The explosive growth of language models and their applications have led ...
Pretraining on a large-scale corpus has become a standard method to buil...
In this paper, we propose a data-model-hardware tri-design framework for...
Advanced deep neural networks (DNNs), designed by either human or AutoML...
This work targets automated designing and scaling of Vision Transformers...
This work presents a simple vision transformer design as a strong baseli...
This work targets designing a principled and unified training-free frame...
Semantic segmentation for scene understanding is nowadays widely demande...
Training on synthetic data can be beneficial for label or data-scarce
sc...
Learning to optimize (L2O) is an emerging approach that leverages machin...
Neural Architecture Search (NAS) has been explosively studied to automat...
We present Sandwich Batch Normalization (SaBN), an embarrassingly easy
i...
Models trained on synthetic images often face degraded generalization to...
The compression of Generative Adversarial Networks (GANs) has lately dra...
We present FasterSeg, an automatically designed semantic segmentation ne...
The comparative losses (typically, triplet loss) are appealing choices f...
Many real-world applications, such as city-scale traffic monitoring and
...
Attention mechanism has been shown to be effective for person
re-identif...
Segmentation of ultra-high resolution images is increasingly demanded, y...