paper-with-me

홈 › Papers

A Unified Variational Framework for Deep Weakly Supervised Image Segmentation

2026-07-22 · Yin King Chu, Lingfeng Li, Sung Ha Kang, Jianping Zhang, Xue-Cheng Tai arxiv

We propose a unified variational framework for image segmentation under sparse pixel-level supervision. Our method is based on a simplex-constrained Potts model with a smooth perimeter regularizer, yielding a convex, smooth energy functional that can be used as a training loss in weakly supervised deep learning paradigms or optimized efficiently using iterative methods. Sparse labels are incorporated into the data fidelity term by constructing a fuzzy membership function via a function extension problem in a Reproducing Kernel Hilbert Space (RKHS), which can effectively capture inhomogeneous intensity statistics. The derived discrete loss for training standard networks demonstrates robustness and consistent improvements over non-training and partial cross-entropy (PCE) baselines in experiments, achieving comparable performance without requiring ground-truth segmentation images.

📄 PDF Abstract BibTeX arXiv:2607.19669

Code (0)

등록된 구현이 없습니다.

Tasks

Image Segmentation

Similar Papers 제목 키워드 기반

CaCL: Class-aware Codebook Learning for Weakly Supervised Segmentation on Diffuse Image Patterns

2020-11-02 · Ruining Deng, Quan Liu, Shunxing Bao, Aadarsh Jha 외

Weakly supervised learning has been rapidly advanced in biomedical image analysis to achieve pixel-wise labels (segmentation) from image-wise annotations (classification), as biomedical images naturally contain image-wis…

Image ReconstructionSegmentationWeakly-supervised LearningWeakly supervised segmentation

Variational Weakly Supervised Sentiment Analysis with Posterior Regularization

2021-04-18 · EACL 2021 2 · Ziqian Zeng, Yangqiu Song

Sentiment analysis is an important task in natural language processing (NLP). Most of existing state-of-the-art methods are under the supervised learning paradigm. However, human annotations can be scarce. Thus, we shoul…

Sentiment Analysis

Audio Event and Scene Recognition: A Unified Approach using Strongly and Weakly Labeled Data

2016-11-12 · Anurag Kumar, Bhiksha Raj

In this paper we propose a novel learning framework called Supervised and Weakly Supervised Learning where the goal is to learn simultaneously from weakly and strongly labeled data. Strongly labeled data can be simply un…

Scene RecognitionWeakly-supervised Learning

Weakly-supervised anomaly detection for multimodal data distributions

2024-06-13 · Xu Tan, Junqi Chen, Sylwan Rahardja, Jiawei Yang 외

Weakly-supervised anomaly detection can outperform existing unsupervised methods with the assistance of a very small number of labeled anomalies, which attracts increasing attention from researchers. However, existing we…

Anomaly DetectionSupervised Anomaly DetectionWeakly-supervised Anomaly Detection

Weakly supervised marine animal detection from remote sensing images using vector-quantized variational autoencoder

2023-07-13 · Minh-Tan Pham, Hugo Gangloff, Sébastien Lefèvre

This paper studies a reconstruction-based approach for weakly-supervised animal detection from aerial images in marine environments. Such an approach leverages an anomaly detection framework that computes metrics directl…

Anomaly DetectionAnomaly Localization