This paper presents MOAT, a family of neural networks that build on top ...
The rise of transformers in vision tasks not only advances network backb...
We propose Clustering Mask Transformer (CMT-DeepLab), a transformer-base...
Panoptic image segmentation is the computer vision task of finding group...
We present TubeFormer-DeepLab, the first attempt to tackle multiple core...
Self-Attention has become prevalent in computer vision models. Inspired ...
DeepLab2 is a TensorFlow library for deep labeling, aiming to provide a
...
In this paper, we present ViP-DeepLab, a unified model attempting to tac...
Batch normalization (BN) is a fundamental unit in modern deep networks, ...
The Wide Residual Networks (Wide-ResNets), a shallow but wide model vari...
Many modern object detectors demonstrate outstanding performances by usi...
Modern instance segmentation approaches mainly adopt a sequential paradi...
In this paper, we study normalization methods for neural networks from t...
Despite deep convolutional neural networks' great success in object
clas...
In this paper, we propose Weight Standardization (WS) to accelerate deep...
In this paper, we study the problem of improving computational resource
...
Computer vision is difficult, partly because the mathematical function
c...
Recent anchor-based deep face detectors have achieved promising performa...
This paper studies teacher-student optimization on neural networks, i.e....
Convolution is spatially-symmetric, i.e., the visual features are indepe...
In this paper, we study the problem of semi-supervised image recognition...
We propose a novel single shot object detection network named Detection ...
We present a simple yet effective neural network architecture for image
...
Convolutional neural networks (CNNs) have been generally acknowledged as...
In this paper, we are interested in the few-shot learning problem. In
pa...