EPContrast: Effective Point-level Contrastive Learning for Large-scale Point Cloud Understanding

• URL: http://arxiv.org/abs/2410.17207v1
• Date: Tue, 22 Oct 2024 17:27:16 GMT
• Title: EPContrast: Effective Point-level Contrastive Learning for Large-scale Point Cloud Understanding
• Authors: Zhiyi Pan, Guoqing Liu, Wei Gao, Thomas H. Li,
• Abstract summary: This paper proposes an Effective Point-level Contrastive Learning method for large-scale point cloud understanding dubbed textbfEPContrast EPContrast constructs positive and negative pairs based on asymmetric embedding, while ChannelContrast imposes contrastive supervision between channel feature maps. The efficacy of EPContrast is substantiated through comprehensive validation on S3DIS and ScanNetV2, encompassing tasks such as semantic segmentation, instance segmentation, and object detection.
• Score: 27.596165112950935
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The acquisition of inductive bias through point-level contrastive learning holds paramount significance in point cloud pre-training. However, the square growth in computational requirements with the scale of the point cloud poses a substantial impediment to the practical deployment and execution. To address this challenge, this paper proposes an Effective Point-level Contrastive Learning method for large-scale point cloud understanding dubbed \textbf{EPContrast}, which consists of AGContrast and ChannelContrast. In practice, AGContrast constructs positive and negative pairs based on asymmetric granularity embedding, while ChannelContrast imposes contrastive supervision between channel feature maps. EPContrast offers point-level contrastive loss while concurrently mitigating the computational resource burden. The efficacy of EPContrast is substantiated through comprehensive validation on S3DIS and ScanNetV2, encompassing tasks such as semantic segmentation, instance segmentation, and object detection. In addition, rich ablation experiments demonstrate remarkable bias induction capabilities under label-efficient and one-epoch training settings.

Related papers

• ICP-4D: Bridging Iterative Closest Point and LiDAR Panoptic Segmentation [44.68614934602709]
  ICP-4D is a training-free framework that unifies spatial and temporal reasoning through geometric relations among instance-level point sets.<n>To stabilize association under noisy instance predictions, we introduce a Sinkhorn-based soft matching.<n>Our experiments across both SemanticKITTI and panoptic nuScenes demonstrate that our method consistently outperforms state-of-the-art approaches.
  arXiv  Detail & Related papers  (2025-12-22T03:13:08Z)
• Generalizing Supervised Contrastive learning: A Projection Perspective [0.9208007322096533]
  We introduce ProjNCE, a generalization of the InfoNCE loss that unifies supervised and self-supervised contrastive objectives.<n>We show that ProjNCE consistently outperforms both SupCon and standard cross-entropy training.
  arXiv  Detail & Related papers  (2025-06-11T14:49:43Z)
• PseudoNeg-MAE: Self-Supervised Point Cloud Learning using Conditional Pseudo-Negative Embeddings [55.55445978692678]
  PseudoNeg-MAE is a self-supervised learning framework that enhances global feature representation of point cloud mask autoencoders. We show that PseudoNeg-MAE achieves state-of-the-art performance on the ModelNet40 and ScanObjectNN datasets.
  arXiv  Detail & Related papers  (2024-09-24T07:57:21Z)
• Skeleton Supervised Airway Segmentation [27.65479179170118]
  We introduce a novel skeleton-level annotation (SkA) tailored to the airway, which simplifies the annotation workflow. We also propose a skeleton-supervised learning framework to achieve accurate airway segmentation. Experiments reveal that our proposed framework outperforms the competing methods with SKA, which amounts to only 1.96% airways.
  arXiv  Detail & Related papers  (2024-03-11T08:37:03Z)
• Joint Learning for Scattered Point Cloud Understanding with Hierarchical Self-Distillation [34.26170741722835]
  We propose an end-to-end architecture that compensates for and identifies partial point clouds on the fly. hierarchical self-distillation (HSD) can be applied to arbitrary hierarchy-based point cloud methods.
  arXiv  Detail & Related papers  (2023-12-28T08:51:04Z)
• Synergistic Anchored Contrastive Pre-training for Few-Shot Relation Extraction [4.7220779071424985]
  Few-shot Relation Extraction (FSRE) aims to extract facts from a sparse set of labeled corpora. Recent studies have shown promising results in FSRE by employing Pre-trained Language Models. We introduce a novel synergistic anchored contrastive pre-training framework.
  arXiv  Detail & Related papers  (2023-12-19T10:16:24Z)
• Enhancing Few-shot CLIP with Semantic-Aware Fine-Tuning [61.902254546858465]
  Methods based on Contrastive Language-Image Pre-training have exhibited promising performance in few-shot adaptation tasks. We propose fine-tuning the parameters of the attention pooling layer during the training process to encourage the model to focus on task-specific semantics.
  arXiv  Detail & Related papers  (2023-11-08T05:18:57Z)
• BEVContrast: Self-Supervision in BEV Space for Automotive Lidar Point Clouds [73.40883276013373]
  We present a surprisingly simple and efficient method for self-supervision of 3D backbone on automotive Lidar point clouds. We design a contrastive loss between features of Lidar scans captured in the same scene. Resulting cell-level representations offer a good trade-off between the point-level representations exploited in PointContrast and segment-level representations exploited in TARL.
  arXiv  Detail & Related papers  (2023-10-26T10:02:33Z)
• Point Contrastive Prediction with Semantic Clustering for Self-Supervised Learning on Point Cloud Videos [71.20376514273367]
  We propose a unified point cloud video self-supervised learning framework for object-centric and scene-centric data. Our method outperforms supervised counterparts on a wide range of downstream tasks.
  arXiv  Detail & Related papers  (2023-08-18T02:17:47Z)
• STS-CCL: Spatial-Temporal Synchronous Contextual Contrastive Learning for Urban Traffic Forecasting [4.947443433688782]
  This work employs the advanced contrastive learning and proposes a novel Spatial-Temporalous Contextual Contrastive Learning (STS-CCL) model. Experiments and evaluations demonstrate that building a predictor upon STS-CCL contrastive learning model gains superior performance than existing traffic forecasting benchmarks.
  arXiv  Detail & Related papers  (2023-07-05T03:47:28Z)
• PointACL:Adversarial Contrastive Learning for Robust Point Clouds Representation under Adversarial Attack [73.3371797787823]
  Adversarial contrastive learning (ACL) is considered an effective way to improve the robustness of pre-trained models. We present our robust aware loss function to train self-supervised contrastive learning framework adversarially. We validate our method, PointACL on downstream tasks, including 3D classification and 3D segmentation with multiple datasets.
  arXiv  Detail & Related papers  (2022-09-14T22:58:31Z)
• Guided Point Contrastive Learning for Semi-supervised Point Cloud Semantic Segmentation [90.2445084743881]
  We present a method for semi-supervised point cloud semantic segmentation to adopt unlabeled point clouds in training to boost the model performance. Inspired by the recent contrastive loss in self-supervised tasks, we propose the guided point contrastive loss to enhance the feature representation and model generalization ability.
  arXiv  Detail & Related papers  (2021-10-15T16:38:54Z)
• Unsupervised Scale-consistent Depth Learning from Video [131.3074342883371]
  We propose a monocular depth estimator SC-Depth, which requires only unlabelled videos for training. Thanks to the capability of scale-consistent prediction, we show that our monocular-trained deep networks are readily integrated into the ORB-SLAM2 system. The proposed hybrid Pseudo-RGBD SLAM shows compelling results in KITTI, and it generalizes well to the KAIST dataset without additional training.
  arXiv  Detail & Related papers  (2021-05-25T02:17:56Z)
• Deep Semantic Matching with Foreground Detection and Cycle-Consistency [103.22976097225457]
  We address weakly supervised semantic matching based on a deep network. We explicitly estimate the foreground regions to suppress the effect of background clutter. We develop cycle-consistent losses to enforce the predicted transformations across multiple images to be geometrically plausible and consistent.
  arXiv  Detail & Related papers  (2020-03-31T22:38:09Z)

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.