paper-with-me

홈 › Papers

Shift-Memory Network for Temporal Scene Segmentation

2022-02-17 · Guo Cheng, Jiang Yu Zheng

Semantic segmentation has achieved great accuracy in understanding spatial layout. For real-time tasks based on dynamic scenes, we extend semantic segmentation in temporal domain to enhance the spatial accuracy with motion. We utilize a shift-mode network over streaming input to ensure zero-latency output. For the data overlap under shifting network, this paper identifies repeated computation in fixed periods across network layers. To avoid this redundancy, we derive a Shift-Memory Network (SMN) from encoding-decoding baseline to reuse the network values without accuracy loss. Trained in patch-mode, the SMN extracts the network parameters for SMN to perform inference promptly in compact memory. We segment dynamic scenes from 1D scanning input and 2D video. The experiments of SMN achieve equivalent accuracy as shift-mode but in faster inference speeds and much smaller memory. This will facilitate semantic segmentation in real-time application on edge devices.

📄 PDF Abstract BibTeX arXiv:2202.08399

Code (0)

등록된 구현이 없습니다.

Tasks

Scene SegmentationSegmentationSemantic Segmentation

Similar Papers 제목 키워드 기반

Class-Agnostic Visio-Temporal Scene Sketch Semantic Segmentation

2024-09-30 · Aleyna Kütük, Tevfik Metin Sezgin

Scene sketch semantic segmentation is a crucial task for various applications including sketch-to-image retrieval and scene understanding. Existing sketch segmentation methods treat sketches as bitmap images, leading to …

Image RetrievalScene UnderstandingSegmentationSemantic Segmentation

Exploiting Temporal State Space Sharing for Video Semantic Segmentation

2025-03-26 · CVPR 2025 1 · Syed Ariff Syed Hesham, Yun Liu, Guolei Sun, Henghui Ding 외

Video semantic segmentation (VSS) plays a vital role in understanding the temporal evolution of scenes. Traditional methods often segment videos frame-by-frame or in a short temporal window, leading to limited temporal c…

MambaSemantic SegmentationState Space ModelsVideo Semantic Segmentation

Memory Matters: Convolutional Recurrent Neural Network for Scene Text Recognition

2016-01-06 · Guo Qiang, Tu Dan, Li Guohui, Lei Jun

Text recognition in natural scene is a challenging problem due to the many factors affecting text appearance. In this paper, we presents a method that directly transcribes scene text images to text without needing of sop…

Scene Text RecognitionSegmentation

TEDi: Temporal Memory-Enhanced and Denoising Transformer for Surgical Instrument Segmentation

2026-09-15 · Jiahong Yuan, Weiming Mi, Tao Zhang, Haoyin Zhou arxiv

Query-based segmentation methods have shown promising potential for surgical instrument segmentation and recognition, which is essential for scene understanding and downstream tasks in computer assisted surgery. However,…

Scene Understanding

MemorySeg: Online LiDAR Semantic Segmentation with a Latent Memory

2023-11-02 · ICCV 2023 1 · Enxu Li, Sergio Casas, Raquel Urtasun

Semantic segmentation of LiDAR point clouds has been widely studied in recent years, with most existing methods focusing on tackling this task using a single scan of the environment. However, leveraging the temporal stre…

LIDAR Semantic SegmentationSegmentationSemantic Segmentation