activity
20172024
most citedAdaComp : Adaptive Residual Gradient Compression for Data-Parallel Distributed Training

74 citations · 83 across the 5 of their papers we have counts for

collaborators

5 papers

cs.CV20241 cited

DetCLIPv3: Towards Versatile Generative Open-vocabulary Object Detection

Lewei Yao, Renjie Pi, Jianhua Han +5

Existing open-vocabulary object detectors typically require a predefined set of categories from users, significantly confining their application scenarios. In this paper, we introd…

cs.CV20234 cited

Learning and Evaluating Human Preferences for Conversational Head Generation

Mohan Zhou, Yalong Bai, Wei Zhang +3

A reliable and comprehensive evaluation metric that aligns with manual preference assessments is crucial for conversational head video synthesis methods development. Existing quant…

cs.CV20232 cited

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

Lewei Yao, Jianhua Han, Xiaodan Liang +4

This paper presents DetCLIPv2, an efficient and scalable training framework that incorporates large-scale image-text pairs to achieve open-vocabulary object detection (OVD). Unlike…

cs.CV20232 cited

CapDet: Unifying Dense Captioning and Open-World Detection Pretraining

Yanxin Long, Youpeng Wen, Jianhua Han +5

Benefiting from large-scale vision-language pre-training on image-text pairs, open-world detection methods have shown superior generalization ability under the zero-shot or few-sho…

cs.LG201774 cited

AdaComp : Adaptive Residual Gradient Compression for Data-Parallel Distributed Training

Chia-Yu Chen, Jungwook Choi, Daniel Brand +3

Highly distributed training of Deep Neural Networks (DNNs) on future compute platforms (offering 100 of TeraOps/s of computational capacity) is expected to be severely communicatio…