168 citations · 726 across the 30 of their papers we have counts for
31 papers
IG Captioner: Information Gain Captioners are Strong Zero-shot Classifiers
Chenglin Yang, Siyuan Qiao, Yuan Cao +4
Generative training has been demonstrated to be powerful for building visual-language models. However, on zero-shot discriminative benchmarks, there is still a performance gap betw…
De-Diffusion Makes Text a Strong Cross-Modal Interface
Chen Wei, Chenxi Liu, Siyuan Qiao +3
We demonstrate text as a strong cross-modal interface. Rather than relying on deep embeddings to connect image and language as the interface representation, our approach represents…
Superpixel Transformers for Efficient Semantic Segmentation
Alex Zihao Zhu, Jieru Mei, Siyuan Qiao +4
Semantic segmentation, which aims to classify every pixel in an image, is a key task in machine perception, with many applications across robotics and autonomous driving. Due to th…
PaLM 2 Technical Report
Rohan Anil, Andrew M. Dai, Orhan Firat +125
We introduce PaLM 2, a new state-of-the-art language model that has better multilingual and reasoning capabilities and is more compute-efficient than its predecessor PaLM. PaLM 2 i…
MOAT: Alternating Mobile Convolution and Attention Brings Strong Vision Models
Chenglin Yang, Siyuan Qiao, Qihang Yu +5
This paper presents MOAT, a family of neural networks that build on top of MObile convolution (i.e., inverted residual blocks) and ATtention. Unlike the current works that stack se…
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…
CMT-DeepLab: Clustering Mask Transformers for Panoptic Segmentation
Qihang Yu, Huiyu Wang, Dahun Kim +6
We propose Clustering Mask Transformer (CMT-DeepLab), a transformer-based framework for panoptic segmentation designed around clustering. It rethinks the existing transformer archi…
Waymo Open Dataset: Panoramic Video Panoptic Segmentation
Jieru Mei, Alex Zihao Zhu, Xinchen Yan +6
Panoptic image segmentation is the computer vision task of finding groups of pixels in an image and assigning semantic classes and object instance identifiers to them. Research in…
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…
Locally Enhanced Self-Attention: Combining Self-Attention and Convolution as Local and Context Terms
Chenglin Yang, Siyuan Qiao, Adam Kortylewski +1
Self-Attention has become prevalent in computer vision models. Inspired by fully connected Conditional Random Fields (CRFs), we decompose self-attention into local and context term…
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…
ViP-DeepLab: Learning Visual Perception with Depth-aware Video Panoptic Segmentation
Siyuan Qiao, Yukun Zhu, Hartwig Adam +2
In this paper, we present ViP-DeepLab, a unified model attempting to tackle the long-standing and challenging inverse projection problem in vision, which we model as restoring the…
Batch Normalization with Enhanced Linear Transformation
Yuhui Xu, Lingxi Xie, Cihang Xie +5
Batch normalization (BN) is a fundamental unit in modern deep networks, in which a linear transformation module was designed for improving BN's flexibility of fitting complex data…
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…
DetectoRS: Detecting Objects with Recursive Feature Pyramid and Switchable Atrous Convolution
Siyuan Qiao, Liang-Chieh Chen, Alan Yuille
Many modern object detectors demonstrate outstanding performances by using the mechanism of looking and thinking twice. In this paper, we explore this mechanism in the backbone des…
Rethinking Normalization and Elimination Singularity in Neural Networks
Siyuan Qiao, Huiyu Wang, Chenxi Liu +2
In this paper, we study normalization methods for neural networks from the perspective of elimination singularity. Elimination singularities correspond to the points on the trainin…
Deeply Shape-guided Cascade for Instance Segmentation
Hao Ding, Siyuan Qiao, Alan Yuille +1
The key to a successful cascade architecture for precise instance segmentation is to fully leverage the relationship between bounding box detection and mask segmentation across mul…
TDAPNet: Prototype Network with Recurrent Top-Down Attention for Robust Object Classification under Partial Occlusion
Mingqing Xiao, Adam Kortylewski, Ruihai Wu +3
Despite deep convolutional neural networks' great success in object classification, it suffers from severe generalization performance drop under occlusion due to the inconsistency…
Micro-Batch Training with Batch-Channel Normalization and Weight Standardization
Siyuan Qiao, Huiyu Wang, Chenxi Liu +2
Batch Normalization (BN) has become an out-of-box technique to improve deep network training. However, its effectiveness is limited for micro-batch training, i.e., each GPU typical…
Neural Rejuvenation: Improving Deep Network Training by Enhancing Computational Resource Utilization
Siyuan Qiao, Zhe Lin, Jianming Zhang +1
In this paper, we study the problem of improving computational resource utilization of neural networks. Deep neural networks are usually over-parameterized for their tasks in order…
Robust Face Detection via Learning Small Faces on Hard Images
Zhishuai Zhang, Wei Shen, Siyuan Qiao +3
Recent anchor-based deep face detectors have achieved promising performance, but they are still struggling to detect hard faces, such as small, blurred and partially occluded faces…
Generalized Coarse-to-Fine Visual Recognition with Progressive Training
Xutong Ren, Lingxi Xie, Chen Wei +6
Computer vision is difficult, partly because the desired mathematical function connecting input and output data is often complex, fuzzy and thus hard to learn. Coarse-to-fine (C2F)…
Knowledge Distillation in Generations: More Tolerant Teachers Educate Better Students
Chenglin Yang, Lingxi Xie, Siyuan Qiao +1
We focus on the problem of training a deep neural network in generations. The flowchart is that, in order to optimize the target network (student), another network (teacher) with t…
Multi-Scale Spatially-Asymmetric Recalibration for Image Classification
Yan Wang, Lingxi Xie, Siyuan Qiao +3
Convolution is spatially-symmetric, i.e., the visual features are independent of its position in the image, which limits its ability to utilize contextual cues for visual recogniti…