13 citations · 13 across the 4 of their papers we have counts for
5 papers
ROSE: Robust Selective Fine-tuning for Pre-trained Language Models
Lan Jiang, Hao Zhou, Yankai Lin +3
Even though the large-scale language models have achieved excellent performances, they suffer from various adversarial attacks. A large body of defense methods has been proposed. H…
IMB-NAS: Neural Architecture Search for Imbalanced Datasets
Rahul Duggal, Shengyun Peng, Hao Zhou +1
Class imbalance is a ubiquitous phenomenon occurring in real world data distributions. To overcome its detrimental effect on training accurate classifiers, existing work follows th…
Towards Regression-Free Neural Networks for Diverse Compute Platforms
Rahul Duggal, Hao Zhou, Shuo Yang +3
With the shift towards on-device deep learning, ensuring a consistent behavior of an AI service across diverse compute platforms becomes tremendously important. Our work tackles th…
Compatibility-aware Heterogeneous Visual Search
Rahul Duggal, Hao Zhou, Shuo Yang +4
We tackle the problem of visual search under resource constraints. Existing systems use the same embedding model to compute representations (embeddings) for the query and gallery i…
Kaleido-BERT: Vision-Language Pre-training on Fashion Domain
Mingchen Zhuge, Dehong Gao, Deng-Ping Fan +5
We present a new vision-language (VL) pre-training model dubbed Kaleido-BERT, which introduces a novel kaleido strategy for fashion cross-modality representations from transformers…