212 citations · 351 across the 9 of their papers we have counts for
9 papers
kMaX-DeepLab: k-means Mask Transformer
Qihang Yu, Huiyu Wang, Siyuan Qiao +5
The rise of transformers in vision tasks not only advances network backbone designs, but also starts a brand-new page to achieve end-to-end image recognition (e.g., object detectio…
TubeFormer-DeepLab: Video Mask Transformer
Dahun Kim, Jun Xie, Huiyu Wang +6
We present TubeFormer-DeepLab, the first attempt to tackle multiple core video segmentation tasks in a unified manner. Different video segmentation tasks (e.g., video semantic/inst…
Searching for TrioNet: Combining Convolution with Local and Global Self-Attention
Huaijin Pi, Huiyu Wang, Yingwei Li +2
Recently, self-attention operators have shown superior performance as a stand-alone building block for vision models. However, existing self-attention models are often hand-designe…
iBOT: Image BERT Pre-Training with Online Tokenizer
Jinghao Zhou, Chen Wei, Huiyu Wang +4
The success of language Transformers is primarily attributed to the pretext task of masked language modeling (MLM), where texts are first tokenized into semantically meaningful pie…
DeepLab2: A TensorFlow Library for Deep Labeling
Mark Weber, Huiyu Wang, Siyuan Qiao +12
DeepLab2 is a TensorFlow library for deep labeling, aiming to provide a state-of-the-art and easy-to-use TensorFlow codebase for general dense pixel prediction problems in computer…
SpecTr: Spectral Transformer for Hyperspectral Pathology Image Segmentation
Boxiang Yun, Yan Wang, Jieneng Chen +3
Hyperspectral imaging (HSI) unlocks the huge potential to a wide variety of applications relied on high-precision pathology image segmentation, such as computational pathology and…
MaX-DeepLab: End-to-End Panoptic Segmentation with Mask Transformers
Huiyu Wang, Yukun Zhu, Hartwig Adam +2
We present MaX-DeepLab, the first end-to-end model for panoptic segmentation. Our approach simplifies the current pipeline that depends heavily on surrogate sub-tasks and hand-desi…
Scaling Wide Residual Networks for Panoptic Segmentation
Liang-Chieh Chen, Huiyu Wang, Siyuan Qiao
The Wide Residual Networks (Wide-ResNets), a shallow but wide model variant of the Residual Networks (ResNets) by stacking a small number of residual blocks with large channel size…
CO2: Consistent Contrast for Unsupervised Visual Representation Learning
Chen Wei, Huiyu Wang, Wei Shen +1
Contrastive learning has been adopted as a core method for unsupervised visual representation learning. Without human annotation, the common practice is to perform an instance disc…