https://github.com/zju-vipa/BKT
공식 코드Visual Boundary Knowledge Translation for Foreground Segmentation
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
Visual Boundary Knowledge Translation for Foreground Segmentation
Neural 3D Scene Reconstruction with the Manhattan-world Assumption
A Refreshed Similarity-based Upsampler for Direct High-Ratio Feature Upsampling
FusionU-Net: U-Net with Enhanced Skip Connection for Pathology Image Segmentation
SU-SAM: A Simple Unified Framework for Adapting Segment Anything Model in Underperformed Scenes
ASI-Seg: Audio-Driven Surgical Instrument Segmentation with Surgeon Intention Understanding
LayoutNet: Reconstructing the 3D Room Layout from a Single RGB Image
SGDraw: Scene Graph Drawing Interface Using Object-Oriented Representation
APAUNet: Axis Projection Attention UNet for Small Target in 3D Medical Segmentation
Point-SAM: Promptable 3D Segmentation Model for Point Clouds
Merging Context Clustering with Visual State Space Models for Medical Image Segmentation
Dynamic Scene Understanding through Object-Centric Voxelization and Neural Rendering
Directional Connectivity-based Segmentation of Medical Images
Event-Free Moving Object Segmentation from Moving Ego Vehicle
Panoramic Depth Estimation via Supervised and Unsupervised Learning in Indoor Scenes
SHREC 2022: pothole and crack detection in the road pavement using images and RGB-D data
Hierarchical Roofline Performance Analysis for Deep Learning Applications
Towards Cross-Disaster Building Damage Assessment with Graph Convolutional Networks
Semi-Supervised Learning for Multi-Task Scene Understanding by Neural Graph Consensus
Semi-Supervised Learning for Multi-Task Scene Understanding by Neural Graph Consensus
One model to use them all: Training a segmentation model with complementary datasets
Semi-Supervised Learning for Multi-Task Scene Understanding by Neural Graph Consensus
Pay Attention to Your Tone: Introducing a New Dataset for Polite Language Rewrite
Identifying the style by a qualified reader on a short fragment of generated poetry
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.