no code implementations • 26 Jan 2023 • Han Zhang, Ziwei Zhu, James Caverlee
However, most existing work focuses on a static setting or over a short-time window, leaving open questions about the long-term and dynamic impacts of news recommendations.
1 code implementation • 2 Jan 2023 • Huiwen Chang, Han Zhang, Jarred Barber, AJ Maschinot, Jose Lezama, Lu Jiang, Ming-Hsuan Yang, Kevin Murphy, William T. Freeman, Michael Rubinstein, Yuanzhen Li, Dilip Krishnan
Compared to pixel-space diffusion models, such as Imagen and DALL-E 2, Muse is significantly more efficient due to the use of discrete tokens and requiring fewer sampling iterations; compared to autoregressive models, such as Parti, Muse is more efficient due to the use of parallel decoding.
Ranked #16 on
Text-to-Image Generation
on COCO
1 code implementation • 15 Dec 2022 • Fangyi Chen, Han Zhang, Kai Hu, Yu-Kai Huang, Chenchen Zhu, Marios Savvides
This paper investigates a phenomenon where query-based object detectors mispredict at the last decoding stage while predicting correctly at an intermediate stage.
Ranked #3 on
Object Detection
on COCO 2017 val
1 code implementation • 10 Dec 2022 • Lijun Yu, Yong Cheng, Kihyuk Sohn, José Lezama, Han Zhang, Huiwen Chang, Alexander G. Hauptmann, Ming-Hsuan Yang, Yuan Hao, Irfan Essa, Lu Jiang
We introduce the MAsked Generative VIdeo Transformer, MAGVIT, to tackle various video synthesis tasks with a single model.
Ranked #1 on
Video Prediction
on Something-Something V2
no code implementations • 7 Dec 2022 • Ronghui Li, Junfan Zhao, Yachao Zhang, Mingyang Su, Zeping Ren, Han Zhang, Xiu Li
To the best of our knowledge, MagicDance is the 3D dance dataset with the most genres.
no code implementations • 29 Nov 2022 • Han Zhang, Ruili Feng, Zhantao Yang, Lianghua Huang, Yu Liu, Yifei Zhang, Yujun Shen, Deli Zhao, Jingren Zhou, Fan Cheng
Diffusion models, which learn to reverse a signal destruction process to generate new data, typically require the signal at each step to have the same dimension.
no code implementations • 23 Nov 2022 • Cheng Ge, Han Zhang, Jiaoyang Li, Sven Koenig
Our theoretical results show that, when combined with either of these two new splitting strategies, MO-CBS maintains its completeness and optimality guarantees.
1 code implementation • 16 Nov 2022 • Tianhong Li, Huiwen Chang, Shlok Kumar Mishra, Han Zhang, Dina Katabi, Dilip Krishnan
In this work, we propose MAsked Generative Encoder (MAGE), the first framework to unify SOTA image generation and self-supervised representation learning.
1 code implementation • 4 Nov 2022 • Xuhai Xu, Han Zhang, Yasaman Sefidgar, Yiyi Ren, Xin Liu, Woosuk Seo, Jennifer Brown, Kevin Kuehn, Mike Merrill, Paula Nurius, Shwetak Patel, Tim Althoff, Margaret E. Morris, Eve Riskin, Jennifer Mankoff, Anind K. Dey
We envision our multi-year datasets can support the ML community in developing generalizable longitudinal behavior modeling algorithms.
no code implementations • 18 Oct 2022 • Lisa Dunlap, Clara Mohri, Devin Guillory, Han Zhang, Trevor Darrell, Joseph E. Gonzalez, aditi raghunathan, Anja Rohrbach
It is expensive to collect training data for every possible domain that a vision model may encounter when deployed.
no code implementations • 7 Oct 2022 • Han Zhang, Lok Ming Lui
Comparing to the segmentation framework based on pixel-wise classification, deformation-based segmentation models that warp a template to enclose the regions are more convenient to enforce geometric constraints.
no code implementations • 5 Oct 2022 • Xia Su, Kaiming Cheng, Han Zhang, Jaewook Lee, Jon E. Froehlich
To help improve the safety and accessibility of indoor spaces, researchers and health professionals have created assessment instruments that enable homeowners and trained experts to audit and improve homes.
1 code implementation • 5 Oct 2022 • Ruben Villegas, Mohammad Babaeizadeh, Pieter-Jan Kindermans, Hernan Moraldo, Han Zhang, Mohammad Taghi Saffar, Santiago Castro, Julius Kunze, Dumitru Erhan
To the best of our knowledge, this is the first time a paper studies generating videos from time variable prompts.
1 code implementation • 3 Oct 2022 • Kihyuk Sohn, Yuan Hao, José Lezama, Luisa Polania, Huiwen Chang, Han Zhang, Irfan Essa, Lu Jiang
We base our framework on state-of-the-art generative vision transformers that represent an image as a sequence of visual tokens to the autoregressive or non-autoregressive transformers.
no code implementations • 22 Sep 2022 • Mianxin Liu, Han Zhang, Feng Shi, Dinggang Shen
In this study, we propose a novel framework to perform multiscale FCN analysis for brain disorder diagnosis.
no code implementations • 15 Aug 2022 • Hao Chen, Ran Tao, Han Zhang, Yidong Wang, Wei Ye, Jindong Wang, Guosheng Hu, Marios Savvides
Beyond classification, Conv-Adapter can generalize to detection and segmentation tasks with more than 50% reduction of parameters but comparable performance to the traditional full fine-tuning.
1 code implementation • 12 Aug 2022 • Yiming Qiu, Chenyu Zhao, Han Zhang, Jingwei Zhuo, TianHao Li, Xiaowei Zhang, Songlin Wang, Sulong Xu, Bo Long, Wen-Yun Yang
BERT-style models pre-trained on the general corpus (e. g., Wikipedia) and fine-tuned on specific task corpus, have recently emerged as breakthrough techniques in many NLP tasks: question answering, text classification, sequence labeling and so on.
1 code implementation • 22 Jun 2022 • Jiahui Yu, Yuanzhong Xu, Jing Yu Koh, Thang Luong, Gunjan Baid, ZiRui Wang, Vijay Vasudevan, Alexander Ku, Yinfei Yang, Burcu Karagol Ayan, Ben Hutchinson, Wei Han, Zarana Parekh, Xin Li, Han Zhang, Jason Baldridge, Yonghui Wu
We present the Pathways Autoregressive Text-to-Image (Parti) model, which generates high-fidelity photorealistic images and supports content-rich synthesis involving complex compositions and world knowledge.
Ranked #10 on
Text-to-Image Generation
on COCO
no code implementations • 24 May 2022 • Zifan Wang, Yuhang Yao, Chaoran Zhang, Han Zhang, Youjie Kang, Carlee Joe-Wong, Matt Fredrikson, Anupam Datta
Second, our analytical and empirical results demonstrate that feature attribution methods cannot capture the nonlinear effect of edge features, while existing subgraph explanation methods are not faithful.
1 code implementation • 6 May 2022 • Zhenghao Liu, Han Zhang, Chenyan Xiong, Zhiyuan Liu, Yu Gu, Xiaohua LI
These embeddings need to be high-dimensional to fit training signals and guarantee the retrieval effectiveness of dense retrievers.
Ranked #1 on
Information Retrieval
on MS MARCO
1 code implementation • 10 Apr 2022 • Zifeng Wang, Zizhao Zhang, Sayna Ebrahimi, Ruoxi Sun, Han Zhang, Chen-Yu Lee, Xiaoqi Ren, Guolong Su, Vincent Perot, Jennifer Dy, Tomas Pfister
Continual learning aims to enable a single model to learn a sequence of tasks without catastrophic forgetting.
no code implementations • 7 Apr 2022 • Ran Tao, Han Zhang, Yutong Zheng, Marios Savvides
Class-agnostic bias is defined as the distribution shifting introduced by domain difference, which we propose Distribution Calibration Module(DCM) to reduce.
10 code implementations • 4 Apr 2022 • Zhengzhong Tu, Hossein Talebi, Han Zhang, Feng Yang, Peyman Milanfar, Alan Bovik, Yinxiao Li
We also show that our proposed model expresses strong generative modeling capability on ImageNet, demonstrating the superior potential of MaxViT blocks as a universal vision module.
Ranked #1 on
Object Detection
on COCO 2017
no code implementations • 1 Apr 2022 • Fangyi Chen, Han Zhang, Zaiwang Li, Jiachen Dou, Shentong Mo, Hao Chen, Yongxin Zhang, Uzair Ahmed, Chenchen Zhu, Marios Savvides
To make full use of computer vision technology in stores, it is required to consider the actual needs that fit the characteristics of the retail scene.
Ranked #1 on
Dense Object Detection
on SKU-110K
Dense Object Detection
One-stage Anchor-free Oriented Object Detection
+1
no code implementations • 30 Mar 2022 • Yuliang Zou, Zizhao Zhang, Chun-Liang Li, Han Zhang, Tomas Pfister, Jia-Bin Huang
We propose a test-time adaptation method for cross-domain image segmentation.
no code implementations • 13 Mar 2022 • Han Zhang, Zihao Zhang, Wenhao Zheng, Wei Xu
A major challenge in image segmentation is classifying object boundaries.
no code implementations • ICLR 2022 • Yunjiang Jiang, Han Zhang, Yiming Qiu, Yun Xiao, Bo Long, Wen-Yun Yang
Product quantization (PQ) coupled with a space rotation, is widely used in modern approximate nearest neighbor (ANN) search systems to significantly compress the disk storage for embeddings and speed up the inner product computation.
no code implementations • 27 Feb 2022 • Han Zhang, Lok Ming Lui
TPSN is a deformation-based model that yields a deformation map through a UNet, which takes the medical image and a template mask as inputs.
no code implementations • 21 Feb 2022 • Chao Lv, Han Zhang, Xinkai Du, Yunhao Zhang, Ying Huang, Wenhao Li, Jia Han, Shanshan Gu
With the success of down streaming task using English pre-trained language model, the pre-trained Chinese language model is also necessary to get a better performance of Chinese NLP task.
3 code implementations • CVPR 2022 • Huiwen Chang, Han Zhang, Lu Jiang, Ce Liu, William T. Freeman
At inference time, the model begins with generating all tokens of an image simultaneously, and then refines the image iteratively conditioned on the previous generation.
Ranked #2 on
Text-to-Image Generation
on LHQC
1 code implementation • CVPR 2022 • Zhengzhong Tu, Hossein Talebi, Han Zhang, Feng Yang, Peyman Milanfar, Alan Bovik, Yinxiao Li
In this work, we present a multi-axis MLP based architecture called MAXIM, that can serve as an efficient and flexible general-purpose vision backbone for image processing tasks.
Ranked #1 on
Deblurring
on RealBlur-J
(using extra training data)
2 code implementations • 31 Dec 2021 • Han Zhang, Weichong Yin, Yewei Fang, Lanxin Li, Boqiang Duan, Zhihua Wu, Yu Sun, Hao Tian, Hua Wu, Haifeng Wang
To explore the landscape of large-scale pre-training for bidirectional text-image generation, we train a 10-billion parameter ERNIE-ViLG model on a large-scale dataset of 145 million (Chinese) image-text pairs which achieves state-of-the-art performance for both text-to-image and image-to-text tasks, obtaining an FID of 7. 9 on MS-COCO for text-to-image synthesis and best results on COCO-CN and AIC-ICC for image captioning.
Ranked #31 on
Text-to-Image Generation
on COCO
1 code implementation • CVPR 2022 • Zifeng Wang, Zizhao Zhang, Chen-Yu Lee, Han Zhang, Ruoxi Sun, Xiaoqi Ren, Guolong Su, Vincent Perot, Jennifer Dy, Tomas Pfister
The mainstream paradigm behind continual learning has been to adapt the model parameters to non-stationary data distributions, where catastrophic forgetting is the central challenge.
no code implementations • 14 Dec 2021 • Yongkang Zhang, Jun Li, Guoming Wu, Han Zhang, Zhiping Shi, Zhaoxun Liu, Zizhang Wu, Na Jiang
The temporal sequence self-supervision module we employ unprecedentedly adopts the streamlined strategy of "random batch random channel" to reverse the sequence of video frames, allowing robust extractions of motion information representation from inversed temporal dimensions and improving the generalization capability of the model.
no code implementations • 9 Dec 2021 • Xiang Kong, Lu Jiang, Huiwen Chang, Han Zhang, Yuan Hao, Haifeng Gong, Irfan Essa
During inference, BLT first generates a draft layout from the input and then iteratively refines it into a high-quality layout by masking out low-confident attributes.
no code implementations • 8 Nov 2021 • Su Wang, Zhiliang Wang, Tao Zhou, Xia Yin, Dongqi Han, Han Zhang, Hongbin Sun, Xingang Shi, Jiahai Yang
Recent studies propose leveraging the rich contextual information in data provenance to detect threats in a host.
no code implementations • 25th International Conference on Pattern Recognition (ICPR) 2021 • Ge Pan, Han Zhang, Fan Yu, Yonghong Song, Yuanlin Zhang, Han Yuan
In this paper, we propose a method called YOLA (You Ought to Look Around) which includes three parts: 1) a robust backbone SPN-I3D for extracting spatio-temporal features.
2 code implementations • ICLR 2022 • Jiahui Yu, Xin Li, Jing Yu Koh, Han Zhang, Ruoming Pang, James Qin, Alexander Ku, Yuanzhong Xu, Jason Baldridge, Yonghui Wu
Motivated by this success, we explore a Vector-quantized Image Modeling (VIM) approach that involves pretraining a Transformer to predict rasterized image tokens autoregressively.
1 code implementation • 23 Sep 2021 • Dongqi Han, Zhiliang Wang, Wenqi Chen, Ying Zhong, Su Wang, Han Zhang, Jiahai Yang, Xingang Shi, Xia Yin
Experimental results show that DeepAID can provide high-quality interpretations for unsupervised DL models while meeting the special requirements of security domains.
no code implementations • 9 Jul 2021 • Yuan Xue, Yuan-Chen Guo, Han Zhang, Tao Xu, Song-Hai Zhang, Xiaolei Huang
In many applications of computer graphics, art and design, it is desirable for a user to provide intuitive non-image input, such as text, sketch, stroke, graph or layout, and have a computer system automatically generate photo-realistic images that adhere to the input content.
3 code implementations • ICLR 2022 • Kwonjoon Lee, Huiwen Chang, Lu Jiang, Han Zhang, Zhuowen Tu, Ce Liu
Recently, Vision Transformers (ViTs) have shown competitive performance on image recognition while requiring less vision-specific inductive biases.
Ranked #42 on
Image Generation
on CIFAR-10
no code implementations • 1 Jul 2021 • Xinlin Xia, Shang Wang, Han Zhang, Songlin Wang, Sulong Xu, Yun Xiao, Bo Long, Wen-Yun Yang
Graph convolution networks (GCN), which recently becomes new state-of-the-art method for graph node classification, recommendation and other applications, has not been successfully applied to industrial-scale search engine yet.
1 code implementation • NeurIPS 2021 • Long Zhao, Zizhao Zhang, Ting Chen, Dimitris N. Metaxas, Han Zhang
Attention-based models, exemplified by the Transformer, can effectively model long range dependency, but suffer from the quadratic complexity of self-attention operation, making them difficult to be adopted for high-resolution image generation based on Generative Adversarial Networks (GANs).
Ranked #2 on
Image Generation
on CelebA 256x256
(FID metric)
5 code implementations • 26 May 2021 • Zizhao Zhang, Han Zhang, Long Zhao, Ting Chen, Sercan O. Arik, Tomas Pfister
Hierarchical structures are popular in recent vision transformers, however, they require sophisticated designs and massive datasets to work well.
Ranked #79 on
Image Classification
on CIFAR-10
1 code implementation • 9 May 2021 • Han Zhang, Hongwei Shen, Yiming Qiu, Yunjiang Jiang, Songlin Wang, Sulong Xu, Yun Xiao, Bo Long, Wen-Yun Yang
Embedding index that enables fast approximate nearest neighbor(ANN) search, serves as an indispensable component for state-of-the-art deep retrieval systems.
2 code implementations • 26 Apr 2021 • Wei Zeng, Xiaozhe Ren, Teng Su, Hui Wang, Yi Liao, Zhiwei Wang, Xin Jiang, ZhenZhang Yang, Kaisheng Wang, Xiaoda Zhang, Chen Li, Ziyan Gong, Yifan Yao, Xinjing Huang, Jun Wang, Jianfeng Yu, Qi Guo, Yue Yu, Yan Zhang, Jin Wang, Hengtao Tao, Dasen Yan, Zexuan Yi, Fang Peng, Fangqing Jiang, Han Zhang, Lingfeng Deng, Yehong Zhang, Zhe Lin, Chao Zhang, Shaojie Zhang, Mingyue Guo, Shanzhi Gu, Gaojun Fan, YaoWei Wang, Xuefeng Jin, Qun Liu, Yonghong Tian
To enhance the generalization ability of PanGu-$\alpha$, we collect 1. 1TB high-quality Chinese data from a wide range of domains to pretrain the model.
Ranked #1 on
Reading Comprehension (Zero-Shot)
on CMRC 2018
Cloze (multi-choices) (Few-Shot)
Cloze (multi-choices) (One-Shot)
+19
no code implementations • 24 Apr 2021 • Han Zhang, Huawei Fan, Liang Wang, Xingang Wang
Reconstructing the KAM dynamics diagram of Hamiltonian system from the time series of a limited number of parameters is an outstanding question in nonlinear science, especially when the Hamiltonian governing the system dynamics are unknown.
no code implementations • 23 Apr 2021 • Han Zhang
We initialize a larger target model from a smaller source model by copy weight values from source model and padding with zeros or small initialization values on it to make the source and target model have approximate outputs, which is valid due to block matrix multiplication and residual connection in transformer structure.
1 code implementation • ICLR 2021 • Wonkwang Lee, Whie Jung, Han Zhang, Ting Chen, Jing Yu Koh, Thomas Huang, Hyungsuk Yoon, Honglak Lee, Seunghoon Hong
Despite the recent advances in the literature, existing approaches are limited to moderately short-term prediction (less than a few seconds), while extrapolating it to a longer future quickly leads to destruction in structure and content.
no code implementations • 1 Mar 2021 • Yiming Qiu, Kang Zhang, Han Zhang, Songlin Wang, Sulong Xu, Yun Xiao, Bo Long, Wen-Yun Yang
Online A/B experiments show that it improves core e-commerce business metrics significantly.
no code implementations • 16 Feb 2021 • Junzheng Wu, Biao Li, Yao Qin, Weiping Ni, Han Zhang, Yuli Sun
In this paper, a novel CD method based on the graph convolutional network (GCN) and multiscale object-based technique is proposed for both homogeneous and heterogeneous images.
1 code implementation • CVPR 2021 • Han Zhang, Jing Yu Koh, Jason Baldridge, Honglak Lee, Yinfei Yang
The quality of XMC-GAN's output is a major step up from previous models, as we show on three challenging datasets.
Ranked #19 on
Text-to-Image Generation
on COCO
(using extra training data)
1 code implementation • 15 Dec 2020 • Han Zhang, Wenhao Zheng, Charley Chen, Kevin Gao, Yao Hu, Ling Huang, Wei Xu
Meanwhile, such applications usually require modeling the intrinsic clusters in high-dimensional data, which usually displays heterogeneous statistical patterns as the patterns of different clusters may appear in different dimensions.
no code implementations • 15 Nov 2020 • Yali Guo, Han Zhang, Liang Wang, Huawei Fan, Xingang Wang
Here we investigate transfer learning of chaotic systems from the perspective of synchronization-based state inference, in which a reservoir computer trained by chaotic system A is used to infer the unmeasured variables of chaotic system B, while A is different from B in either parameter or dynamics.
2 code implementations • NAACL 2021 • Dongling Xiao, Yu-Kun Li, Han Zhang, Yu Sun, Hao Tian, Hua Wu, Haifeng Wang
We argue that such contiguously masking method neglects to model the intra-dependencies and inter-relation of coarse-grained linguistic information.
2 code implementations • ICLR 2021 • Yuliang Zou, Zizhao Zhang, Han Zhang, Chun-Liang Li, Xiao Bian, Jia-Bin Huang, Tomas Pfister
We demonstrate the effectiveness of the proposed pseudo-labeling strategy in both low-data and high-data regimes.
no code implementations • 15 Sep 2020 • Xuyun Wen, Liming Hsu, Weili Lin, Han Zhang, Dinggang Shen
By applying our proposed methodological framework on the collected longitudinal infant dataset, we provided the first evidence that, in the first 2 years of life, the brain functional network is co-evolved at different scales, where each scale displays the unique reconfiguration pattern in terms of modular organization.
2 code implementations • 5 Aug 2020 • Chengbin Hou, Han Zhang, Shan He, Ke Tang
The main and common objective of Dynamic Network Embedding (DNE) is to efficiently update node embeddings while preserving network topology at each time step.
1 code implementation • 31 Jul 2020 • Han Zhang
Training large deep neural networks needs massive high quality annotation data, but the time and labor costs are too expensive for small business.
no code implementations • 1 Jul 2020 • Songyang Zhang, Han Zhang, Shuguang Cui, Zhi Ding
Graph convolutional networks (GCN) have been recently utilized to extract the underlying structures of datasets with some labeled data and high-dimensional features.
no code implementations • 27 Jun 2020 • Han Zhang, Jialin Liu, Xin Yao
The reliable facility location problem (RFLP) is an important research topic of operational research and plays a vital role in the decision-making and management of modern supply chain and logistics.
no code implementations • 4 Jun 2020 • Zhengli Zhao, Zizhao Zhang, Ting Chen, Sameer Singh, Han Zhang
We provide new state-of-the-art results for conditional generation on CIFAR-10 with both consistency loss and contrastive loss as additional regularizations.
no code implementations • 3 Jun 2020 • Han Zhang, Songlin Wang, Kang Zhang, Zhiling Tang, Yunjiang Jiang, Yun Xiao, Weipeng Yan, Wen-Yun Yang
Two critical challenges stay in today's e-commerce search: how to retrieve items that are semantically relevant but not exact matching to query terms, and how to retrieve items that are more personalized to different users for the same search query.
6 code implementations • 10 May 2020 • Kihyuk Sohn, Zizhao Zhang, Chun-Liang Li, Han Zhang, Chen-Yu Lee, Tomas Pfister
Semi-supervised learning (SSL) has a potential to improve the predictive performance of machine learning models using unlabeled data.
Ranked #10 on
Semi-Supervised Object Detection
on COCO 100% labeled data
(using extra training data)
1 code implementation • ICLR 2020 • David Berthelot, Nicholas Carlini, Ekin D. Cubuk, Alex Kurakin, Kihyuk Sohn, Han Zhang, Colin Raffel
We improve the recently-proposed ``MixMatch semi-supervised learning algorithm by introducing two new techniques: distribution alignment and augmentation anchoring.
2 code implementations • 12 Feb 2020 • Han Zhang, Fangyi Chen, Zhiqiang Shen, Qiqi Hao, Chenchen Zhu, Marios Savvides
In this paper, we introduce a superior solution called Background Recalibration Loss (BRL) that can automatically re-calibrate the loss signals according to the pre-defined IoU threshold and input image.
no code implementations • 11 Feb 2020 • Zhengli Zhao, Sameer Singh, Honglak Lee, Zizhao Zhang, Augustus Odena, Han Zhang
Recent work has increased the performance of Generative Adversarial Networks (GANs) by enforcing a consistency cost on the discriminator.
4 code implementations • 26 Jan 2020 • Dongling Xiao, Han Zhang, Yukun Li, Yu Sun, Hao Tian, Hua Wu, Haifeng Wang
Current pre-training works in natural language generation pay little attention to the problem of exposure bias on downstream tasks.
Ranked #1 on
Question Generation
on SQuAD1.1
(using extra training data)
24 code implementations • NeurIPS 2020 • Kihyuk Sohn, David Berthelot, Chun-Liang Li, Zizhao Zhang, Nicholas Carlini, Ekin D. Cubuk, Alex Kurakin, Han Zhang, Colin Raffel
Semi-supervised learning (SSL) provides an effective means of leveraging unlabeled data to improve a model's performance.
no code implementations • 1 Dec 2019 • Han Zhang, Hong Xu
On the other hand, learning network embeddings on distributively stored networks still remained understudied: To the best of our knowledge, all existing algorithms for learning network embeddings have hitherto been exclusively centralized and thus cannot be applied to these networks.
3 code implementations • CVPR 2020 • Giannis Daras, Augustus Odena, Han Zhang, Alexandros G. Dimakis
We introduce a new local sparse attention layer that preserves two-dimensional geometry and locality.
Ranked #16 on
Conditional Image Generation
on ImageNet 128x128
3 code implementations • 21 Nov 2019 • David Berthelot, Nicholas Carlini, Ekin D. Cubuk, Alex Kurakin, Kihyuk Sohn, Han Zhang, Colin Raffel
Distribution alignment encourages the marginal distribution of predictions on unlabeled data to be close to the marginal distribution of ground-truth labels.
no code implementations • WS 2019 • James Route, Steven Hillis, Isak Czeresnia Etinger, Han Zhang, Alan W. black
Grapheme-to-phoneme conversion (g2p) is the task of predicting the pronunciation of words from their orthographic representation.
no code implementations • ICML 2020 • Samarth Sinha, Han Zhang, Anirudh Goyal, Yoshua Bengio, Hugo Larochelle, Augustus Odena
Recent work by Brock et al. (2018) suggests that Generative Adversarial Networks (GANs) benefit disproportionately from large mini-batch sizes.
no code implementations • ICLR 2020 • Han Zhang, Zizhao Zhang, Augustus Odena, Honglak Lee
Generative Adversarial Networks (GANs) are known to be difficult to train, despite considerable research effort.
Ranked #5 on
Conditional Image Generation
on ArtBench-10 (32x32)
no code implementations • 18 Oct 2019 • Xi Gao, Han Zhang, Aliakbar Panahi, Tom Arodz
When samples have internal structure, we often see a mismatch between the objective optimized during training and the model's goal during inference.
2 code implementations • CVPR 2020 • Zizhao Zhang, Han Zhang, Sercan O. Arik, Honglak Lee, Tomas Pfister
For instance, on CIFAR100 with a $40\%$ uniform noise ratio and only 10 trusted labeled data per class, our method achieves $80. 2{\pm}0. 3\%$ classification accuracy, where the error rate is only $1. 4\%$ higher than a neural network trained without label noise.
no code implementations • 10 Sep 2019 • Haidong Rong, Yangzihao Wang, Feihu Zhou, Junjie Zhai, Haiyang Wu, Rui Lan, Fan Li, Han Zhang, Yuekui Yang, Zhenyu Guo, Di Wang
We present Distributed Equivalent Substitution (DES) training, a novel distributed training framework for large-scale recommender systems with dynamic sparse features.
no code implementations • 22 Aug 2019 • Qi Bi, Kun Qin, Zhili Li, Han Zhang, Kai Xu
While the current convolution neural network tends to extract global features and global semantic information in a scene, the geo-spatial objects can be located at anywhere in an aerial image scene and their spatial arrangement tends to be more complicated.
no code implementations • 22 Aug 2019 • Qi Bi, Kun Qin, Han Zhang, Wenjun Han, Zhili Li, Kai Xu
Exhaustive experiments indicate that the proposed method can detect building change types directly and outperform the current multi-index learning method.
no code implementations • ICML 2020 • Han Zhang, Xi Gao, Jacob Unterman, Tom Arodz
Neural ODEs and i-ResNet are recently proposed methods for enforcing invertibility of residual neural models.
2 code implementations • arXiv 2019 • Chengbin Hou, Han Zhang, Ke Tang, Shan He
Dynamic network embedding aims to learn low dimensional embeddings for unseen and seen nodes by using any currently available snapshots of a dynamic network.
1 code implementation • 17 Jun 2019 • Zhen Zhou, Xiaobo Chen, Yu Zhang, Lishan Qiao, Renping Yu, Gang Pan, Han Zhang, Dinggang Shen
The goal of this work is to introduce a toolbox namely "Brain Network Construction and Classification" (BrainNetClass) to the field to promote more advanced brain network construction methods.
8 code implementations • 19 Apr 2019 • Yu Sun, Shuohuan Wang, Yukun Li, Shikun Feng, Xuyi Chen, Han Zhang, Xin Tian, Danxiang Zhu, Hao Tian, Hua Wu
We present a novel language representation model enhanced by knowledge called ERNIE (Enhanced Representation through kNowledge IntEgration).
Ranked #3 on
Chinese Sentiment Analysis
on ChnSentiCorp Dev
Chinese Named Entity Recognition
Chinese Sentence Pair Classification
+7
no code implementations • 13 Mar 2019 • Shuai Ma, Jiahui Dai, Songtao Lu, Hang Li, Han Zhang, Chun Du, Shiyin Li
The dataset is available online, which contains eight types of modulated signals.
no code implementations • 8 Mar 2019 • Hongmei Wang, Zhenzhen Wu, Shuai Ma, Songtao Lu, Han Zhang, Guoru Ding, Shiyin Li
In this paper, we investigate deep learning (DL)-enabled signal demodulation methods and establish the first open dataset of real modulated signals for wireless communication systems.
no code implementations • 26 Dec 2018 • Han Zhang, Bo Ai, Wenjun Xu, Li Xu, Shuguang Cui
Channel interpolation is an essential technique for providing high-accuracy estimation of the channel state information (CSI) for wireless systems design where the frequency-space structural correlations of multi-antenna channel are typically hidden in matrix or tensor forms.
no code implementations • EMNLP 2018 • Weikang Wang, Jiajun Zhang, Han Zhang, Mei-Yuh Hwang, Cheng-qing Zong, Zhifei Li
Specifically, the {``}student{''} is an extended dialog manager based on a new ontology, and the {``}teacher{''} is existing resources used for guiding the learning process of the {``}student{''}.
1 code implementation • 31 Aug 2018 • Rongzhao Zhang, Han Zhang, Albert C. S. Chung
In this work, we present a unified mammogram analysis framework for both whole-mammogram classification and segmentation.
no code implementations • 30 Aug 2018 • Weizheng Yan, Han Zhang, Jing Sui, Dinggang Shen
Dynamic functional connectivity (dFC), consisting of time-varying spatiotemporal dynamics, may characterize "chronnectome" diagnostic information for improving MCI classification.
48 code implementations • arXiv 2018 • Han Zhang, Ian Goodfellow, Dimitris Metaxas, Augustus Odena
In this paper, we propose the Self-Attention Generative Adversarial Network (SAGAN) which allows attention-driven, long-range dependency modeling for image generation tasks.
Ranked #17 on
Conditional Image Generation
on ImageNet 128x128
2 code implementations • ICLR 2018 • Tim Salimans, Han Zhang, Alec Radford, Dimitris Metaxas
We present Optimal Transport GAN (OT-GAN), a variant of generative adversarial nets minimizing a new metric measuring the distance between the generator distribution and the data distribution.
17 code implementations • CVPR 2018 • Tao Xu, Pengchuan Zhang, Qiuyuan Huang, Han Zhang, Zhe Gan, Xiaolei Huang, Xiaodong He
In this paper, we propose an Attentional Generative Adversarial Network (AttnGAN) that allows attention-driven, multi-stage refinement for fine-grained text-to-image generation.
Ranked #6 on
Text-to-Image Generation
on Multi-Modal-CelebA-HQ
16 code implementations • 19 Oct 2017 • Han Zhang, Tao Xu, Hongsheng Li, Shaoting Zhang, Xiaogang Wang, Xiaolei Huang, Dimitris Metaxas
In this paper, we propose Stacked Generative Adversarial Networks (StackGAN) aiming at generating high-resolution photo-realistic images.
Ranked #5 on
Text-to-Image Generation
on Oxford 102 Flowers
no code implementations • CVPR 2017 • Mohamed Elhoseiny, Yizhe Zhu, Han Zhang, Ahmed Elgammal
We propose a learning framework that is able to connect text terms to its relevant parts and suppress connections to non-visual text terms without any part-text annotations.
2 code implementations • 6 Jun 2017 • Yuan Xue, Tao Xu, Han Zhang, Rodney Long, Xiaolei Huang
Extensive experimental results demonstrate the effectiveness of the proposed SegAN with multi-scale loss: on BRATS 2013 SegAN gives performance comparable to the state-of-the-art for whole tumor and tumor core segmentation while achieves better precision and sensitivity for Gd-enhance tumor core segmentation; on BRATS 2015 SegAN achieves better performance than the state-of-the-art in both dice score and precision.
Ranked #1 on
Brain Tumor Segmentation
on BRATS-2013 leaderboard
21 code implementations • ICCV 2017 • Han Zhang, Tao Xu, Hongsheng Li, Shaoting Zhang, Xiaogang Wang, Xiaolei Huang, Dimitris Metaxas
Synthesizing high-quality images from text descriptions is a challenging problem in computer vision and has many practical applications.
Ranked #3 on
Text-to-Image Generation
on Oxford 102 Flowers
(Inception score metric)
no code implementations • CVPR 2016 • Han Zhang, Tao Xu, Mohamed Elhoseiny, Xiaolei Huang, Shaoting Zhang, Ahmed Elgammal, Dimitris Metaxas
In this paper, we propose a new CNN architecture that integrates semantic part detection and abstraction (SPDA-CNN) for fine-grained classification.
no code implementations • 6 Nov 2015 • Xu Chen, Han Zhang, Judith Gelernter
Our results for geoparsing Chinese and Arabic text using our multi-lingual geoparsing method are comparable to our results for geoparsing English text with our English tools.