https://github.com/mostafajahanifar/nuclick_torch
NuClick: A Deep Learning Framework for Interactive Segmentation of Microscopy Images
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
Instance Segmentation is a computer vision task that involves identifying and separating individual objects within an image, including detecting the boundaries of each object and assigning a unique label to each object. The goal of instance segmentation is to produce a pixel-wise segmentation map of the image, where each pixel is assigned to a specific object instance.
Image Credit: Deep Occlusion-Aware Instance Segmentation with Overlapping BiLayers, CVPR'21
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
NuClick: A Deep Learning Framework for Interactive Segmentation of Microscopy Images
Nuclei instance segmentation and classification in histopathology images with StarDist
UNet++: Redesigning Skip Connections to Exploit Multiscale Features in Image Segmentation
Multi-Task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semantics
Towards End-to-End Lane Detection: an Instance Segmentation Approach
MSeg: A Composite Dataset for Multi-domain Semantic Segmentation
Swin Transformer: Hierarchical Vision Transformer using Shifted Windows
HS-ResNet: Hierarchical-Split Block on Convolutional Neural Network
Swin Transformer: Hierarchical Vision Transformer using Shifted Windows
PolyLoss: A Polynomial Expansion Perspective of Classification Loss Functions
Swin Transformer: Hierarchical Vision Transformer using Shifted Windows
An Energy and GPU-Computation Efficient Backbone Network for Real-Time Object Detection
TernausNetV2: Fully Convolutional Network for Instance Segmentation
HoughNet: Integrating near and long-range evidence for visual detection
CSA-Net: Channel-wise Spatially Autocorrelated Attention Networks
Masked-attention Mask Transformer for Universal Image Segmentation
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.