Large pretrained plain vision Transformers (ViTs) have been the workhors...
Large pre-trained models (LPMs), such as LLaMA and ViT-G, have shown
exc...
Diffusion models have recently dominated image synthesis and other relat...
The public model zoo containing enormous powerful pretrained model famil...
Recent advances in Transformers have come with a huge requirement on
com...
Model binarization can significantly compress model size, reduce energy
...
Transformer is a transformative framework that models sequential data an...
Vision Transformers (ViTs) have underpinned the recent breakthroughs in
...
The task of action detection aims at deducing both the action category a...
Vision Transformers (ViTs) have triggered the most recent and significan...
Recent advances in vision Transformers (ViTs) have come with a voracious...
Network quantization is an effective compression method to reduce the mo...
There has been an explosion of interest in designing high-performance
Tr...
We study a new challenging problem of efficient deployment for diverse t...
Transformers have become one of the dominant architectures in deep learn...
Previous human parsing models are limited to parsing humans into pre-def...
The recently proposed Visual image Transformers (ViT) with pure attentio...
We present Automatic Bit Sharing (ABS) to automatically search for optim...
With the rising popularity of intelligent mobile devices, it is of great...
Ternary Neural Networks (TNNs) have received much attention due to being...
Network quantization aims to lower the bitwidth of weights and activatio...
Knowledge Distillation (KD) is a common method for transferring the
“kno...
Neural network quantization is an effective way to compress deep models ...
Instantaneous and on demand accuracy-efficiency trade-off has been recen...
Neural network quantization and pruning are two techniques commonly used...
We study network pruning which aims to remove redundant channels/kernels...
We propose methods to train convolutional neural networks (CNNs) with bo...
It is observed that overparameterization (i.e., designing neural network...
Binarized convolutional neural networks (BCNNs) are widely used to impro...
This paper tackles the problem of training a deep convolutional neural
n...
In this paper, we seek to tackle two challenges in training low-precisio...
In this paper, we propose to train convolutional neural networks (CNNs) ...
In this paper, we propose to train a network with both binary weights an...
Channel pruning is one of the predominant approaches for deep model
comp...
In this paper, we propose to train a network with binary weights and
low...
Recognising objects according to a pre-defined fixed set of class labels...
This paper tackles the problem of training a deep convolutional neural
n...
Accurately counting maize tassels is important for monitoring the growth...
Visual relationship detection aims to capture interactions between pairs...
Recognizing how objects interact with each other is a crucial task in vi...
Recognizing the identities of people in everyday photos is still a very
...
Large-scale datasets have driven the rapid development of deep neural
ne...
In this paper, we propose a robust tracking method based on the collabor...
In this paper, we aim to learn a mapping (or embedding) from images to a...