Class-Level Confidence Based 3D Semi-Supervised Learning

• URL: http://arxiv.org/abs/2210.10138v1
• Date: Tue, 18 Oct 2022 20:13:28 GMT
• Title: Class-Level Confidence Based 3D Semi-Supervised Learning
• Authors: Zhimin Chen, Longlong Jing, Liang Yang, Bing Li
• Abstract summary: We show that unlabeled data class-level confidence can represent the learning status in the 3D imbalanced dataset. Our method significantly outperforms state-of-the-art counterparts for both 3D SSL classification and detection tasks.
• Score: 18.95161296147023
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Recent state-of-the-art method FlexMatch firstly demonstrated that correctly estimating learning status is crucial for semi-supervised learning (SSL). However, the estimation method proposed by FlexMatch does not take into account imbalanced data, which is the common case for 3D semi-supervised learning. To address this problem, we practically demonstrate that unlabeled data class-level confidence can represent the learning status in the 3D imbalanced dataset. Based on this finding, we present a novel class-level confidence based 3D SSL method. Firstly, a dynamic thresholding strategy is proposed to utilize more unlabeled data, especially for low learning status classes. Then, a re-sampling strategy is designed to avoid biasing toward high learning status classes, which dynamically changes the sampling probability of each class. To show the effectiveness of our method in 3D SSL tasks, we conduct extensive experiments on 3D SSL classification and detection tasks. Our method significantly outperforms state-of-the-art counterparts for both 3D SSL classification and detection tasks in all datasets.

Related papers

• DyConfidMatch: Dynamic Thresholding and Re-sampling for 3D Semi-supervised Learning [4.259908158892314]
  Semi-supervised learning (SSL) leverages limited labeled and abundant unlabeled data but often faces challenges with data imbalance. This study investigates class-level confidence as an indicator of learning status in 3D SSL, proposing a novel method that utilizes dynamic thresholding. A re-sampling strategy is also introduced to mitigate bias towards well-represented classes, ensuring equitable class representation.
  arXiv  Detail & Related papers  (2024-11-13T05:09:28Z)
• Class-Imbalanced Semi-Supervised Learning for Large-Scale Point Cloud Semantic Segmentation via Decoupling Optimization [64.36097398869774]
  Semi-supervised learning (SSL) has been an active research topic for large-scale 3D scene understanding. The existing SSL-based methods suffer from severe training bias due to class imbalance and long-tail distributions of the point cloud data. We introduce a new decoupling optimization framework, which disentangles feature representation learning and classifier in an alternative optimization manner to shift the bias decision boundary effectively.
  arXiv  Detail & Related papers  (2024-01-13T04:16:40Z)
• Semi-Supervised Class-Agnostic Motion Prediction with Pseudo Label Regeneration and BEVMix [59.55173022987071]
  We study the potential of semi-supervised learning for class-agnostic motion prediction. Our framework adopts a consistency-based self-training paradigm, enabling the model to learn from unlabeled data. Our method exhibits comparable performance to weakly and some fully supervised methods.
  arXiv  Detail & Related papers  (2023-12-13T09:32:50Z)
• How To Overcome Confirmation Bias in Semi-Supervised Image Classification By Active Learning [2.1805442504863506]
  We present three data challenges common in real-world applications: between-class imbalance, within-class imbalance, and between-class similarity. We find that random sampling does not mitigate confirmation bias and, in some cases, leads to worse performance than supervised learning. Our results provide insights into the potential of combining active and semi-supervised learning in the presence of common real-world challenges.
  arXiv  Detail & Related papers  (2023-08-16T08:52:49Z)
• Rethinking Self-Supervised Visual Representation Learning in Pre-training for 3D Human Pose and Shape Estimation [57.206129938611454]
  Self-supervised representation learning (SSL) methods have outperformed the ImageNet classification pre-training for vision tasks such as object detection. We empirically study and analyze the effects of SSL and compare it with other pre-training alternatives for 3DHPSE. Our observations challenge the naive application of the current SSL pre-training to 3DHPSE and relight the value of other data types in the pre-training aspect.
  arXiv  Detail & Related papers  (2023-03-09T16:17:52Z)
• Open-Set Semi-Supervised Learning for 3D Point Cloud Understanding [62.17020485045456]
  It is commonly assumed in semi-supervised learning (SSL) that the unlabeled data are drawn from the same distribution as that of the labeled ones. We propose to selectively utilize unlabeled data through sample weighting, so that only conducive unlabeled data would be prioritized.
  arXiv  Detail & Related papers  (2022-05-02T16:09:17Z)
• Understanding the Challenges When 3D Semantic Segmentation Faces Class Imbalanced and OOD Data [4.503636381237414]
  3D semantic segmentation is an essential process in the creation of a safe autonomous driving system. Deep learning models for 3D semantic segmentation often suffer from the class imbalance problem and out-of-distribution data. In this study, we explore how the class imbalance problem affects 3DSS performance and whether the model can detect the category prediction correctness.
  arXiv  Detail & Related papers  (2022-03-01T03:53:18Z)
• Generative Zero-Shot Learning for Semantic Segmentation of 3D Point Cloud [79.99653758293277]
  We present the first generative approach for both Zero-Shot Learning (ZSL) and Generalized ZSL (GZSL) on 3D data. We show that it reaches or outperforms the state of the art on ModelNet40 classification for both inductive ZSL and inductive GZSL. Our experiments show that our method outperforms strong baselines, which we additionally propose for this task.
  arXiv  Detail & Related papers  (2021-08-13T13:29:27Z)
• Adversarial Self-Supervised Learning for Semi-Supervised 3D Action Recognition [123.62183172631443]
  We present Adversarial Self-Supervised Learning (ASSL), a novel framework that tightly couples SSL and the semi-supervised scheme. Specifically, we design an effective SSL scheme to improve the discrimination capability of learned representations for 3D action recognition.
  arXiv  Detail & Related papers  (2020-07-12T08:01:06Z)

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.