https://github.com/idea-research/maskdino
공식 코드Mask DINO: Towards A Unified Transformer-based Framework for Object Detection and Segmentation
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
Mask DINO: Towards A Unified Transformer-based Framework for Object Detection and Segmentation
Pyramidal Convolution: Rethinking Convolutional Neural Networks for Visual Recognition
Skew Class-balanced Re-weighting for Unbiased Scene Graph Generation
A Comprehensive Study on Deep Learning-based Methods for Sign Language Recognition
A Versatile and Efficient Reinforcement Learning Framework for Autonomous Driving
A Versatile and Efficient Reinforcement Learning Framework for Autonomous Driving
BLO-SAM: Bi-level Optimization Based Overfitting-Preventing Finetuning of SAM
Generative AI Enables Medical Image Segmentation in Ultra Low-Data Regimes
Robust deep learning-based semantic organ segmentation in hyperspectral images
Fast Template Matching and Update for Video Object Tracking and Segmentation
Towards Global Localization using Multi-Modal Object-Instance Re-Identification
RS-Agent: Automating Remote Sensing Tasks through Intelligent Agent
AMMUNet: Multi-Scale Attention Map Merging for Remote Sensing Image Segmentation
IRSAM: Advancing Segment Anything Model for Infrared Small Target Detection
T-Mamba: Frequency-Enhanced Gated Long-Range Dependency for Tooth 3D CBCT Segmentation
ReferDINO-Plus: 2nd Solution for 4th PVUW MeViS Challenge at CVPR 2025
Semantic Segmentation-Assisted Instance Feature Fusion for Multi-Level 3D Part Instance Segmentation
Cellpose+, a morphological analysis tool for feature extraction of stained cell images
SegTransVAE: Hybrid CNN -- Transformer with Regularization for medical image segmentation
Compensating Supervision Incompleteness with Prior Knowledge in Semantic Image Interpretation
Kolmogorov-Arnold Convolutions: Design Principles and Empirical Studies
Evidence fusion with contextual discounting for multi-modality medical image segmentation
Instruct Me More! Random Prompting for Visual In-Context Learning
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.