DETR-like models have significantly boosted the performance of detectors...
The large-scale visual pretraining has significantly improve the perform...
The extraordinary ability of generative models to generate photographic
...
The recent upsurge in pre-trained large models (e.g. GPT-4) has swept ac...
Recent releases of Large Language Models (LLMs), e.g. ChatGPT, are
aston...
The tremendous success of large models trained on extensive datasets
dem...
At the heart of foundation models is the philosophy of "more is differen...
Masked Image Modeling (MIM) achieves outstanding success in self-supervi...
This paper studies the problem of designing compact binary architectures...
Adder Neural Network (AdderNet) provides a new way for developing
energy...
The combination of transformers and masked image modeling (MIM) pre-trai...
Light-weight convolutional neural networks (CNNs) are specially designed...
This paper studies the Binary Neural Networks (BNNs) in which weights an...
Network architecture plays a key role in the deep learning-based compute...
Domain Adaptation aims to transfer the knowledge learned from a labeled
...
Many adaptations of transformers have emerged to address the single-moda...
Recently, Multilayer Perceptron (MLP) becomes the hotspot in the field o...
This paper studies the 3D instance segmentation problem, which has a var...
Neural architecture search (NAS) has shown encouraging results in automa...
Deploying convolutional neural networks (CNNs) on mobile devices is diff...
Transformer networks have achieved great progress for computer vision ta...
Adder neural networks (AdderNets) have shown impressive performance on i...
Different from traditional convolutional neural network (CNN) and vision...
Recently, many evolutionary computation methods have been developed to s...
This paper introduces versatile filters to construct efficient convoluti...
This paper presents Hire-MLP, a simple yet competitive vision MLP
archit...
With the tremendous advances in the architecture and scale of convolutio...
Recent studies on deep convolutional neural networks present a simple
pa...
Vision transformers have been successfully applied to image recognition ...
This paper studies the model compression problem of vision transformers....
Transformer models have achieved great progress on computer vision tasks...
Recently, transformer has achieved remarkable performance on a variety o...
We study the problem of learning from positive and unlabeled (PU) data i...
Deep convolutional neural networks (CNNs) are often of sophisticated des...
This paper studies the efficiency problem for visual transformers by
exc...
Adder neural network (AdderNet) is a new kind of deep model that replace...
This paper studies the neural architecture search (NAS) problem for
deve...
Visual transformer has achieved competitive performance on a variety of
...
Knowledge distillation is a widely used paradigm for inheriting informat...
Deep learning based methods, especially convolutional neural networks (C...
Neural network pruning is an essential approach for reducing the
computa...
Binary neural networks (BNNs) represent original full-precision weights ...
Transformer is a type of self-attention-based neural networks originally...
Convolutional neural networks (CNN) have been widely used for boosting t...
Modern single image super-resolution (SISR) system based on convolutiona...
Transformer is a type of deep neural network mainly based on self-attent...
This paper studies feature pyramid network (FPN), which is a widely used...
As the computing power of modern hardware is increasing strongly, pre-tr...
This paper proposes a reliable neural network pruning algorithm by setti...
This paper formalizes the binarization operations over neural networks f...