Search Results for author: Bo Zhao

Found 66 papers, 28 papers with code

Where and when to look? Spatial-temporal attention for action recognition in videos

no code implementations ICLR 2019 Lili Meng, Bo Zhao, Bo Chang, Gao Huang, Frederick Tung, Leonid Sigal

Our model is efficient, as it proposes a separable spatio-temporal mechanism for video attention, while being able to identify important parts of the video both spatially and temporally.

Action Recognition In Videos Temporal Action Localization +1

Open-DDVM: A Reproduction and Extension of Diffusion Model for Optical Flow Estimation

1 code implementation4 Dec 2023 Qiaole Dong, Bo Zhao, Yanwei Fu

Recently, Google proposes DDVM which for the first time demonstrates that a general diffusion model for image-to-image translation task works impressively well on optical flow estimation task without any specific designs like RAFT.

Image-to-Image Translation Optical Flow Estimation +1

SegVol: Universal and Interactive Volumetric Medical Image Segmentation

1 code implementation22 Nov 2023 Yuxin Du, Fan Bai, Tiejun Huang, Bo Zhao

Despite the remarkable progress achieved in medical image segmentation, there is still an absence of foundation segmentation model that can segment a wide range of anatomical categories with easy user interaction.

Computed Tomography (CT) Image Segmentation +3

A global product of fine-scale urban building height based on spaceborne lidar

no code implementations22 Oct 2023 Xiao Ma, Guang Zheng, Chi Xu, L. Monika Moskal, Peng Gong, Qinghua Guo, Huabing Huang, Xuecao Li, Yong Pang, Cheng Wang, Huan Xie, Bailang Yu, Bo Zhao, Yuyu Zhou

Our results revealed that the estimated method of building height samples based on the GEDI data was effective with 0. 78 of Pearson's r and 3. 67 m of RMSE in comparison to the reference data.

Real-Fake: Effective Training Data Synthesis Through Distribution Matching

no code implementations16 Oct 2023 Jianhao Yuan, Jie Zhang, Shuyang Sun, Philip Torr, Bo Zhao

Synthetic training data has gained prominence in numerous learning tasks and scenarios, offering advantages such as dataset augmentation, generalization evaluation, and privacy preservation.

Image Classification Out-of-Distribution Generalization

Image Captions are Natural Prompts for Text-to-Image Models

no code implementations17 Jul 2023 Shiye Lei, Hao Chen, Sen Zhang, Bo Zhao, DaCheng Tao

With the rapid development of Artificial Intelligence Generated Content (AIGC), it has become common practice in many learning tasks to train or fine-tune large models on synthetic data due to the data-scarcity and privacy leakage problems.

Image Captioning Image Generation

SVIT: Scaling up Visual Instruction Tuning

1 code implementation9 Jul 2023 Bo Zhao, Boya Wu, Tiejun Huang

Thanks to the emerging of foundation models, the large language and vision models are integrated to acquire the multimodal ability of visual captioning, dialogue, question answering, etc.

Image Captioning Question Answering

Federated Generative Learning with Foundation Models

1 code implementation28 Jun 2023 Jie Zhang, Xiaohua Qi, Bo Zhao

Existing federated learning solutions focus on transmitting features, parameters or gadients between clients and server, which suffer from serious low-efficiency and privacy-leakage problems.

Federated Learning

Pushing the Limits of 3D Shape Generation at Scale

no code implementations20 Jun 2023 Yu Wang, Xuelin Qian, Jingyang Huo, Tiejun Huang, Bo Zhao, Yanwei Fu

Through the adaptation of the Auto-Regressive model and the utilization of large language models, we have developed a remarkable model with an astounding 3. 6 billion trainable parameters, establishing it as the largest 3D shape generation model to date, named Argus-3D.

3D Shape Generation Quantization +1

Large-scale Dataset Pruning with Dynamic Uncertainty

1 code implementation8 Jun 2023 Muyang He, Shuo Yang, Tiejun Huang, Bo Zhao

The state of the art of many learning tasks, e. g., image classification, is advanced by collecting larger datasets and then training larger models on them.

Image Classification

DYffusion: A Dynamics-informed Diffusion Model for Spatiotemporal Forecasting

1 code implementation NeurIPS 2023 Salva Rühling Cachay, Bo Zhao, Hailey Joren, Rose Yu

While diffusion models can successfully generate data and make predictions, they are predominantly designed for static images.

Inductive Bias

Improving Convergence and Generalization Using Parameter Symmetries

no code implementations22 May 2023 Bo Zhao, Robert M. Gower, Robin Walters, Rose Yu

In this paper, we show that teleportation not only speeds up optimization in the short-term, but gives overall faster time to convergence.


Accelerated MR Fingerprinting with Low-Rank and Generative Subspace Modeling

no code implementations18 May 2023 Hengfa Lu, Huihui Ye, Lawrence L. Wald, Bo Zhao

To address this problem, we present a new image reconstruction method for MR Fingerprinting, integrating low-rank and subspace modeling with a deep generative prior.

Image Reconstruction

Toward Moiré-Free and Detail-Preserving Demosaicking

no code implementations15 May 2023 Xuanchen Li, Yan Niu, Bo Zhao, Haoyuan Shi, Zitong An

In both applications, our model substantially alleviates artifacts such as Moir\'e and over-smoothness at similar or lower computational cost to currently top-performing models, as validated by diverse evaluations.

Demosaicking Denoising +1

Accelerating Dataset Distillation via Model Augmentation

2 code implementations CVPR 2023 Lei Zhang, Jie Zhang, Bowen Lei, Subhabrata Mukherjee, Xiang Pan, Bo Zhao, Caiwen Ding, Yao Li, Dongkuan Xu

Dataset Distillation (DD), a newly emerging field, aims at generating much smaller but efficient synthetic training datasets from large ones.

The Impact of Weather on Local Government Spending

no code implementations journal 2022 Bo Zhao

While there is a new and rapidly growing literature on the effects of climatic factors on economic and social outcomes, little research has been conducted to understand the fiscal impact of weather, especially at the sub-state level.

CR-LSO: Convex Neural Architecture Optimization in the Latent Space of Graph Variational Autoencoder with Input Convex Neural Networks

1 code implementation11 Nov 2022 Xuan Rao, Bo Zhao, Xiaosong Yi, Derong Liu

In neural architecture search (NAS) methods based on latent space optimization (LSO), a deep generative model is trained to embed discrete neural architectures into a continuous latent space.

Neural Architecture Search

Symmetries, flat minima, and the conserved quantities of gradient flow

1 code implementation31 Oct 2022 Bo Zhao, Iordan Ganev, Robin Walters, Rose Yu, Nima Dehmamy

Empirical studies of the loss landscape of deep networks have revealed that many local minima are connected through low-loss valleys.

Nowhere to Hide: A Lightweight Unsupervised Detector against Adversarial Examples

no code implementations16 Oct 2022 Hui Liu, Bo Zhao, Kehuan Zhang, Peng Liu

In this paper, we propose an AutoEncoder-based Adversarial Examples (AEAE) detector, that can guard DNN models by detecting adversarial examples with low computation in an unsupervised manner.

MSRL: Distributed Reinforcement Learning with Dataflow Fragments

no code implementations3 Oct 2022 Huanzhou Zhu, Bo Zhao, Gang Chen, Weifeng Chen, Yijie Chen, Liang Shi, Yaodong Yang, Peter Pietzuch, Lei Chen

Yet, current distributed RL systems tie the definition of RL algorithms to their distributed execution: they hard-code particular distribution strategies and only accelerate specific parts of the computation (e. g. policy network updates) on GPU workers.

reinforcement-learning Reinforcement Learning (RL)

Everyone's Preference Changes Differently: Weighted Multi-Interest Retrieval Model

1 code implementation14 Jul 2022 Hui Shi, Yupeng Gu, Yitong Zhou, Bo Zhao, Sicun Gao, Jishen Zhao

In this paper, we propose the Multi-Interest Preference (MIP) model, an approach that not only produces multi-interest for users by using the user's sequential engagement more effectively but also automatically learns a set of weights to represent the preference over each embedding so that the candidates can be retrieved from each interest proportionally.

Recommendation Systems Retrieval

LIMO: Latent Inceptionism for Targeted Molecule Generation

1 code implementation17 Jun 2022 Peter Eckmann, Kunyang Sun, Bo Zhao, Mudong Feng, Michael K. Gilson, Rose Yu

We corroborate these docking-based results with more accurate molecular dynamics-based calculations of absolute binding free energy and show that one of our generated drug-like compounds has a predicted $K_D$ (a measure of binding affinity) of $6 \cdot 10^{-14}$ M against the human estrogen receptor, well beyond the affinities of typical early-stage drug candidates and most FDA-approved drugs to their respective targets.

Drug Discovery Gaussian Processes +1

Privacy for Free: How does Dataset Condensation Help Privacy?

1 code implementation1 Jun 2022 Tian Dong, Bo Zhao, Lingjuan Lyu

In this work, we for the first time identify that dataset condensation (DC) which is originally designed for improving training efficiency is also a better solution to replace the traditional data generators for private data generation, thus providing privacy for free.

Dataset Condensation Privacy Preserving

Symmetry Teleportation for Accelerated Optimization

1 code implementation21 May 2022 Bo Zhao, Nima Dehmamy, Robin Walters, Rose Yu

Experimentally, we show that teleportation improves the convergence speed of gradient descent and AdaGrad for several optimization problems including test functions, multi-layer regressions, and MNIST classification.

Second-order methods Test

DeepCore: A Comprehensive Library for Coreset Selection in Deep Learning

1 code implementation18 Apr 2022 Chengcheng Guo, Bo Zhao, Yanbing Bai

Coreset selection, which aims to select a subset of the most informative training samples, is a long-standing learning problem that can benefit many downstream tasks such as data-efficient learning, continual learning, neural architecture search, active learning, etc.

Active Learning Continual Learning +1

Synthesizing Informative Training Samples with GAN

3 code implementations15 Apr 2022 Bo Zhao, Hakan Bilen

However, traditional GANs generated images are not as informative as the real training samples when being used to train deep neural networks.

Dataset Condensation

CAFE: Learning to Condense Dataset by Aligning Features

2 code implementations CVPR 2022 Kai Wang, Bo Zhao, Xiangyu Peng, Zheng Zhu, Shuo Yang, Shuo Wang, Guan Huang, Hakan Bilen, Xinchao Wang, Yang You

Dataset condensation aims at reducing the network training effort through condensing a cumbersome training set into a compact synthetic one.

Dataset Condensation

Towards Understanding and Harnessing the Effect of Image Transformation in Adversarial Detection

no code implementations4 Jan 2022 Hui Liu, Bo Zhao, Yuefeng Peng, Weidong Li, Peng Liu

Experimental results show that the contribution of image transformations to adversarial detection is significantly different, the combination of them can significantly improve the generic detection ability against state-of-the-art adversarial attacks.

Makeup216: Logo Recognition with Adversarial Attention Representations

no code implementations13 Dec 2021 Junjun Hu, Yanhao Zhu, Bo Zhao, Jiexin Zheng, Chenxu Zhao, Xiangyu Zhu, Kangle Wu, Darun Tang

One of the challenges of logo recognition lies in the diversity of forms, such as symbols, texts or a combination of both; further, logos tend to be extremely concise in design while similar in appearance, suggesting the difficulty of learning discriminative representations.

Logo Recognition

One-dimensional Deep Low-rank and Sparse Network for Accelerated MRI

no code implementations9 Dec 2021 Zi Wang, Chen Qian, Di Guo, Hongwei Sun, Rushuai Li, Bo Zhao, Xiaobo Qu

Deep learning has shown astonishing performance in accelerated magnetic resonance imaging (MRI).

Dataset Condensation with Distribution Matching

3 code implementations8 Oct 2021 Bo Zhao, Hakan Bilen

Computational cost of training state-of-the-art deep models in many learning problems is rapidly increasing due to more sophisticated models and larger datasets.

Continual Learning Dataset Condensation +1

Accelerated MRI Reconstruction with Separable and Enhanced Low-Rank Hankel Regularization

no code implementations24 Jul 2021 Xinlin Zhang, Hengfa Lu, Di Guo, Zongying Lai, Huihui Ye, Xi Peng, Bo Zhao, Xiaobo Qu

The combination of the sparse sampling and the low-rank structured matrix reconstruction has shown promising performance, enabling a significant reduction of the magnetic resonance imaging data acquisition time.

MRI Reconstruction

Feature-Filter: Detecting Adversarial Examples through Filtering off Recessive Features

no code implementations19 Jul 2021 Hui Liu, Bo Zhao, Minzhi Ji, Yuefeng Peng, Jiabao Guo, Peng Liu

In this paper, we reveal that imperceptible adversarial examples are the product of recessive features misleading neural networks, and an adversarial attack is essentially a kind of method to enrich these recessive features in the image.

Adversarial Attack

FedCom: A Byzantine-Robust Local Model Aggregation Rule Using Data Commitment for Federated Learning

no code implementations16 Apr 2021 Bo Zhao, Peng Sun, Liming Fang, Tao Wang, Keyu Jiang

The results demonstrate its effectiveness and superior performance compared to the state-of-the-art Byzantine-robust schemes in defending against typical data poisoning and model poisoning attacks under practical Non-IID data distributions.

Data Poisoning Federated Learning +2

Concentric Spherical GNN for 3D Representation Learning

no code implementations18 Mar 2021 James Fox, Bo Zhao, Sivasankaran Rajamanickam, Rampi Ramprasad, Le Song

Learning 3D representations that generalize well to arbitrarily oriented inputs is a challenge of practical importance in applications varying from computer vision to physics and chemistry.

3D Classification Representation Learning

Dataset Condensation with Differentiable Siamese Augmentation

2 code implementations16 Feb 2021 Bo Zhao, Hakan Bilen

In many machine learning problems, large-scale datasets have become the de-facto standard to train state-of-the-art deep networks at the price of heavy computation load.

Continual Learning Data Augmentation +3

Quantum Adiabatic Doping for Atomic Fermi-Hubbard Quantum Simulations

no code implementations5 Jan 2021 Jue Nan, Jian Lin, Yuchen Luo, Bo Zhao, Xiaopeng Li

Its feasibility has been demonstrated with numerical simulations of the adiabatic preparation for certain incommensurate particle-doping fractions, where the major problem to circumvent is the atomic localization in the incommensurate lattice.

Quantum Gases Strongly Correlated Electrons Quantum Physics

Multiple Plans are Better than One: Diverse Stochastic Planning

no code implementations31 Dec 2020 Mahsa Ghasemi, Evan Scope Crafts, Bo Zhao, Ufuk Topcu

In planning problems, it is often challenging to fully model the desired specifications.

Active Sampling for Accelerated MRI with Low-Rank Tensors

no code implementations23 Dec 2020 Zichang He, Bo Zhao, Zheng Zhang

In this paper, we introduce an active low-rank tensor model for fast MR imaging.

GreedyFool: Multi-Factor Imperceptibility and Its Application to Designing a Black-box Adversarial Attack

1 code implementation14 Oct 2020 Hui Liu, Bo Zhao, Minzhi Ji, Peng Liu

Adversarial examples are well-designed input samples, in which perturbations are imperceptible to the human eyes, but easily mislead the output of deep neural networks (DNNs).

Adversarial Attack

Attribute-guided image generation from layout

2 code implementations27 Aug 2020 Ke Ma, Bo Zhao, Leonid Sigal

Also, the generated images from our model have higher resolution, object classification accuracy and consistency, as compared to the previous state-of-the-art.

Image Generation Semantic Segmentation

Augmented Bi-path Network for Few-shot Learning

no code implementations15 Jul 2020 Baoming Yan, Chen Zhou, Bo Zhao, Kan Guo, Jiang Yang, Xiaobo Li, Ming Zhang, Yizhou Wang

Finally, the model learns to compare global and local features separately, i. e., in two paths, before merging the similarities.

Few-Shot Learning

Privacy-Preserving Technology to Help Millions of People: Federated Prediction Model for Stroke Prevention

no code implementations15 Jun 2020 Ce Ju, Ruihui Zhao, Jichao Sun, Xiguang Wei, Bo Zhao, Yang Liu, Hongshan Li, Tianjian Chen, Xinwei Zhang, Dashan Gao, Ben Tan, Han Yu, Chuning He, Yuan Jin

It adopts federated averaging during the model training process, without patient data being taken out of the hospitals during the whole process of model training and forecasting.

Privacy Preserving

Dataset Condensation with Gradient Matching

4 code implementations ICLR 2021 Bo Zhao, Konda Reddy Mopuri, Hakan Bilen

As the state-of-the-art machine learning methods in many fields rely on larger datasets, storing datasets and training models on them become significantly more expensive.

Continual Learning Dataset Condensation +2

Continual Representation Learning for Biometric Identification

1 code implementation8 Jun 2020 Bo Zhao, Shixiang Tang, Dapeng Chen, Hakan Bilen, Rui Zhao

With the explosion of digital data in recent years, continuously learning new tasks from a stream of data without forgetting previously acquired knowledge has become increasingly important.

Continual Learning Knowledge Distillation +1

iDLG: Improved Deep Leakage from Gradients

2 code implementations8 Jan 2020 Bo Zhao, Konda Reddy Mopuri, Hakan Bilen

Particularly, our approach can certainly extract the ground-truth labels as opposed to DLG, hence we name it Improved DLG (iDLG).

Federated Learning valid

DwNet: Dense warp-based network for pose-guided human video generation

2 code implementations21 Oct 2019 Polina Zablotskaia, Aliaksandr Siarohin, Bo Zhao, Leonid Sigal

In this paper, we focus on human motion transfer - generation of a video depicting a particular subject, observed in a single image, performing a series of motions exemplified by an auxiliary (driving) video.

Video Generation

Image Generation from Layout

no code implementations CVPR 2019 Bo Zhao, Lili Meng, Weidong Yin, Leonid Sigal

The representation of each object is disentangled into a specified/certain part (category) and an unspecified/uncertain part (appearance).

Layout-to-Image Generation

Interpretable Spatio-temporal Attention for Video Action Recognition

no code implementations1 Oct 2018 Lili Meng, Bo Zhao, Bo Chang, Gao Huang, Wei Sun, Frederich Tung, Leonid Sigal

Inspired by the observation that humans are able to process videos efficiently by only paying attention where and when it is needed, we propose an interpretable and easy plug-in spatial-temporal attention mechanism for video action recognition.

Action Recognition Temporal Action Localization

Guess Me if You Can: Acronym Disambiguation for Enterprises

no code implementations ACL 2018 Yang Li, Bo Zhao, Ariel Fuxman, Fangbo Tao

The framework takes the enterprise corpus as input and produces a high-quality acronym disambiguation system as output.

Question Answering

MSplit LBI: Realizing Feature Selection and Dense Estimation Simultaneously in Few-shot and Zero-shot Learning

no code implementations ICML 2018 Bo Zhao, Xinwei Sun, Yanwei Fu, Yuan YAO, Yizhou Wang

To solve this task, $L_{1}$ regularization is widely used for the pursuit of feature selection and avoiding overfitting, and yet the sparse estimation of features in $L_{1}$ regularization may cause the underfitting of training data.

feature selection Zero-Shot Learning

A Large-scale Attribute Dataset for Zero-shot Learning

1 code implementation12 Apr 2018 Bo Zhao, Yanwei Fu, Rui Liang, Jia-Hong Wu, Yonggang Wang, Yizhou Wang

In classical ZSL algorithms, attributes are introduced as the intermediate semantic representation to realize the knowledge transfer from seen classes to unseen classes.

Transfer Learning Zero-Shot Learning

Modular Generative Adversarial Networks

2 code implementations ECCV 2018 Bo Zhao, Bo Chang, Zequn Jie, Leonid Sigal

Existing methods for multi-domain image-to-image translation (or generation) attempt to directly map an input image (or a random vector) to an image in one of the output domains.

Image-to-Image Translation Test +1

Left-Right Comparative Recurrent Model for Stereo Matching

no code implementations CVPR 2018 Zequn Jie, Pengfei Wang, Yonggen Ling, Bo Zhao, Yunchao Wei, Jiashi Feng, Wei Liu

Left-right consistency check is an effective way to enhance the disparity estimation by referring to the information from the opposite view.

Disparity Estimation Stereo Disparity Estimation +2

Zero-shot Learning via Shared-Reconstruction-Graph Pursuit

no code implementations20 Nov 2017 Bo Zhao, Xinwei Sun, Yuan YAO, Yizhou Wang

With the learned SRG, each unseen class prototype (cluster center) in the image feature space can be synthesized by the linear combination of other class prototypes, so that testing instances can be classified based on the distance to these synthesized prototypes.

Clustering Generalized Zero-Shot Learning +1

Optimal Experiment Design for Magnetic Resonance Fingerprinting: Cramér-Rao Bound Meets Spin Dynamics

no code implementations23 Oct 2017 Bo Zhao, Justin P. Haldar, Congyu Liao, Dan Ma, Yun Jiang, Mark A. Griswold, Kawin Setsompop, Lawrence L. Wald

Magnetic resonance (MR) fingerprinting is a new quantitative imaging paradigm, which simultaneously acquires multiple MR tissue parameter maps in a single experiment.

Signal Processing

Memory-Augmented Attribute Manipulation Networks for Interactive Fashion Search

no code implementations CVPR 2017 Bo Zhao, Jiashi Feng, Xiao Wu, Shuicheng Yan

We introduce a new fashion search protocol where attribute manipulation is allowed within the interaction between users and search engines, e. g. manipulating the color attribute of the clothing from red to blue.

Representation Learning

Multi-View Image Generation from a Single-View

no code implementations17 Apr 2017 Bo Zhao, Xiao Wu, Zhi-Qi Cheng, Hao liu, Zequn Jie, Jiashi Feng

This paper addresses a challenging problem -- how to generate multi-view cloth images from only a single view input.

Image Generation Variational Inference

Zero-Shot Learning posed as a Missing Data Problem

no code implementations2 Dec 2016 Bo Zhao, Botong Wu, Tianfu Wu, Yizhou Wang

This paper presents a method of zero-shot learning (ZSL) which poses ZSL as the missing data problem, rather than the missing label problem.

Zero-Shot Learning

Diversified Visual Attention Networks for Fine-Grained Object Classification

no code implementations28 Jun 2016 Bo Zhao, Xiao Wu, Jiashi Feng, Qiang Peng, Shuicheng Yan

Fine-grained object classification is a challenging task due to the subtle inter-class difference and large intra-class variation.

Classification General Classification

Fast Low-rank Representation based Spatial Pyramid Matching for Image Classification

no code implementations22 Sep 2014 Xi Peng, Rui Yan, Bo Zhao, Huajin Tang, Zhang Yi

Although the methods achieve a higher recognition rate than the traditional SPM, they consume more time to encode the local descriptors extracted from the image.

General Classification Image Classification +1

Cannot find the paper you are looking for? You can Submit a new open access paper.