田运杰
田运杰
beyond_masking
Beyond Masking: Demystifying Token-Based Pre-Training for Vision Transformers
DAAS
'Discretization-Aware Architecture Search' alleviates the discretization gap in one-shot differentiable NAS. DAAS has been accepted by PR (2021).
SaGe
(SaGe) Semantic-Aware Generation for Self-Supervised Visual Representation Learning
SDL-Skeleton
A toolbox for object skeleton detection, can also be used for edge detection, building extraction and road extraction. TIP (2021)
iTPN
(CVPR2023/TPAMI2024) Integrally Pre-Trained Transformer Pyramid Networks -- A Hierarchical Vision Transformer for Masked Image Modeling
ChatterBox
[AAAI2025] ChatterBox: Multi-round Multimodal Referring and Grounding, Multimodal, Multi-round dialogues
yolov12
[NeurIPS 2025] YOLOv12: Attention-Centric Real-Time Object Detectors