In this paper, we propose a novel cross-modal distillation method, calle...
This paper reveals that every image can be understood as a first-order
n...
Recently, both Contrastive Learning (CL) and Mask Image Modeling (MIM)
d...
This paper presents a new perspective of self-supervised learning based ...
Recent advances in artificial intelligence largely benefit from better n...
Vision transformer (ViT) recently has drawn great attention in computer
...
The complexity-precision trade-off of an object detector is a critical
p...
Leveraging large-scale data can introduce performance gains on many comp...
Transformers have achieved great success in pluralistic image inpainting...
Mixture of Experts (MoE) is able to scale up vision transformers effecti...
Vision Transformer (ViT) models have recently drawn much attention in
co...
Automated visual understanding of our diverse and open world demands com...
We present Mobile-Former, a parallel design of MobileNet and Transformer...
This paper aims at addressing the problem of substantial performance
deg...
The complex nature of combining localization and classification in objec...
We present in this paper a new architecture, named Convolutional vision
...
Recent research in dynamic convolution shows substantial performance boo...
Neural Architecture Search (NAS) finds the best network architecture by
...
In this paper, we present MicroNet, which is an efficient convolutional
...
Visual analytics for machine learning has recently evolved as one of the...
Concept drift is a phenomenon in which the distribution of a data stream...
Efficient search is a core issue in Neural Architecture Search (NAS). It...
Rectified linear units (ReLU) are commonly used in deep neural networks....
Light-weight convolutional neural networks (CNNs) suffer performance
deg...
Deep neural networks (DNNs) are vulnerable to maliciously generated
adve...
Interactive model analysis, the process of understanding, diagnosing, an...
Deep convolutional neural networks (CNNs) have achieved breakthrough
per...
Although there has been a great deal of interest in analyzing customer
o...