FILIP: Fine-grained Interactive Language-Image Pre-Training

Lewei Yao, Runhui Huang, Lu Hou, +7

arXiv (Cornell University)

EngineeringMachine LearningNatural Language ProcessingMultimodal LlmImage Analysis +15

SM-NAS: Structural-to-Modular Neural Architecture Search for Object Detection

Lewei Yao, Hang Xu, Wei Zhang, +2

Proceedings of the AAAI Conference on Artificial Intelligence

Convolutional Neural NetworkMachine VisionMachine LearningImage AnalysisEngineering +11

DetCLIP: Dictionary-Enriched Visual-Concept Paralleled Pre-training for Open-world Detection

Lewei Yao, Jianhua Han, Youpeng Wen, +6

arXiv (Cornell University)

EngineeringMachine LearningObject CategorizationArbitrary Category NamesNatural Language Processing +16

DetCLIPv2: Scalable Open-Vocabulary Object Detection Pre-training via Word-Region Alignment

Lewei Yao, Jianhua Han, Xiaodan Liang, +4

EngineeringMachine LearningNatural Language ProcessingMultimodal LlmImage Analysis +15

DetGPT: Detect What You Need via Reasoning

Renjie Pi, Jiahui Gao, Shizhe Diao, +8

Program CheckingEngineeringVerificationSoftware AnalysisLanguage Processing +21

G-DetKD: Towards General Distillation Framework for Object Detectors via Contrastive and Semantic-guided Feature Imitation

Lewei Yao, Renjie Pi, Hang Xu, +3

2021 IEEE/CVF International Conference on Computer Vision (ICCV)

Artificial IntelligenceContrastive DistillationEngineeringMachine LearningObject Categorization +16

DiffFit: Unlocking Transferability of Large Diffusion Models via Simple Parameter-Efficient Fine-Tuning

Enze Xie, Lewei Yao, Han Shi, +5

EngineeringMachine LearningLarge Diffusion ModelsOptimal TransportFast Adaptation +19

Wukong: A 100 Million Large-scale Chinese Cross-modal Pre-training Benchmark

Jiaxi Gu, Xiaojun Meng, Guansong Lu, +9

arXiv (Cornell University)

EngineeringMachine LearningMultimodal LearningMultilingual PretrainingSpeech Recognition +14

Joint-DetNAS: Upgrade Your Detector with NAS, Pruning and Dynamic Distillation

Lewei Yao, Renjie Pi, Hang Xu, +3

DetCLIPv3: Towards Versatile Generative Open-Vocabulary Object Detection

Lewei Yao, Renjie Pi, Jianhua Han, +5