https://github.com/lab206/adaptiveclick
공식 코드AdaptiveClick: Clicks-aware Transformer with Adaptive Focal Loss for Interactive Image Segmentation
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
AdaptiveClick: Clicks-aware Transformer with Adaptive Focal Loss for Interactive Image Segmentation
Thank you BART! Rewarding Pre-Trained Models Improves Formality Style Transfer
Human Judgement as a Compass to Navigate Automatic Metrics for Formality Transfer
Multilingual Pre-training with Language and Task Adaptation for Multilingual Text Style Transfer
Global-Reasoned Multi-Task Learning Model for Surgical Scene Understanding
CateNorm: Categorical Normalization for Robust Medical Image Segmentation
RefSAM: Efficiently Adapting Segmenting Anything Model for Referring Video Object Segmentation
MOoSE: Multi-Orientation Sharing Experts for Open-set Scene Text Recognition
Unpaired Sentiment-to-Sentiment Translation: A Cycled Reinforcement Learning Approach
Siamese Network with Interactive Transformer for Video Object Segmentation
Visual Prompt Selection for In-Context Learning Segmentation
PointSAM: Pointly-Supervised Segment Anything Model for Remote Sensing Images
Zoom In and Out: A Mixed-scale Triplet Network for Camouflaged Object Detection
SurgTPGS: Semantic 3D Surgical Scene Understanding with Text Promptable Gaussian Splatting
Self-supervised Video Representation Learning by Uncovering Spatio-temporal Statistics
Multi-Modal Data-Efficient 3D Scene Understanding for Autonomous Driving
Calib3D: Calibrating Model Preferences for Reliable 3D Scene Understanding
OpenESS: Event-based Semantic Scene Understanding with Open Vocabularies
Deep Incubation: Training Large Models by Divide-and-Conquering
Deep Incubation: Training Large Models by Divide-and-Conquering
2D LiDAR and Camera Fusion Using Motion Cues for Indoor Layout Estimation
Cross-head mutual Mean-Teaching for semi-supervised medical image segmentation
DeepPS2: Revisiting Photometric Stereo Using Two Differently Illuminated Images
STRAP: Structured Object Affordance Segmentation with Point Supervision
Bridging Stereo Matching and Optical Flow via Spatiotemporal Correspondence
Ground-truth or DAER: Selective Re-query of Secondary Information
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.