annotations for Robust Maritime Obstacle Detection [10.773819584718648]
  Maritime obstacle detection is crucial for safe navigation of autonomous boats. Per-pixel ground truth labeling of such datasets is labor-intensive and expensive. We propose a new scaffolding learning regime ( SLR) to train segmentation-based obstacle detection networks. SLR trains an initial model from weak annotations, then alternates between re-estimating the segmentation pseudo labels and improving the network parameters.
  arXiv  Detail & Related papers  (2022-06-27T12:52:26Z)
• Temporal Context for Robust Maritime Obstacle Detection [10.773819584718648]
  We propose WaSR-T, a novel maritime obstacle detection network. By learning the local temporal characteristics of object reflection on the water surface, WaSR-T substantially improves obstacle detection accuracy. Compared with existing single-frame methods, WaSR-T reduces the number of false positive detections by 41% overall and by over 53% within the danger zone of the boat.
  arXiv  Detail & Related papers  (2022-03-10T12:58:14Z)
• Context-Preserving Instance-Level Augmentation and Deformable Convolution Networks for SAR Ship Detection [50.53262868498824]
  Shape deformation of targets in SAR image due to random orientation and partial information loss is an essential challenge in SAR ship detection. We propose a data augmentation method to train a deep network that is robust to partial information loss within the targets.
  arXiv  Detail & Related papers  (2022-02-14T07:01:01Z)
• 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)
• MODS -- A USV-oriented object detection and obstacle segmentation benchmark [12.356257470551348]
  We introduce a new obstacle detection benchmark MODS, which considers two major perception tasks: maritime object detection and the more general maritime obstacle segmentation. We present a new diverse maritime evaluation dataset containing approximately 81k stereo images synchronized with an on-board IMU, with over 60k objects annotated. We propose a new obstacle segmentation performance evaluation protocol that reflects the detection accuracy in a way meaningful for practical USV navigation.
  arXiv  Detail & Related papers  (2021-05-05T22:40:27Z)
• Mixed-Privacy Forgetting in Deep Networks [114.3840147070712]
  We show that the influence of a subset of the training samples can be removed from the weights of a network trained on large-scale image classification tasks. Inspired by real-world applications of forgetting techniques, we introduce a novel notion of forgetting in mixed-privacy setting. We show that our method allows forgetting without having to trade off the model accuracy.
  arXiv  Detail & Related papers  (2020-12-24T19:34:56Z)

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.