Exploring Scene Affinity for Semi-Supervised LiDAR Semantic Segmentation

• URL: http://arxiv.org/abs/2408.11280v3
• Date: Tue, 01 Apr 2025 11:31:12 GMT
• Title: Exploring Scene Affinity for Semi-Supervised LiDAR Semantic Segmentation
• Authors: Chuandong Liu, Xingxing Weng, Shuguo Jiang, Pengcheng Li, Lei Yu, Gui-Song Xia,
• Abstract summary: This paper explores scene affinity, namely intra-scene consistency and inter-scene correlation, for semi-supervised LiDAR semantic segmentation in driving scenes.<n>Adopting teacher-student training, AIScene employs a teacher network to generate pseudo-labeled scenes from unlabeled data, which then supervise the student network's learning.<n>Experiments show that AIScene outperforms previous methods on two popular benchmarks across four settings, achieving notable improvements of 1.9% and 2.1% in the most challenging 1% labeled data.
• Score: 28.480775624544478
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: This paper explores scene affinity (AIScene), namely intra-scene consistency and inter-scene correlation, for semi-supervised LiDAR semantic segmentation in driving scenes. Adopting teacher-student training, AIScene employs a teacher network to generate pseudo-labeled scenes from unlabeled data, which then supervise the student network's learning. Unlike most methods that include all points in pseudo-labeled scenes for forward propagation but only pseudo-labeled points for backpropagation, AIScene removes points without pseudo-labels, ensuring consistency in both forward and backward propagation within the scene. This simple point erasure strategy effectively prevents unsupervised, semantically ambiguous points (excluded in backpropagation) from affecting the learning of pseudo-labeled points. Moreover, AIScene incorporates patch-based data augmentation, mixing multiple scenes at both scene and instance levels. Compared to existing augmentation techniques that typically perform scene-level mixing between two scenes, our method enhances the semantic diversity of labeled (or pseudo-labeled) scenes, thereby improving the semi-supervised performance of segmentation models. Experiments show that AIScene outperforms previous methods on two popular benchmarks across four settings, achieving notable improvements of 1.9% and 2.1% in the most challenging 1% labeled data.

Related papers

• Co-Training with Active Contrastive Learning and Meta-Pseudo-Labeling on 2D Projections for Deep Semi-Supervised Learning [42.56511266791916]
  SSL tackles this challenge by capitalizing on scarce labeled and abundant unlabeled data. We present active-DeepFA, a method that effectively combines CL, teacher-student-based meta-pseudo-labeling and AL.
  arXiv  Detail & Related papers  (2025-04-25T19:41:45Z)
• SemiETS: Integrating Spatial and Content Consistencies for Semi-Supervised End-to-end Text Spotting [59.14029549151904]
  We propose a new Semi-supervised framework for End-to-end Text Spotting, namely SemiETS. Specifically, it gradually generates reliable hierarchical pseudo labels for each task, thereby reducing noisy labels. It extracts important information in locations and transcriptions from bidirectional flows to improve consistency.
  arXiv  Detail & Related papers  (2025-04-14T08:09:17Z)
• Scribble Hides Class: Promoting Scribble-Based Weakly-Supervised Semantic Segmentation with Its Class Label [16.745019028033518]
  We propose a class-driven scribble promotion network, which utilizes both scribble annotations and pseudo-labels informed by image-level classes and global semantics for supervision. Experiments on the ScribbleSup dataset with different qualities of scribble annotations outperform all the previous methods, demonstrating the superiority and robustness of our method.
  arXiv  Detail & Related papers  (2024-02-27T14:51:56Z)
• TagCLIP: A Local-to-Global Framework to Enhance Open-Vocabulary Multi-Label Classification of CLIP Without Training [29.431698321195814]
  Contrastive Language-Image Pre-training (CLIP) has demonstrated impressive capabilities in open-vocabulary classification. CLIP shows poor performance on multi-label datasets because the global feature tends to be dominated by the most prominent class. We propose a local-to-global framework to obtain image tags.
  arXiv  Detail & Related papers  (2023-12-20T08:15:40Z)
• Pseudo-label Alignment for Semi-supervised Instance Segmentation [67.9616087910363]
  Pseudo-labeling is significant for semi-supervised instance segmentation. In existing pipelines, pseudo-labels that contain valuable information may be filtered out due to mismatches in class and mask quality. We propose a novel framework, called pseudo-label aligning instance segmentation (PAIS), in this paper.
  arXiv  Detail & Related papers  (2023-08-10T05:56:53Z)
• STRAP: Structured Object Affordance Segmentation with Point Supervision [20.56373848741831]
  We study affordance segmentation with point supervision, wherein the setting inherits an unexplored dual affinity-spatial affinity and label affinity. We devise a dense prediction network that enhances label relations by effectively densifying labels in a new domain. In experiments, we benchmark our method on the challenging CAD120 dataset, showing significant performance gains over prior methods.
  arXiv  Detail & Related papers  (2023-04-17T17:59:49Z)
• Dense FixMatch: a simple semi-supervised learning method for pixel-wise prediction tasks [68.36996813591425]
  We propose Dense FixMatch, a simple method for online semi-supervised learning of dense and structured prediction tasks. We enable the application of FixMatch in semi-supervised learning problems beyond image classification by adding a matching operation on the pseudo-labels. Dense FixMatch significantly improves results compared to supervised learning using only labeled data, approaching its performance with 1/4 of the labeled samples.
  arXiv  Detail & Related papers  (2022-10-18T15:02:51Z)
• LESS: Label-Efficient Semantic Segmentation for LiDAR Point Clouds [62.49198183539889]
  We propose a label-efficient semantic segmentation pipeline for outdoor scenes with LiDAR point clouds. Our method co-designs an efficient labeling process with semi/weakly supervised learning. Our proposed method is even highly competitive compared to the fully supervised counterpart with 100% labels.
  arXiv  Detail & Related papers  (2022-10-14T19:13:36Z)
• Unsupervised Domain Adaptation with Implicit Pseudo Supervision for Semantic Segmentation [7.748333539159297]
  We train the model by the pseudo labels which are implicitly produced by itself to learn new complementary knowledge about target domain. Experiments on GTA5 to Cityscapes and SYNTHIA to Cityscapes tasks show that the proposed method has considerable improvements.
  arXiv  Detail & Related papers  (2022-04-14T04:06:22Z)
• Adversarial Dual-Student with Differentiable Spatial Warping for Semi-Supervised Semantic Segmentation [70.2166826794421]
  We propose a differentiable geometric warping to conduct unsupervised data augmentation. We also propose a novel adversarial dual-student framework to improve the Mean-Teacher. Our solution significantly improves the performance and state-of-the-art results are achieved on both datasets.
  arXiv  Detail & Related papers  (2022-03-05T17:36:17Z)
• Scaling up Multi-domain Semantic Segmentation with Sentence Embeddings [81.09026586111811]
  We propose an approach to semantic segmentation that achieves state-of-the-art supervised performance when applied in a zero-shot setting. This is achieved by replacing each class label with a vector-valued embedding of a short paragraph that describes the class. The resulting merged semantic segmentation dataset of over 2 Million images enables training a model that achieves performance equal to that of state-of-the-art supervised methods on 7 benchmark datasets.
  arXiv  Detail & Related papers  (2022-02-04T07:19:09Z)
• GuidedMix-Net: Semi-supervised Semantic Segmentation by Using Labeled Images as Reference [90.5402652758316]
  We propose a novel method for semi-supervised semantic segmentation named GuidedMix-Net. It uses labeled information to guide the learning of unlabeled instances. It achieves competitive segmentation accuracy and significantly improves the mIoU by +7$%$ compared to previous approaches.
  arXiv  Detail & Related papers  (2021-12-28T06:48:03Z)
• Improving Semi-Supervised and Domain-Adaptive Semantic Segmentation with Self-Supervised Depth Estimation [94.16816278191477]
  We present a framework for semi-adaptive and domain-supervised semantic segmentation. It is enhanced by self-supervised monocular depth estimation trained only on unlabeled image sequences. We validate the proposed model on the Cityscapes dataset.
  arXiv  Detail & Related papers  (2021-08-28T01:33:38Z)
• Semi-Supervised Semantic Segmentation with Cross Pseudo Supervision [56.950950382415925]
  We propose a novel consistency regularization approach, called cross pseudo supervision (CPS) The CPS consistency has two roles: encourage high similarity between the predictions of two perturbed networks for the same input image, and expand training data by using the unlabeled data with pseudo labels. Experiment results show that our approach achieves the state-of-the-art semi-supervised segmentation performance on Cityscapes and PASCAL VOC 2012.
  arXiv  Detail & Related papers  (2021-06-02T15:21:56Z)

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.