2D Feature Distillation for Weakly- and Semi-Supervised 3D Semantic Segmentation

• URL: http://arxiv.org/abs/2311.15605v1
• Date: Mon, 27 Nov 2023 07:57:29 GMT
• Title: 2D Feature Distillation for Weakly- and Semi-Supervised 3D Semantic Segmentation
• Authors: Ozan Unal, Dengxin Dai, Lukas Hoyer, Yigit Baran Can, Luc Van Gool
• Abstract summary: 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.
• Score: 92.17700318483745
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: As 3D perception problems grow in popularity and the need for large-scale labeled datasets for LiDAR semantic segmentation increase, new methods arise that aim to reduce the necessity for dense annotations by employing weakly-supervised training. However these methods continue to show weak boundary estimation and high false negative rates for small objects and distant sparse regions. We argue that such weaknesses can be compensated by using RGB images which provide a denser representation of the scene. 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. We further utilize a one-way contrastive learning scheme alongside a novel mixing strategy called FOVMix, to combat the horizontal field-of-view mismatch between the two sensors and enhance the effects of image guidance. 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, while introducing no additional annotation burden or computational/memory cost during inference. Furthermore, we show that our contributions also prove effective for semi-supervised training, where IGNet claims state-of-the-art results on both ScribbleKITTI and SemanticKITTI.

Related papers

• Weakly Supervised LiDAR Semantic Segmentation via Scatter Image Annotation [38.715754110667916]
  We implement LiDAR semantic segmentation using scatter image annotation. We also propose ScatterNet, a network that includes three pivotal strategies to reduce the performance gap. Our method requires less than 0.02% of the labeled points to achieve over 95% of the performance of fully-supervised methods.
  arXiv  Detail & Related papers  (2024-04-19T13:01:30Z)
• 3D Medical Image Segmentation with Sparse Annotation via Cross-Teaching between 3D and 2D Networks [26.29122638813974]
  We propose a framework that can robustly learn from sparse annotation using the cross-teaching of both 3D and 2D networks. Our experimental results on the MMWHS dataset demonstrate that our method outperforms the state-of-the-art (SOTA) semi-supervised segmentation methods.
  arXiv  Detail & Related papers  (2023-07-30T15:26:17Z)
• On Triangulation as a Form of Self-Supervision for 3D Human Pose Estimation [57.766049538913926]
  Supervised approaches to 3D pose estimation from single images are remarkably effective when labeled data is abundant. Much of the recent attention has shifted towards semi and (or) weakly supervised learning. We propose to impose multi-view geometrical constraints by means of a differentiable triangulation and to use it as form of self-supervision during training when no labels are available.
  arXiv  Detail & Related papers  (2022-03-29T19:11:54Z)
• Activation to Saliency: Forming High-Quality Labels for Unsupervised Salient Object Detection [54.92703325989853]
  We propose a two-stage Activation-to-Saliency (A2S) framework that effectively generates high-quality saliency cues. No human annotations are involved in our framework during the whole training process. Our framework reports significant performance compared with existing USOD methods.
  arXiv  Detail & Related papers  (2021-12-07T11:54:06Z)
• 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)
• Semi-supervised Left Atrium Segmentation with Mutual Consistency Training [60.59108570938163]
  We propose a novel Mutual Consistency Network (MC-Net) for semi-supervised left atrium segmentation from 3D MR images. Our MC-Net consists of one encoder and two slightly different decoders, and the prediction discrepancies of two decoders are transformed as an unsupervised loss. We evaluate our MC-Net on the public Left Atrium (LA) database and it obtains impressive performance gains by exploiting the unlabeled data effectively.
  arXiv  Detail & Related papers  (2021-03-04T09:34:32Z)
• Semantics-Driven Unsupervised Learning for Monocular Depth and Ego-Motion Estimation [33.83396613039467]
  We propose a semantics-driven unsupervised learning approach for monocular depth and ego-motion estimation from videos. Recent unsupervised learning methods employ photometric errors between synthetic view and actual image as a supervision signal for training.
  arXiv  Detail & Related papers  (2020-06-08T05:55:07Z)

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.