Real-Time Semantic Segmentation
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 0
- 평가표
- 8
- 보존된 평가 기록
- 108
Semantic Segmentation is a computer vision task that involves assigning a semantic label to each pixel in an image. In Real-Time Semantic Segmentation, the goal is to perform this labeling quickly and accurately in real-time, allowing for the segmentation results to be used for tasks such as object recognition, scene understanding, and autonomous navigation.
<span style="color:grey; opacity: 0.6">( Image credit: TorchSeg )</span>
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/renhaa/semantic-diffusion
BiSeNet: Bilateral Segmentation Network for Real-time Semantic Segmentation
https://github.com/reshalfahsi/NanoNet
NanoNet: Real-Time Polyp Segmentation in Video Capsule Endoscopy and Colonoscopy
https://github.com/reshalfahsi/NanoNet-PyTorch
NanoNet: Real-Time Polyp Segmentation in Video Capsule Endoscopy and Colonoscopy
https://github.com/retis-ai/patchattacktool
https://github.com/rickyHong/FCN-segmentation-repl
https://github.com/robin-chan/decision-rules
Full-Resolution Residual Networks for Semantic Segmentation in Street Scenes
https://github.com/rotemgoren/segNet
SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation
https://github.com/rudolfsteiner/fast_scnn
https://github.com/s9mondal9upriti/Segnet
SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation
https://github.com/sacmehta/3d-espnet
ESPNet: Efficient Spatial Pyramid of Dilated Convolutions for Semantic Segmentation
https://github.com/sacmehta/espnetv2-coreml
ESPNetv2: A Light-weight, Power Efficient, and General Purpose Convolutional Neural Network
https://github.com/sadeepj/crfasrnn_keras
https://github.com/sadeepj/crfasrnn_pytorch
https://github.com/sagieppel/Focusing-attention-of-Fully-convolutional-neural-networks-on-Region-of-interest-ROI-input-map-
https://github.com/sagieppel/Fully-convolutional-neural-network-FCN-for-semantic-segmentation-Tensorflow-implementation
https://github.com/sahadevpoudel/hardnet-mseg
https://github.com/shanglianlm0525/CvPytorch
SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation
https://github.com/shekkizh/FCN.tensorflow
https://github.com/shelhamer/fcn.berkeleyvision.org
https://github.com/simuler/ESPNet
ESPNet: Efficient Spatial Pyramid of Dilated Convolutions for Semantic Segmentation
https://github.com/sithu31296/semantic-segmentation
https://github.com/soumik12345/Enet
ENet: A Deep Neural Network Architecture for Real-Time Semantic Segmentation
https://github.com/soumik12345/Enet-Tensorflow
ENet: A Deep Neural Network Architecture for Real-Time Semantic Segmentation
https://github.com/srihari-humbarwadi/ENet-A-Deep-Neural-Network-Architecture-for-Real-Time-Semantic-Segmentation
ENet: A Deep Neural Network Architecture for Real-Time Semantic Segmentation
https://github.com/srihari-humbarwadi/Multi-Scale-Context-Aggregation-by-Dilated-Convolutions
https://github.com/srihari-humbarwadi/RefineNet-Multi-Path-Refinement-Networks-for-High-Resolution-Semantic-Segmentation
ENet: A Deep Neural Network Architecture for Real-Time Semantic Segmentation
https://github.com/stuartchen1949/segnet_paddle
SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation
https://github.com/switchablenorms/SwitchNorm_Segmentation
https://github.com/tahaemara/LiteSeg
LiteSeg: A Novel Lightweight ConvNet for Semantic Segmentation
https://github.com/talshaharabany/DeepACM2D
https://github.com/tejaswigowda/semseg-pytorch
https://github.com/tensorflow/models
Semantic Image Segmentation with Deep Convolutional Nets and Fully Connected CRFs
https://github.com/tensorflow/models/tree/master/research/deeplab
Semantic Image Segmentation with Deep Convolutional Nets and Fully Connected CRFs
https://github.com/tkuanlun350/Tensorflow-SegNet
SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation
https://github.com/trhieu310/customDataset
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.