paper-with-me

홈 › Papers

MRIFE: A Mask-Recovering and Interactive-Feature-Enhancing Semantic Segmentation Network For Relic Landslide Detection

2024-11-26 · Juefei He, Yuexing Peng, Wei Li, Junchuan Yu, Daqing Ge, Wei Xiang

Relic landslide, formed over a long period, possess the potential for reactivation, making them a hazardous geological phenomenon. While reliable relic landslide detection benefits the effective monitoring and prevention of landslide disaster, semantic segmentation using high-resolution remote sensing images for relic landslides faces many challenges, including the object visual blur problem, due to the changes of appearance caused by prolonged natural evolution and human activities, and the small-sized dataset problem, due to difficulty in recognizing and labelling the samples. To address these challenges, a semantic segmentation model, termed mask-recovering and interactive-feature-enhancing (MRIFE), is proposed for more efficient feature extraction and separation. Specifically, a contrastive learning and mask reconstruction method with locally significant feature enhancement is proposed to improve the ability to distinguish between the target and background and represent landslide semantic features. Meanwhile, a dual-branch interactive feature enhancement architecture is used to enrich the extracted features and address the issue of visual ambiguity. Self-distillation learning is introduced to leverage the feature diversity both within and between samples for contrastive learning, improving sample utilization, accelerating model convergence, and effectively addressing the problem of the small-sized dataset. The proposed MRIFE is evaluated on a real relic landslide dataset, and experimental results show that it greatly improves the performance of relic landslide detection. For the semantic segmentation task, compared to the baseline, the precision increases from 0.4226 to 0.5347, the mean intersection over union (IoU) increases from 0.6405 to 0.6680, the landslide IoU increases from 0.3381 to 0.3934, and the F1-score increases from 0.5054 to 0.5646.

📄 PDF Abstract BibTeX arXiv:2411.17167

Code (0)

등록된 구현이 없습니다.

Tasks

Contrastive LearningSemantic Segmentation

Methods 이 논문이 사용한 방법론

Contrastive Learning 설명 없음
ReLIC ReLIC, or Representation Learning via Invariant Causal Mechanisms, is a self-supervised learning objective that enforces invariant prediction of proxy targets across…

Similar Papers 제목 키워드 기반

Segment and Matte Anything in a Unified Model

2026-01-17 · Zezhong Fan, Xiaohan Li, Topojoy Biswas, Kaushiki Nag 외 arxiv

Segment Anything (SAM) has recently pushed the boundaries of segmentation by demonstrating zero-shot generalization and flexible prompting after training on over one billion masks. Despite this, its mask prediction accur…

Zero-shot GeneralizationImage SegmentationImage Matting

CtrlFuse: Mask-Prompt Guided Controllable Infrared and Visible Image Fusion

2026-01-12 · Yiming Sun, Yuan Ruan, Qinghua Hu, Pengfei Zhu arxiv

Infrared and visible image fusion generates all-weather perception-capable images by combining complementary modalities, enhancing environmental awareness for intelligent unmanned systems. Existing methods either focus o…

Mask-GVAE: Blind Denoising Graphs via Partition

2021-02-08 · Jia Li, Mengzhou Liu, Honglei Zhang, Pengyun Wang 외

We present Mask-GVAE, a variational generative model for blind denoising large discrete graphs, in which "blind denoising" means we don't require any supervision from clean graphs. We focus on recovering graph structures…

Denoising

AskToAct: Enhancing LLMs Tool Use via Self-Correcting Clarification

2025-03-03 · Xuan Zhang, Yongliang Shen, Zhe Zheng, Linjuan Wu 외

Large language models (LLMs) have demonstrated remarkable capabilities in tool learning. In real-world scenarios, user queries are often ambiguous and incomplete, requiring effective clarification. However, existing inte…

SAM3D-Phys: Towards Multi-Object Interactive Simulation in Real World

2026-05-28 · Xin Dong, Weijian Deng, Lihan Zhang, Tianru Dai 외 arxiv

This work addresses the problem of recovering complete, simulatable object geometry from reconstructed real-world scenes, enabling physics-based interaction with objects embedded in the scene. While modern multi-view rec…