PCT: Perspective Cue Training Framework for Multi-Camera BEV Segmentation

• URL: http://arxiv.org/abs/2403.12530v2
• Date: Mon, 15 Jul 2024 13:59:23 GMT
• Title: PCT: Perspective Cue Training Framework for Multi-Camera BEV Segmentation
• Authors: Haruya Ishikawa, Takumi Iida, Yoshinori Konishi, Yoshimitsu Aoki,
• Abstract summary: Cue Perspective Training (PCT) is a novel training framework that utilizes pseudo-labels generated from unlabeled perspective images. PCT can be applied to various settings where unlabeled data is available.
• Score: 6.429761894240062
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Generating annotations for bird's-eye-view (BEV) segmentation presents significant challenges due to the scenes' complexity and the high manual annotation cost. In this work, we address these challenges by leveraging the abundance of unlabeled data available. We propose the Perspective Cue Training (PCT) framework, a novel training framework that utilizes pseudo-labels generated from unlabeled perspective images using publicly available semantic segmentation models trained on large street-view datasets. PCT applies a perspective view task head to the image encoder shared with the BEV segmentation head, effectively utilizing the unlabeled data to be trained with the generated pseudo-labels. Since image encoders are present in nearly all camera-based BEV segmentation architectures, PCT is flexible and applicable to various existing BEV architectures. PCT can be applied to various settings where unlabeled data is available. In this paper, we applied PCT for semi-supervised learning (SSL) and unsupervised domain adaptation (UDA). Additionally, we introduce strong input perturbation through Camera Dropout (CamDrop) and feature perturbation via BEV Feature Dropout (BFD), which are crucial for enhancing SSL capabilities using our teacher-student framework. Our comprehensive approach is simple and flexible but yields significant improvements over various baselines for SSL and UDA, achieving competitive performances even against the current state-of-the-art.

Related papers

• BEVPose: Unveiling Scene Semantics through Pose-Guided Multi-Modal BEV Alignment [8.098296280937518]
  We present BEVPose, a framework that integrates BEV representations from camera and lidar data, using sensor pose as a guiding supervisory signal. By leveraging pose information, we align and fuse multi-modal sensory inputs, facilitating the learning of latent BEV embeddings that capture both geometric and semantic aspects of the environment.
  arXiv  Detail & Related papers  (2024-10-28T12:40:27Z)
• Physically Feasible Semantic Segmentation [58.17907376475596]
  State-of-the-art semantic segmentation models are typically optimized in a data-driven fashion. Our method, Physically Feasible Semantic (PhyFea), extracts explicit physical constraints that govern spatial class relations. PhyFea yields significant performance improvements in mIoU over each state-of-the-art network we use.
  arXiv  Detail & Related papers  (2024-08-26T22:39:08Z)
• Point-In-Context: Understanding Point Cloud via In-Context Learning [67.20277182808992]
  We introduce Point-In-Context (PIC), a novel framework for 3D point cloud understanding via in-context learning. We address the technical challenge of effectively extending masked point modeling to 3D point clouds by introducing a Joint Sampling module. We propose two novel training strategies, In-Context Labeling and In-Context Enhancing, forming an extended version of PIC named Point-In-Context-Segmenter (PIC-S)
  arXiv  Detail & Related papers  (2024-04-18T17:32:32Z)
• Few-Shot Panoptic Segmentation With Foundation Models [23.231014713335664]
  We propose to leverage task-agnostic image features to enable few-shot panoptic segmentation by presenting Segmenting Panoptic Information with Nearly 0 labels (SPINO) In detail, our method combines a DINOv2 backbone with lightweight network heads for semantic segmentation and boundary estimation. We show that our approach, albeit being trained with only ten annotated images, predicts high-quality pseudo-labels that can be used with any existing panoptic segmentation method.
  arXiv  Detail & Related papers  (2023-09-19T16:09:01Z)
• CSP: Self-Supervised Contrastive Spatial Pre-Training for Geospatial-Visual Representations [90.50864830038202]
  We present Contrastive Spatial Pre-Training (CSP), a self-supervised learning framework for geo-tagged images. We use a dual-encoder to separately encode the images and their corresponding geo-locations, and use contrastive objectives to learn effective location representations from images. CSP significantly boosts the model performance with 10-34% relative improvement with various labeled training data sampling ratios.
  arXiv  Detail & Related papers  (2023-05-01T23:11:18Z)
• Towards Automated Polyp Segmentation Using Weakly- and Semi-Supervised Learning and Deformable Transformers [8.01814397869811]
  Polyp segmentation is a crucial step towards computer-aided diagnosis of colorectal cancer. Most of the polyp segmentation methods require pixel-wise annotated datasets. We propose a novel framework that can be trained using only weakly annotated images along with exploiting unlabeled images.
  arXiv  Detail & Related papers  (2022-11-21T20:44:12Z)
• Panoramic Panoptic Segmentation: Insights Into Surrounding Parsing for Mobile Agents via Unsupervised Contrastive Learning [93.6645991946674]
  We introduce panoramic panoptic segmentation, as the most holistic scene understanding. A complete surrounding understanding provides a maximum of information to a mobile agent. We propose a framework which allows model training on standard pinhole images and transfers the learned features to a different domain.
  arXiv  Detail & Related papers  (2022-06-21T20:07:15Z)
• Semi-weakly Supervised Contrastive Representation Learning for Retinal Fundus Images [0.2538209532048867]
  We propose a semi-weakly supervised contrastive learning framework for representation learning using semi-weakly annotated images. We empirically validate the transfer learning performance of SWCL on seven public retinal fundus datasets.
  arXiv  Detail & Related papers  (2021-08-04T15:50:09Z)
• Towards Unsupervised Sketch-based Image Retrieval [126.77787336692802]
  We introduce a novel framework that simultaneously performs unsupervised representation learning and sketch-photo domain alignment. Our framework achieves excellent performance in the new unsupervised setting, and performs comparably or better than state-of-the-art in the zero-shot setting.
  arXiv  Detail & Related papers  (2021-05-18T02:38:22Z)
• Reducing the Annotation Effort for Video Object Segmentation Datasets [50.893073670389164]
  densely labeling every frame with pixel masks does not scale to large datasets. We use a deep convolutional network to automatically create pseudo-labels on a pixel level from much cheaper bounding box annotations. We obtain the new TAO-VOS benchmark, which we make publicly available at www.vision.rwth-aachen.de/page/taovos.
  arXiv  Detail & Related papers  (2020-11-02T17:34:45Z)

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.