1 code implementation • Findings (EMNLP) 2021 • Yang song, Xin Cai Ong, Hwee Tou Ng, Qian Lin
Current state-of-the-art supervised word sense disambiguation (WSD) systems (such as GlossBERT and bi-encoder model) yield surprisingly good results by purely leveraging pre-trained language models and short dictionary definitions (or glosses) of the different word senses.
Ranked #2 on
Word Sense Disambiguation
on Supervised:
1 code implementation • 3 May 2022 • Yu Tian, Jianxin Chang, Yannan Niu, Yang song, Chenliang Li
Specifically, multi-interest methods such as ComiRec and MIMN, focus on extracting different interests for a user by performing historical item clustering, while graph convolution methods including TGSRec and SURGE elect to refine user preferences based on multi-level correlations between historical items.
1 code implementation • 2 May 2022 • Yuqian Chen, Chaoyi Zhang, Tengfei Xue, Yang song, Nikos Makris, Yogesh Rathi, Weidong Cai, Fan Zhang, Lauren J. O'Donnell
In this work, we propose a novel deep learning framework for WMFC, Deep Fiber Clustering (DFC), which solves the unsupervised clustering problem as a self-supervised learning task with a domain-specific pretext task to predict pairwise fiber distances.
no code implementations • 4 Apr 2022 • Jiyang Jiang, Dadong Wang, Yang song, Perminder S. Sachdev, Wei Wen
Cerebral small vessel disease (CSVD) is a major vascular contributor to cognitive impairment in ageing, including dementias.
no code implementations • 27 Mar 2022 • Yupeng Hou, Xingyu Pan, Wayne Xin Zhao, Shuqing Bian, Yang song, Tao Zhang, Ji-Rong Wen
As the core technique of online recruitment platforms, person-job fit can improve hiring efficiency by accurately matching job positions with qualified candidates.
no code implementations • 17 Mar 2022 • Peibo Li, Yixing Yang, Maurice Pagnucco, Yang song
Graph neural networks (GNNs) have been extensively developed for graph representation learning in various application domains.
no code implementations • 11 Mar 2022 • Tiange Xiang, Chaoyi Zhang, Xinyi Wang, Yang song, Dongnan Liu, Heng Huang, Weidong Cai
With the backward skip connections, we propose a U-Net based network family, namely Bi-directional O-shape networks, which set new benchmarks on multiple public medical imaging segmentation datasets.
1 code implementation • 10 Mar 2022 • Lei Fan, Yiwen Ding, Dongdong Fan, Donglin Di, Maurice Pagnucco, Yang song
To the best of our knowledge, GrainSpace is the first publicly released dataset for cereal grain inspection.
1 code implementation • ICLR 2022 • Minkai Xu, Lantao Yu, Yang song, Chence Shi, Stefano Ermon, Jian Tang
GeoDiff treats each atom as a particle and learns to directly reverse the diffusion process (i. e., transforming from a noise distribution to stable conformations) as a Markov chain.
1 code implementation • 28 Feb 2022 • Yunhao Du, Yang song, Bo Yang, Yanyun Zhao
By integrating StrongSORT with the two algorithms, the final tracker StrongSORT++ ranks first on MOT17 and MOT20 in terms of HOTA and IDF1 metrics and surpasses the second-place one by 1. 3 - 2. 2.
Ranked #2 on
Multi-Object Tracking
on MOT17
(using extra training data)
1 code implementation • 26 Feb 2022 • Yu Zheng, Chen Gao, Jianxin Chang, Yanan Niu, Yang song, Depeng Jin, Yong Li
Modeling user's long-term and short-term interests is crucial for accurate recommendation.
1 code implementation • 9 Feb 2022 • Zihua Si, Xueran Han, Xiao Zhang, Jun Xu, Yue Yin, Yang song, Ji-Rong Wen
In this paper, we propose a model-agnostic framework named IV4Rec that can effectively decompose the embedding vectors into these two parts, hence enhancing recommendation results.
1 code implementation • 29 Jan 2022 • Tengfei Xue, Fan Zhang, Chaoyi Zhang, Yuqian Chen, Yang song, Nikos Makris, Yogesh Rathi, Weidong Cai, Lauren J. O'Donnell
Most parcellation methods focus on the deep white matter (DWM), while fewer methods address the superficial white matter (SWM) due to its complexity.
no code implementations • 25 Jan 2022 • Peng Wang, Zihuai Lin, Xucun Yan, Zijiao Chen, Ming Ding, Yang song, Lu Meng
Cardiovascular disease has become one of the most significant threats endangering human life and health.
1 code implementation • 6 Jan 2022 • Dongnan Liu, Chaoyi Zhang, Yang song, Heng Huang, Chenyu Wang, Michael Barnett, Weidong Cai
Recent advances in unsupervised domain adaptation (UDA) techniques have witnessed great success in cross-domain computer vision tasks, enhancing the generalization ability of data-driven deep learning architectures by bridging the domain distribution gaps.
no code implementations • 22 Dec 2021 • Jingxiao Zheng, Xinwei Shi, Alexander Gorban, Junhua Mao, Yang song, Charles R. Qi, Ting Liu, Visesh Chari, Andre Cornman, Yin Zhou, CongCong Li, Dragomir Anguelov
3D human pose estimation (HPE) in autonomous vehicles (AV) differs from other use cases in many factors, including the 3D resolution and range of data, absence of dense depth maps, failure modes for LiDAR, relative location between the camera and LiDAR, and a high bar for estimation accuracy.
1 code implementation • 9 Dec 2021 • Jianhui Yu, Chaoyi Zhang, Heng Wang, Dingxin Zhang, Yang song, Tiange Xiang, Dongnan Liu, Weidong Cai
General point clouds have been increasingly investigated for different tasks, and recently Transformer-based networks are proposed for point cloud analysis.
Ranked #1 on
3D Point Cloud Classification
on IntrA
1 code implementation • 22 Nov 2021 • Kristy Choi, Chenlin Meng, Yang song, Stefano Ermon
We then estimate the instantaneous rate of change of the bridge distributions indexed by time (the "time score") -- a quantity defined analogously to data (Stein) scores -- with a novel time score matching objective.
no code implementations • NeurIPS Workshop Deep_Invers 2021 • Yang song, Liyue Shen, Lei Xing, Stefano Ermon
These measurements are typically synthesized from images using a fixed physical model of the measurement process, which hinders the generalization capability of models to unknown measurement processes.
no code implementations • NeurIPS 2021 • Chenlin Meng, Yang song, Wenzhe Li, Stefano Ermon
By leveraging Tweedie's formula on higher order moments, we generalize denoising score matching to estimate higher order derivatives.
no code implementations • NeurIPS 2021 • Lantao Yu, Jiaming Song, Yang song, Stefano Ermon
Energy-based models (EBMs) offer flexible distribution parametrization.
2 code implementations • NeurIPS 2021 • Qiyu Kang, Yang song, Qinxu Ding, Wee Peng Tay
By ensuring that the equilibrium points of the ODE solution used as part of SODEF is Lyapunov-stable, the ODE solution for an input with a small perturbation converges to the same solution as the unperturbed input.
no code implementations • 1 Oct 2021 • Roland S. Zimmermann, Lukas Schott, Yang song, Benjamin A. Dunn, David A. Klindt
In this work, we investigate score-based generative models as classifiers for natural images.
no code implementations • 28 Sep 2021 • Yiyu Liu, Qian Liu, Yu Tian, Changping Wang, Yanan Niu, Yang song, Chenliang Li
In this paper, we propose a novel concept-aware denoising graph neural network (named CONDE) for micro-video recommendation.
no code implementations • 13 Sep 2021 • Tiange Xiang, Yang song, Chaoyi Zhang, Dongnan Liu, Mei Chen, Fan Zhang, Heng Huang, Lauren O'Donnell, Weidong Cai
With image-level labels only, patch-wise classification would be sub-optimal due to inconsistency between the patch appearance and image-level label.
no code implementations • 14 Aug 2021 • Heng Wang, Chaoyi Zhang, Jianhui Yu, Yang song, SiQi Liu, Wojciech Chrzanowski, Weidong Cai
Recently, a series of deep learning based segmentation methods have been proposed to improve the quality of raw 3D optical image stacks by removing noises and restoring neuronal structures from low-contrast background.
1 code implementation • 8 Aug 2021 • Yang Bai, Junyan Wang, Yang Long, Bingzhang Hu, Yang song, Maurice Pagnucco, Yu Guan
Video captioning aims to automatically generate natural language sentences that can describe the visual contents of a given video.
1 code implementation • ICLR 2022 • Chenlin Meng, Yutong He, Yang song, Jiaming Song, Jiajun Wu, Jun-Yan Zhu, Stefano Ermon
The key challenge is balancing faithfulness to the user input (e. g., hand-drawn colored strokes) and realism of the synthesized image.
no code implementations • 11 Jul 2021 • Yuqian Chen, Chaoyi Zhang, Yang song, Nikos Makris, Yogesh Rathi, Weidong Cai, Fan Zhang, Lauren J. O'Donnell
White matter fiber clustering (WMFC) enables parcellation of white matter tractography for applications such as disease classification and anatomical tract segmentation.
1 code implementation • NeurIPS 2021 • Yusuke Tashiro, Jiaming Song, Yang song, Stefano Ermon
In this paper, we propose Conditional Score-based Diffusion models for Imputation (CSDI), a novel time series imputation method that utilizes score-based diffusion models conditioned on observed data.
no code implementations • ACL 2021 • Xiaoxue Zang, Lijuan Liu, Maria Wang, Yang song, Hao Zhang, Jindong Chen
Based on this dataset, we propose two tasks to facilitate research on image-text modeling: a photo-sharing intent prediction task that predicts whether one intends to share a photo in the next conversation turn, and a photo retrieval task that retrieves the most relevant photo according to the dialogue context.
1 code implementation • 27 Jun 2021 • Jianxin Chang, Chen Gao, Yu Zheng, Yiqun Hui, Yanan Niu, Yang song, Depeng Jin, Yong Li
This helps explicitly distinguish users' core interests, by forming dense clusters in the interest graph.
1 code implementation • 26 Jun 2021 • Xinyi Wang, Tiange Xiang, Chaoyi Zhang, Yang song, Dongnan Liu, Heng Huang, Weidong Cai
We evaluate BiX-NAS on two segmentation tasks using three different medical image datasets, and the experimental results show that our BiX-NAS searched architecture achieves the state-of-the-art performance with significantly lower computational cost.
1 code implementation • 3 Jun 2021 • Tiange Xiang, Chaoyi Zhang, Yang song, SiQi Liu, Hongliang Yuan, Weidong Cai
This add-on graph regularizes the network during training and can be completely skipped during inference.
2 code implementations • ICCV 2021 • Tiange Xiang, Chaoyi Zhang, Yang song, Jianhui Yu, Weidong Cai
Discrete point cloud objects lack sufficient shape descriptors of 3D geometries.
Ranked #4 on
3D Point Cloud Classification
on ModelNet40
no code implementations • 20 Apr 2021 • Yang Ma, Chaoyi Zhang, Mariano Cabezas, Yang song, Zihao Tang, Dongnan Liu, Weidong Cai, Michael Barnett, Chenyu Wang
Further, we review technical strategies, such as domain adaptation, to enhance MS lesion segmentation in real-world clinical settings.
no code implementations • ICLR 2021 • Chenlin Meng, Jiaming Song, Yang song, Shengjia Zhao, Stefano Ermon
While autoregressive models excel at image compression, their sample quality is often lacking.
1 code implementation • CVPR 2021 • Chaoyi Zhang, Jianhui Yu, Yang song, Weidong Cai
Scene understanding is a critical problem in computer vision.
1 code implementation • ICLR 2021 • Yilun Xu, Yang song, Sahaj Garg, Linyuan Gong, Rui Shu, Aditya Grover, Stefano Ermon
Experimentally, we demonstrate in several image and audio generation tasks that sample quality degrades gracefully as we reduce the computational budget for sampling.
no code implementations • 20 Feb 2021 • Yuqian Chen, Yang song, Chaoyi Zhang, Fan Zhang, Lauren O'Donnell, Wojciech Chrzanowski, Weidong Cai
Cell segmentation and tracking in microscopy images are of great significance to new discoveries in biology and medicine.
2 code implementations • NeurIPS 2021 • Yang song, Conor Durkan, Iain Murray, Stefano Ermon
Score-based diffusion models synthesize samples by reversing a stochastic process that diffuses data to noise, and are trained by minimizing a weighted combination of score matching losses.
Ranked #5 on
Image Generation
on ImageNet 32x32
(bpd metric)
no code implementations • 22 Jan 2021 • Heng Wang, Yang song, Chaoyi Zhang, Jianhui Yu, SiQi Liu, Hanchuan Peng, Weidong Cai
One of the critical steps in improving accurate single neuron reconstruction from three-dimensional (3D) optical microscope images is the neuronal structure segmentation.
2 code implementations • 9 Jan 2021 • Yang song, Diederik P. Kingma
Energy-Based Models (EBMs), also known as non-normalized probabilistic models, specify probability density or mass functions up to an unknown normalizing constant.
no code implementations • 1 Jan 2021 • Laëtitia Shao, Yang song, Stefano Ermon
Although deep neural networks are effective on supervised learning tasks, they have been shown to be brittle.
no code implementations • EMNLP 2021 • Xinying Song, Alex Salcianu, Yang song, Dave Dopson, Denny Zhou
For general text, we further propose an algorithm that combines pre-tokenization (splitting the text into words) and our linear-time WordPiece method into a single pass.
1 code implementation • ICLR 2021 • Ruiqi Gao, Yang song, Ben Poole, Ying Nian Wu, Diederik P. Kingma
Inspired by recent progress on diffusion probabilistic models, we present a diffusion recovery likelihood method to tractably learn and sample from a sequence of EBMs trained on increasingly noisy versions of a dataset.
Ranked #6 on
Image Generation
on CelebA 64x64
6 code implementations • ICLR 2021 • Yang song, Jascha Sohl-Dickstein, Diederik P. Kingma, Abhishek Kumar, Stefano Ermon, Ben Poole
Combined with multiple architectural improvements, we achieve record-breaking performance for unconditional image generation on CIFAR-10 with an Inception score of 9. 89 and FID of 2. 20, a competitive likelihood of 2. 99 bits/dim, and demonstrate high fidelity generation of 1024 x 1024 images for the first time from a score-based generative model.
Ranked #5 on
Image Generation
on CIFAR-10
no code implementations • NeurIPS 2020 • Chenlin Meng, Lantao Yu, Yang song, Jiaming Song, Stefano Ermon
To increase flexibility, we propose autoregressive conditional score models (AR-CSM) where we parameterize the joint distribution in terms of the derivatives of univariate log-conditionals (scores), which need not be normalized.
no code implementations • NeurIPS 2021 • Kuno Kim, Akshat Jindal, Yang song, Jiaming Song, Yanan Sui, Stefano Ermon
We propose a new framework for Imitation Learning (IL) via density estimation of the expert's occupancy measure followed by Maximum Occupancy Entropy Reinforcement Learning (RL) using the density as a reward.
no code implementations • 5 Oct 2020 • Laëtitia Shao, Yang song, Stefano Ermon
From this observation, we develop a detection criteria for samples on which a classifier is likely to fail at test time.
no code implementations • 25 Sep 2020 • Shuqing Bian, Xu Chen, Wayne Xin Zhao, Kun Zhou, Yupeng Hou, Yang song, Tao Zhang, Ji-Rong Wen
Compared with pure text-based matching models, the proposed approach is able to learn better data representations from limited or even sparse interaction data, which is more resistible to noise in training data.
1 code implementation • 11 Sep 2020 • Dongnan Liu, Donghao Zhang, Yang song, Fan Zhang, Lauren O'Donnell, Heng Huang, Mei Chen, Weidong Cai
In this work, we present an unsupervised domain adaptation (UDA) method, named Panoptic Domain Adaptive Mask R-CNN (PDAM), for unsupervised instance segmentation in microscopy images.
1 code implementation • NeurIPS 2020 • Tianyu Pang, Kun Xu, Chongxuan Li, Yang song, Stefano Ermon, Jun Zhu
Several machine learning applications involve the optimization of higher-order derivatives (e. g., gradients of gradients) during training, which can be expensive in respect to memory and computation even with automatic differentiation.
1 code implementation • 1 Jul 2020 • Tiange Xiang, Chaoyi Zhang, Dongnan Liu, Yang song, Heng Huang, Weidong Cai
U-Net has become one of the state-of-the-art deep learning-based approaches for modern computer vision tasks such as semantic segmentation, super resolution, image denoising, and inpainting.
7 code implementations • NeurIPS 2020 • Yang Song, Stefano Ermon
Score-based generative models can produce high quality image samples comparable to GANs, without requiring adversarial optimization.
Ranked #43 on
Image Generation
on CIFAR-10
no code implementations • 30 May 2020 • Yunkai Xiao, Gabriel Zingle, Qinjin Jia, Harsh R. Shah, Yi Zhang, Tianyi Li, Mohsin Karovaliya, Weixiang Zhao, Yang song, Jie Ji, Ashwin Balasubramaniam, Harshit Patel, Priyankha Bhalasubbramanian, Vikram Patel, Edward F. Gehringer
We attempt to automate the process of deciding whether a review comment detects a problem.
no code implementations • 11 May 2020 • Yi-Hong Zhang, Jing Zhang, Yang song, Chaomin Shen, Guang Yang
Prostate cancer (PCa) is one of the most common cancers in men around the world.
1 code implementation • 9 May 2020 • Jianhui Yu, Chaoyi Zhang, Yang song, Weidong Cai
Micro-expressions are reflections of people's true feelings and motives, which attract an increasing number of researchers into the study of automatic facial micro-expression recognition.
1 code implementation • CVPR 2020 • Dongnan Liu, Donghao Zhang, Yang song, Fan Zhang, Lauren O'Donnell, Heng Huang, Mei Chen, Weidong Cai
More specifically, we first propose a nuclei inpainting mechanism to remove the auxiliary generated objects in the synthesized images.
no code implementations • 20 Apr 2020 • Chaoyi Zhang, Yang song, Lina Yao, Weidong Cai
Point cloud is a principal data structure adopted for 3D geometric information encoding.
no code implementations • ECCV 2020 • Shuyang Cheng, Zhaoqi Leng, Ekin Dogus Cubuk, Barret Zoph, Chunyan Bai, Jiquan Ngiam, Yang song, Benjamin Caine, Vijay Vasudevan, Cong-Cong Li, Quoc V. Le, Jonathon Shlens, Dragomir Anguelov
Data augmentation has been widely adopted for object detection in 3D point clouds.
1 code implementation • NeurIPS 2020 • Yusuke Tashiro, Yang song, Stefano Ermon
Adversarial attacks often involve random perturbations of the inputs drawn from uniform or Gaussian distributions, e. g., to initialize optimization-based white-box attacks or generate update directions in black-box attacks.
1 code implementation • ICML 2020 • Lantao Yu, Yang song, Jiaming Song, Stefano Ermon
Experimental results demonstrate the superiority of f-EBM over contrastive divergence, as well as the benefits of training EBMs using f-divergences other than KL.
3 code implementations • 4 Mar 2020 • Chenlin Meng, Yang song, Jiaming Song, Stefano Ermon
Iterative Gaussianization is a fixed-point iteration procedure that can transform any continuous random vector into a Gaussian one.
1 code implementation • 2 Mar 2020 • Chenhao Niu, Yang song, Jiaming Song, Shengjia Zhao, Aditya Grover, Stefano Ermon
In particular, we design a permutation equivariant, multi-channel graph neural network to model the gradient of the data distribution at the input graph (a. k. a., the score function).
1 code implementation • 15 Feb 2020 • Dongnan Liu, Donghao Zhang, Yang song, Heng Huang, Weidong Cai
Specifically, our proposed PFFNet contains a residual attention feature fusion mechanism to incorporate the instance prediction with the semantic features, in order to facilitate the semantic contextual information learning in the instance branch.
1 code implementation • 10 Feb 2020 • Yang Song, Chenlin Meng, Renjie Liao, Stefano Ermon
Feedforward computation, such as evaluating a neural network or sampling from an autoregressive model, is ubiquitous in machine learning.
no code implementations • 14 Dec 2019 • Heng Wang, Donghao Zhang, Yang song, Heng Huang, Mei Chen, Weidong Cai
Our contribution consists of the proposal of a significant task worth investigating and a naive baseline of solving it.
no code implementations • 30 Nov 2019 • Yang Song, Qiyu Kang, Wee Peng Tay
Though deep learning has been applied successfully in many scenarios, malicious inputs with human-imperceptible perturbations can make it vulnerable in real applications.
no code implementations • IJCNLP 2019 • Shuqing Bian, Wayne Xin Zhao, Yang song, Tao Zhang, Ji-Rong Wen
Furthermore, we extend the match network and implement domain adaptation in three levels, sentence-level representation, sentence-level match, and global match.
no code implementations • 21 Oct 2019 • Jiaming Song, Yang song, Stefano Ermon
Based on this insight, we propose to exploit in-batch dependencies for OoD detection.
2 code implementations • NeurIPS 2019 • Renjie Liao, Yujia Li, Yang Song, Shenlong Wang, Charlie Nash, William L. Hamilton, David Duvenaud, Raquel Urtasun, Richard S. Zemel
Our model generates graphs one block of nodes and associated edges at a time.
1 code implementation • IJCNLP 2019 • Yao Zhu, Hongzhi Liu, Zhonghai Wu, Yang song, Tao Zhang
Recently, a few methods take relation paths into consideration but pay less attention to the order of relations in paths which is important for reasoning.
Ranked #3 on
Link Prediction
on FB15k
(MR metric)
no code implementations • EACL 2021 • Sanqiang Zhao, Raghav Gupta, Yang song, Denny Zhou
Pretrained language models like BERT have achieved good results on NLP tasks, but are impractical on resource-limited devices due to memory footprint.
no code implementations • 25 Sep 2019 • Shengjia Zhao, Yang song, Stefano Ermon
Our defense draws inspiration from differential privacy, and is based on intentionally adding noise to the classifier's outputs to limit the attacker's knowledge about the parameters.
no code implementations • 22 Aug 2019 • Hongzhi Wang, Yijie Yang, Yang song
In industrial data analytics, one of the fundamental problems is to utilize the temporal correlation of the industrial data to make timely predictions in the production process, such as fault prediction and yield prediction.
1 code implementation • International Joint Conference on Artificial Intelligence (IJCAI-19) 2019 • Dongnan Liu, Donghao Zhang, Yang song, Chaoyi Zhang, Fan Zhang, Lauren O’Donnell, Weidong Cai
Automated detection and segmentation of individual nuclei in histopathology images is important for cancer diagnosis and prognosis.
no code implementations • 9 Aug 2019 • Hongzhi Wang, Yang song, Shihan Tang
In this paper, a method of prediction on continuous time series variables from the production or flow -- an LSTM algorithm based on multivariate tuning -- is proposed.
1 code implementation • NeurIPS 2019 • Yang Song, Chenlin Meng, Stefano Ermon
To demonstrate their flexibility, we show that our invertible neural networks are competitive with ResNets on MNIST and CIFAR-10 classification.
Ranked #4 on
Image Generation
on MNIST
10 code implementations • NeurIPS 2019 • Yang Song, Stefano Ermon
We introduce a new generative model where samples are produced via Langevin dynamics using gradients of the data distribution estimated with score matching.
Ranked #75 on
Image Generation
on CIFAR-10
1 code implementation • ACL 2019 • Junyi Li, Wayne Xin Zhao, Ji-Rong Wen, Yang song
In this paper, we propose a novel review generation model by characterizing an elaborately designed aspect-aware coarse-to-fine generation process.
1 code implementation • 4 Jun 2019 • Grace Chu, Brian Potetz, Weijun Wang, Andrew Howard, Yang song, Fernando Brucher, Thomas Leung, Hartwig Adam
By leveraging geolocation information we improve top-1 accuracy in iNaturalist from 70. 1% to 79. 0% for a strong baseline image-only model.
6 code implementations • 17 May 2019 • Yang Song, Sahaj Garg, Jiaxin Shi, Stefano Ermon
However, it has been so far limited to simple, shallow models or low-dimensional data, due to the difficulty of computing the Hessian of log-density functions.
7 code implementations • CVPR 2019 • Yin Cui, Menglin Jia, Tsung-Yi Lin, Yang song, Serge Belongie
We design a re-weighting scheme that uses the effective number of samples for each class to re-balance the loss, thereby yielding a class-balanced loss.
Ranked #2 on
Long-tail Learning
on EGTEA
1 code implementation • 3 Dec 2018 • Zhibo Wang, Mengkai Song, Zhifei Zhang, Yang song, Qian Wang, Hairong Qi
Although the state-of-the-art attacking techniques that incorporated the advance of Generative adversarial networks (GANs) could construct class representatives of the global data distribution among all clients, it is still challenging to distinguishably attack a specific client (i. e., user-level privacy leakage), which is a stronger privacy threat to precisely recover the private data from a specific client.
no code implementations • MICCAI 2018 2018 • Donghao Zhang, Yang song, Dongnan Liu, Haozhe Jia, Si-Qi Liu, Yong Xia, Heng Huang, Weidong Cai
The morphological clues of various cancer cells are essential for pathologists to determine the stages of cancers.
Ranked #1 on
Nuclear Segmentation
on Cell17
no code implementations • 21 Sep 2018 • Chen Gao, Xiangnan He, Dahua Gan, Xiangning Chen, Fuli Feng, Yong Li, Tat-Seng Chua, Lina Yao, Yang song, Depeng Jin
To fully exploit the signal in the data of multiple types of behaviors, we perform a joint optimization based on the multi-task learning framework, where the optimization on a behavior is treated as a task.
no code implementations • 31 Jul 2018 • Qijie Zhao, Feng Ni, Yang song, Yongtao Wang, Zhi Tang
Specifically, a synthesizing method was proposed to generate well-annotated images containing barcode and QR code labels, which contributes to largely decrease the annotation time.
no code implementations • 18 Jul 2018 • Haozhe Jia, Yang song, Donghao Zhang, Heng Huang, Dagan Feng, Michael Fulham, Yong Xia, Weidong Cai
In this paper, we propose a 3D Global Convolutional Adversarial Network (3D GCA-Net) to address efficient prostate MR volume segmentation.
1 code implementation • CVPR 2018 • Yin Cui, Yang song, Chen Sun, Andrew Howard, Serge Belongie
We propose a measure to estimate domain similarity via Earth Mover's Distance and demonstrate that transfer learning benefits from pre-training on a source domain that is similar to the target domain by this measure.
Ranked #16 on
Fine-Grained Image Classification
on CUB-200-2011
Fine-Grained Image Classification
Fine-Grained Visual Categorization
+1
1 code implementation • NeurIPS 2018 • Yang Song, Rui Shu, Nate Kushman, Stefano Ermon
Then, conditioned on a desired class, we search over the AC-GAN latent space to find images that are likely under the generative model and are misclassified by a target classifier.
1 code implementation • 13 Apr 2018 • Yang Song, Jingwen Zhu, Dawei Li, Xiaolong Wang, Hairong Qi
Given an arbitrary face image and an arbitrary speech clip, the proposed work attempts to generating the talking face video with accurate lip synchronization while maintaining smooth transition of both lip and facial movement over the entire video clip.
2 code implementations • ICML 2018 • Yang Song, Jiaming Song, Stefano Ermon
An appealing property of the natural gradient is that it is invariant to arbitrary differentiable reparameterizations of the model.
1 code implementation • 21 Jan 2018 • Zhifei Zhang, Yang song, Hairong Qi
Incorporating encoding-decoding nets with adversarial nets has been widely adopted in image generation tasks.
1 code implementation • ICLR 2018 • Yang Song, Taesup Kim, Sebastian Nowozin, Stefano Ermon, Nate Kushman
Adversarial perturbations of normal images are usually imperceptible to humans, but they can seriously confuse state-of-the-art machine learning models.
no code implementations • ICCV 2017 • Yang Song, Fan Zhang, Qing Li, Heng Huang, Lauren J. O'Donnell, Weidong Cai
Texture classification has been extensively studied in computer vision.
no code implementations • 23 Jul 2017 • Alireza Rahimpour, Liu Liu, Ali Taalimi, Yang song, Hairong Qi
Despite recent attempts for solving the person re-identification problem, it remains a challenging task since a person's appearance can vary significantly when large variations in view angle, human pose, and illumination are involved.
7 code implementations • CVPR 2018 • Grant Van Horn, Oisin Mac Aodha, Yang song, Yin Cui, Chen Sun, Alex Shepard, Hartwig Adam, Pietro Perona, Serge Belongie
Existing image classification datasets used in computer vision tend to have a uniform distribution of images across object categories.
Ranked #6 on
Image Classification
on iNaturalist
no code implementations • 19 Jul 2017 • Yang Song, Yuan Li, Bo Wu, Chao-Yeh Chen, Xiao Zhang, Hartwig Adam
To ease the training difficulty, a novel learning scheme is proposed by using the output from specialized models as learning targets so that L2 loss can be used instead of triplet loss.
no code implementations • 2 Jun 2017 • Yang Song, Zhifei Zhang, Hairong Qi
A more generalized question is that if a large proportion (e. g., more than 50%) of the face/sketch is missing, can a realistic whole face sketch/image still be estimated.
4 code implementations • CVPR 2017 • Zhifei Zhang, Yang song, Hairong Qi
In CAAE, the face is first mapped to a latent vector through a convolutional encoder, and then the vector is projected to the face manifold conditional on age through a deconvolutional generator.
no code implementations • NeurIPS 2016 • Chang Liu, Jun Zhu, Yang song
We propose two stochastic gradient MCMC methods for sampling from Bayesian posterior distributions defined on Riemann manifolds with a known geodesic flow, e. g. hyperspheres.
14 code implementations • CVPR 2017 • Jonathan Huang, Vivek Rathod, Chen Sun, Menglong Zhu, Anoop Korattikara, Alireza Fathi, Ian Fischer, Zbigniew Wojna, Yang song, Sergio Guadarrama, Kevin Murphy
On the opposite end in which accuracy is critical, we present a detector that achieves state-of-the-art performance measured on the COCO detection task.
Ranked #190 on
Object Detection
on COCO test-dev
1 code implementation • 24 Sep 2016 • Zhifei Zhang, Yang song, Wei Wang, Hairong Qi
The staggering amount of streaming time series coming from the real world calls for more efficient and effective online modeling solution.
no code implementations • NeurIPS 2016 • Yang Song, Jun Zhu, Yong Ren
We propose a vector-valued regression problem whose solution is equivalent to the reproducing kernel Hilbert space (RKHS) embedding of the Bayesian posterior distribution.
no code implementations • CVPR 2016 • Stephan Zheng, Yang song, Thomas Leung, Ian Goodfellow
In this paper we address the issue of output instability of deep neural networks: small perturbations in the visual input can significantly distort the feature embeddings and output of a neural network.
1 code implementation • 3 Dec 2015 • Yang Song, Jun Zhu
Bayesian matrix completion has been studied based on a low-rank matrix factorization formulation with promising results.
1 code implementation • 19 Nov 2015 • Yang Song, Alexander G. Schwing, Richard S. Zemel, Raquel Urtasun
Supervised training of deep neural nets typically relies on minimizing cross-entropy.
no code implementations • CVPR 2015 • Yang Song, Weidong Cai, Qing Li, Fan Zhang, David Dagan Feng, Heng Huang
Texture, as a fundamental characteristic of objects, has attracted much attention in computer vision research.
no code implementations • CVPR 2015 • Vignesh Ramanathan, Cong-Cong Li, Jia Deng, Wei Han, Zhen Li, Kunlong Gu, Yang song, Samy Bengio, Charles Rosenberg, Li Fei-Fei
Human actions capture a wide variety of interactions between people and objects.
1 code implementation • WWW 2015 • Ali Elkahky, Yang song, Xiaodong He
We extend the model to jointly learn from features of items from different domains and user features by introducing a multi-view Deep Learning model.
no code implementations • WWW 2015 • Arnab Sinha, Zhihong Shen, Yang song, Hao Ma, Darrin Eide, Bo-June (Paul) Hsu, Kuansan Wang
In addition to obtaining these entities from the publisher feeds as in the previous effort, we in this version include data mining results from the Web index and an in-house knowledge base from Bing, a major commercial search engine.
6 code implementations • CVPR 2014 • Jiang Wang, Yang song, Thomas Leung, Chuck Rosenberg, Jinbin Wang, James Philbin, Bo Chen, Ying Wu
This paper proposes a deep ranking model that employs deep learning techniques to learn similarity metric directly from images. It has higher learning capability than models based on hand-crafted features.