paper-with-me

홈 › Papers

Rethinking Video Segmentation with Masked Video Consistency: Did the Model Learn as Intended?

2024-08-20 · Chen Liang, Qiang Guo, Xiaochao Qu, Luoqi Liu, Ting Liu

Video segmentation aims at partitioning video sequences into meaningful segments based on objects or regions of interest within frames. Current video segmentation models are often derived from image segmentation techniques, which struggle to cope with small-scale or class-imbalanced video datasets. This leads to inconsistent segmentation results across frames. To address these issues, we propose a training strategy Masked Video Consistency, which enhances spatial and temporal feature aggregation. MVC introduces a training strategy that randomly masks image patches, compelling the network to predict the entire semantic segmentation, thus improving contextual information integration. Additionally, we introduce Object Masked Attention (OMA) to optimize the cross-attention mechanism by reducing the impact of irrelevant queries, thereby enhancing temporal modeling capabilities. Our approach, integrated into the latest decoupled universal video segmentation framework, achieves state-of-the-art performance across five datasets for three video segmentation tasks, demonstrating significant improvements over previous methods without increasing model parameters.

📄 PDF Abstract BibTeX arXiv:2408.10627

Code (0)

등록된 구현이 없습니다.

Tasks

Image SegmentationSegmentationSemantic SegmentationVideo SegmentationVideo Semantic Segmentation

Methods 이 논문이 사용한 방법론

Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Attention 설명 없음

Similar Papers 제목 키워드 기반

Semantic Segmentation on VSPW Dataset through Masked Video Consistency

2024-06-07 · Chen Liang, Qiang Guo, Chongkai Yu, Chengjing Wu 외

Pixel-level Video Understanding requires effectively integrating three-dimensional data in both spatial and temporal dimensions to learn accurate and stable semantic information from continuous frames. However, existing …

Semantic SegmentationVideo Understanding

MATIS: Masked-Attention Transformers for Surgical Instrument Segmentation

2023-03-16 · Nicolás Ayobi, Alejandra Pérez-Rondón, Santiago Rodríguez, Pablo Arbeláez

We propose Masked-Attention Transformers for Surgical Instrument Segmentation (MATIS), a two-stage, fully transformer-based method that leverages modern pixel-wise attention mechanisms for instrument segmentation. MATIS …

Segmentation

Motion-Saliency Complementary Masked Modeling for Point Cloud Video Understanding

2026-08-31 · Wei Wang, Yiding Sun, Yuyan Wang, Zhuoyue Zhang 외 arxiv

Point cloud video representation learning is crucial for 3D dynamic scene understanding. In this paper, we propose MoSaiC, a novel Motion-Saliency Complementary masked modeling framework for self-supervised point cloud v…

Representation LearningSemantic SegmentationScene UnderstandingAction Segmentation

VideoMAC: Video Masked Autoencoders Meet ConvNets

2024-02-29 · CVPR 2024 1 · Gensheng Pei, Tao Chen, Xiruo Jiang, Huafeng Liu 외

Recently, the advancement of self-supervised learning techniques, like masked autoencoders (MAE), has greatly influenced visual representation learning for images and videos. Nevertheless, it is worth noting that the pre…

Pose TrackingRepresentation LearningSelf-Supervised LearningSemantic Segmentation+2

Masked Video Distillation: Rethinking Masked Feature Modeling for Self-supervised Video Representation Learning

2022-12-08 · CVPR 2023 1 · Rui Wang, Dongdong Chen, Zuxuan Wu, Yinpeng Chen 외

Benefiting from masked visual modeling, self-supervised video representation learning has achieved remarkable progress. However, existing methods focus on learning representations from scratch through reconstructing low-…

Action ClassificationAction RecognitionRepresentation LearningSelf-Supervised Action Recognition