2.8k citations · 8.6k across the 72 of their papers we have counts for
14 papers · 1 filter
ModeRNN: Harnessing Spatiotemporal Mode Collapse in Unsupervised Predictive Learning
Zhiyu Yao, Yunbo Wang, Haixu Wu +2
Learning predictive models for unlabeled spatiotemporal data is challenging in part because visual dynamics can be highly entangled in real scenes, making existing approaches prone…
X-model: Improving Data Efficiency in Deep Learning with A Minimax Model
Ximei Wang, Xinyang Chen, Jianmin Wang +1
To mitigate the burden of data labeling, we aim at improving data efficiency for both classification and regression setups in deep learning. However, the current focus is on classi…
Ranking and Tuning Pre-trained Models: A New Paradigm for Exploiting Model Hubs
Kaichao You, Yong Liu, Ziyang Zhang +3
Model hubs with many pre-trained models (PTMs) have become a cornerstone of deep learning. Although built at a high cost, they remain \emph{under-exploited} -- practitioners usuall…
Omni-Training: Bridging Pre-Training and Meta-Training for Few-Shot Learning
Yang Shu, Zhangjie Cao, Jinghan Gao +3
Few-shot learning aims to fast adapt a deep model from a few examples. While pre-training and meta-training can create deep models powerful for few-shot generalization, we find tha…
Anomaly Transformer: Time Series Anomaly Detection with Association Discrepancy
Jiehui Xu, Haixu Wu, Jianmin Wang +1
Unsupervised detection of anomaly points in time series is a challenging problem, which requires the model to derive a distinguishable criterion. Previous methods tackle the proble…
Decoupled Adaptation for Cross-Domain Object Detection
Junguang Jiang, Baixu Chen, Jianmin Wang +1
Cross-domain object detection is more challenging than object classification since multiple objects exist in an image and the location of each object is unknown in the unlabeled ta…