https://github.com/the-veeraraghavan-lab/smit
Self-supervised 3D anatomy segmentation using self-distilled masked image transformer (SMIT)
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
Self-supervised 3D anatomy segmentation using self-distilled masked image transformer (SMIT)
SemanticKITTI: A Dataset for Semantic Scene Understanding of LiDAR Sequences
ResUNet-a: a deep learning framework for semantic segmentation of remotely sensed data
Key Points Estimation and Point Instance Segmentation Approach for Lane Detection
ADVENT: Adversarial Entropy Minimization for Domain Adaptation in Semantic Segmentation
BiX-NAS: Searching Efficient Bi-directional Architecture for Medical Image Segmentation
XMem: Long-Term Video Object Segmentation with an Atkinson-Shiffrin Memory Model
U-Net: Convolutional Networks for Biomedical Image Segmentation
CrOC: Cross-View Online Clustering for Dense Visual Representation Learning
Unsupervised Meta-learning of Figure-Ground Segmentation via Imitating Visual Effects
Unsupervised Meta-learning of Figure-Ground Segmentation via Imitating Visual Effects
SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation
Self-Supervision with Superpixels: Training Few-shot Medical Image Segmentation without Annotation
Neural Ctrl-F: Segmentation-free Query-by-String Word Spotting in Handwritten Manuscript Collections
Evidential fully convolutional network for semantic segmentation
Pavementscapes: a large-scale hierarchical image dataset for asphalt pavement damage segmentation
U-Net: Convolutional Networks for Biomedical Image Segmentation
U-Net: Convolutional Networks for Biomedical Image Segmentation
FloodNet: A High Resolution Aerial Imagery Dataset for Post Flood Scene Understanding
3D MRI brain tumor segmentation using autoencoder regularization
U-Net: Convolutional Networks for Biomedical Image Segmentation
U-Net: Convolutional Networks for Biomedical Image Segmentation
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.