Unbiased Subclass Regularization for Semi-Supervised Semantic Segmentation

• URL: http://arxiv.org/abs/2203.10026v1
• Date: Fri, 18 Mar 2022 15:53:18 GMT
• Title: Unbiased Subclass Regularization for Semi-Supervised Semantic Segmentation
• Authors: Dayan Guan, Jiaxing Huang, Aoran Xiao, Shijian Lu
• Abstract summary: Semi-supervised semantic segmentation learns from small amounts of labelled images and large amounts of unlabelled images. This paper presents an unbiased subclass regularization network (USRN) that alleviates the class imbalance issue.
• Score: 47.533612505477535
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Semi-supervised semantic segmentation learns from small amounts of labelled images and large amounts of unlabelled images, which has witnessed impressive progress with the recent advance of deep neural networks. However, it often suffers from severe class-bias problem while exploring the unlabelled images, largely due to the clear pixel-wise class imbalance in the labelled images. This paper presents an unbiased subclass regularization network (USRN) that alleviates the class imbalance issue by learning class-unbiased segmentation from balanced subclass distributions. We build the balanced subclass distributions by clustering pixels of each original class into multiple subclasses of similar sizes, which provide class-balanced pseudo supervision to regularize the class-biased segmentation. In addition, we design an entropy-based gate mechanism to coordinate learning between the original classes and the clustered subclasses which facilitates subclass regularization effectively by suppressing unconfident subclass predictions. Extensive experiments over multiple public benchmarks show that USRN achieves superior performance as compared with the state-of-the-art.

Related papers

• LCGC: Learning from Consistency Gradient Conflicting for Class-Imbalanced Semi-Supervised Debiasing [7.868824589618853]
  We theoretically analyze why exploiting a baseline image can refine pseudo-labels and prove that the black image is the best choice. We propose a debiasing scheme dubbed LCGC, which Learning from Gradient Conflicting, by encouraging biased class predictions. LCGC can significantly improve the prediction accuracy of existing CISSL models on public benchmarks.
  arXiv  Detail & Related papers  (2025-04-09T02:57:53Z)
• Cluster-guided Contrastive Class-imbalanced Graph Classification [10.48026949398536]
  We propose C$3$GNN, which integrates the idea of clustering into contrastive learning to enhance class-imbalanced graph classification. C$3$GNN clusters graphs from each majority class into multiple subclasses, with sizes comparable to the minority class, mitigating class imbalance. supervised contrastive learning is used to hierarchically learn effective graph representations, enabling the model to thoroughly explore semantic substructures in majority classes.
  arXiv  Detail & Related papers  (2024-12-17T15:04:54Z)
• Tendency-driven Mutual Exclusivity for Weakly Supervised Incremental Semantic Segmentation [56.1776710527814]
  Weakly Incremental Learning for Semantic (WILSS) leverages a pre-trained segmentation model to segment new classes using cost-effective and readily available image-level labels. A prevailing way to solve WILSS is the generation of seed areas for each new class, serving as a form of pixel-level supervision. We propose an innovative, tendency-driven relationship of mutual exclusivity, meticulously tailored to govern the behavior of the seed areas.
  arXiv  Detail & Related papers  (2024-04-18T08:23:24Z)
• Subclass-balancing Contrastive Learning for Long-tailed Recognition [38.31221755013738]
  Long-tailed recognition with imbalanced class distribution naturally emerges in practical machine learning applications. We propose a novel subclass-balancing contrastive learning'' approach that clusters each head class into multiple subclasses of similar sizes as the tail classes. We evaluate SBCL over a list of long-tailed benchmark datasets and it achieves the state-of-the-art performance.
  arXiv  Detail & Related papers  (2023-06-28T05:08:43Z)
• Compound Batch Normalization for Long-tailed Image Classification [77.42829178064807]
  We propose a compound batch normalization method based on a Gaussian mixture. It can model the feature space more comprehensively and reduce the dominance of head classes. The proposed method outperforms existing methods on long-tailed image classification.
  arXiv  Detail & Related papers  (2022-12-02T07:31:39Z)
• Learning to Annotate Part Segmentation with Gradient Matching [58.100715754135685]
  This paper focuses on tackling semi-supervised part segmentation tasks by generating high-quality images with a pre-trained GAN. In particular, we formulate the annotator learning as a learning-to-learn problem. We show that our method can learn annotators from a broad range of labelled images including real images, generated images, and even analytically rendered images.
  arXiv  Detail & Related papers  (2022-11-06T01:29:22Z)
• One-Class Risk Estimation for One-Class Hyperspectral Image Classification [8.206701378422968]
  Hyperspectral imagery (HSI) one-class classification is aimed at identifying a single target class from the HSI. Deep learning-based methods are currently the mainstream to overcome distribution overlap in HSI multiclassification. In this article, a weakly supervised deep HSI one-class classification, HOneCls, is proposed.
  arXiv  Detail & Related papers  (2022-10-27T14:15:13Z)
• Prediction Calibration for Generalized Few-shot Semantic Segmentation [101.69940565204816]
  Generalized Few-shot Semantic (GFSS) aims to segment each image pixel into either base classes with abundant training examples or novel classes with only a handful of (e.g., 1-5) training images per class. We build a cross-attention module that guides the classifier's final prediction using the fused multi-level features. Our PCN outperforms the state-the-art alternatives by large margins.
  arXiv  Detail & Related papers  (2022-10-15T13:30:12Z)
• Exploring Smoothness and Class-Separation for Semi-supervised Medical Image Segmentation [39.068698033394064]
  We propose the SS-Net for semi-supervised medical image segmentation tasks. pixel-level smoothness forces the model to generate invariant results under adversarial perturbations. The inter-class separation constrains individual class features should approach their corresponding high-quality prototypes.
  arXiv  Detail & Related papers  (2022-03-02T08:38:09Z)
• Boosting few-shot classification with view-learnable contrastive learning [19.801016732390064]
  We introduce contrastive loss into few-shot classification for learning latent fine-grained structure in the embedding space. We develop a learning-to-learn algorithm to automatically generate different views of the same image.
  arXiv  Detail & Related papers  (2021-07-20T03:13:33Z)
• No Subclass Left Behind: Fine-Grained Robustness in Coarse-Grained Classification Problems [20.253644336965042]
  In real-world classification tasks, each class often comprises multiple finer-grained "subclasses" As the subclass labels are frequently unavailable, models trained using only the coarser-grained class labels often exhibit highly variable performance across different subclasses. We propose GEORGE, a method to both measure and mitigate hidden stratification even when subclass labels are unknown.
  arXiv  Detail & Related papers  (2020-11-25T18:50:32Z)
• M2m: Imbalanced Classification via Major-to-minor Translation [79.09018382489506]
  In most real-world scenarios, labeled training datasets are highly class-imbalanced, where deep neural networks suffer from generalizing to a balanced testing criterion. In this paper, we explore a novel yet simple way to alleviate this issue by augmenting less-frequent classes via translating samples from more-frequent classes. Our experimental results on a variety of class-imbalanced datasets show that the proposed method improves the generalization on minority classes significantly compared to other existing re-sampling or re-weighting methods.
  arXiv  Detail & Related papers  (2020-04-01T13:21:17Z)

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.