Search Results for author: Siyu Huang

Found 33 papers, 16 papers with code

Make a Cheap Scaling: A Self-Cascade Diffusion Model for Higher-Resolution Adaptation

1 code implementation16 Feb 2024 Lanqing Guo, Yingqing He, Haoxin Chen, Menghan Xia, Xiaodong Cun, YuFei Wang, Siyu Huang, Yong Zhang, Xintao Wang, Qifeng Chen, Ying Shan, Bihan Wen

Diffusion models have proven to be highly effective in image and video generation; however, they still face composition challenges when generating images of varying sizes due to single-scale training data.

Video Generation

MUSCLE: Multi-task Self-supervised Continual Learning to Pre-train Deep Models for X-ray Images of Multiple Body Parts

no code implementations3 Oct 2023 Weibin Liao, Haoyi Xiong, Qingzhong Wang, Yan Mo, Xuhong LI, Yi Liu, Zeyu Chen, Siyu Huang, Dejing Dou

In this work, we study a novel self-supervised pre-training pipeline, namely Multi-task Self-super-vised Continual Learning (MUSCLE), for multiple medical imaging tasks, such as classification and segmentation, using X-ray images collected from multiple body parts, including heads, lungs, and bones.

Continual Learning Representation Learning +1

Domain-Scalable Unpaired Image Translation via Latent Space Anchoring

1 code implementation26 Jun 2023 Siyu Huang, Jie An, Donglai Wei, Zudi Lin, Jiebo Luo, Hanspeter Pfister

However, given a UNIT model trained on certain domains, it is difficult for current methods to incorporate new domains because they often need to train the full model on both existing and new domains.

Image-to-Image Translation Translation

ShadowFormer: Global Context Helps Image Shadow Removal

1 code implementation3 Feb 2023 Lanqing Guo, Siyu Huang, Ding Liu, Hao Cheng, Bihan Wen

It is still challenging for the deep shadow removal model to exploit the global contextual correlation between shadow and non-shadow regions.

Image Shadow Removal Shadow Removal

QuantArt: Quantizing Image Style Transfer Towards High Visual Fidelity

1 code implementation CVPR 2023 Siyu Huang, Jie An, Donglai Wei, Jiebo Luo, Hanspeter Pfister

The mechanism of existing style transfer algorithms is by minimizing a hybrid loss function to push the generated image toward high similarities in both content and style.

Quantization Style Transfer +1

Temporal Output Discrepancy for Loss Estimation-based Active Learning

no code implementations20 Dec 2022 Siyu Huang, Tianyang Wang, Haoyi Xiong, Bihan Wen, Jun Huan, Dejing Dou

Inspired by the fact that the samples with higher loss are usually more informative to the model than the samples with lower loss, in this paper we present a novel deep active learning approach that queries the oracle for data annotation when the unlabeled sample is believed to incorporate high loss.

Active Learning Image Classification +1

Making Your First Choice: To Address Cold Start Problem in Vision Active Learning

1 code implementation5 Oct 2022 Liangyu Chen, Yutong Bai, Siyu Huang, Yongyi Lu, Bihan Wen, Alan L. Yuille, Zongwei Zhou

However, we uncover a striking contradiction to this promise: active learning fails to select data as efficiently as random selection at the first few choices.

Active Learning Contrastive Learning

Boosting Active Learning via Improving Test Performance

1 code implementation10 Dec 2021 Tianyang Wang, Xingjian Li, Pengkun Yang, Guosheng Hu, Xiangrui Zeng, Siyu Huang, Cheng-Zhong Xu, Min Xu

In this work, we explore such an impact by theoretically proving that selecting unlabeled data of higher gradient norm leads to a lower upper-bound of test loss, resulting in better test performance.

Active Learning Electron Tomography +2

FINO: Flow-based Joint Image and Noise Model

no code implementations11 Nov 2021 Lanqing Guo, Siyu Huang, Haosen Liu, Bihan Wen

One of the fundamental challenges in image restoration is denoising, where the objective is to estimate the clean image from its noisy measurements.

Denoising Image Restoration

AutoGCL: Automated Graph Contrastive Learning via Learnable View Generators

1 code implementation21 Sep 2021 Yihang Yin, Qingzhong Wang, Siyu Huang, Haoyi Xiong, Xiang Zhang

Most of the existing contrastive learning methods employ pre-defined view generation methods, e. g., node drop or edge perturbation, which usually cannot adapt to input data or preserve the original semantic structures well.

Contrastive Learning Graph Representation Learning +3

Cross-Model Consensus of Explanations and Beyond for Image Classification Models: An Empirical Study

no code implementations2 Sep 2021 Xuhong LI, Haoyi Xiong, Siyu Huang, Shilei Ji, Dejing Dou

Existing interpretation algorithms have found that, even deep models make the same and right predictions on the same image, they might rely on different sets of input features for classification.

Attribute Image Classification +2

Semi-Supervised Active Learning with Temporal Output Discrepancy

1 code implementation ICCV 2021 Siyu Huang, Tianyang Wang, Haoyi Xiong, Jun Huan, Dejing Dou

To lower the cost of data annotation, active learning has been proposed to interactively query an oracle to annotate a small proportion of informative samples in an unlabeled dataset.

Active Learning Image Classification +1

ReLLIE: Deep Reinforcement Learning for Customized Low-Light Image Enhancement

1 code implementation13 Jul 2021 Rongkai Zhang, Lanqing Guo, Siyu Huang, Bihan Wen

Low-light image enhancement (LLIE) is a pervasive yet challenging problem, since: 1) low-light measurements may vary due to different imaging conditions in practice; 2) images can be enlightened subjectively according to diverse preferences by each individual.

Low-Light Image Enhancement reinforcement-learning +2

Practical Assessment of Generalization Performance Robustness for Deep Networks via Contrastive Examples

no code implementations20 Jun 2021 Xuanyu Wu, Xuhong LI, Haoyi Xiong, Xiao Zhang, Siyu Huang, Dejing Dou

Incorporating with a set of randomized strategies for well-designed data transformations over the training set, ContRE adopts classification errors and Fisher ratios on the generated contrastive examples to assess and analyze the generalization performance of deep models in complement with a testing set.

Contrastive Learning

BM-NAS: Bilevel Multimodal Neural Architecture Search

1 code implementation19 Apr 2021 Yihang Yin, Siyu Huang, Xiang Zhang

Deep neural networks (DNNs) have shown superior performances on various multimodal learning problems.

Neural Architecture Search

ArtFlow: Unbiased Image Style Transfer via Reversible Neural Flows

1 code implementation CVPR 2021 Jie An, Siyu Huang, Yibing Song, Dejing Dou, Wei Liu, Jiebo Luo

The forward inference projects input images into deep features, while the backward inference remaps deep features back to input images in a lossless and unbiased way.

Style Transfer

Democratizing Evaluation of Deep Model Interpretability through Consensus

no code implementations1 Jan 2021 Xuhong LI, Haoyi Xiong, Siyu Huang, Shilei Ji, Yanjie Fu, Dejing Dou

Given any task/dataset, Consensus first obtains the interpretation results using existing tools, e. g., LIME (Ribeiro et al., 2016), for every model in the committee, then aggregates the results from the entire committee and approximates the “ground truth” of interpretations through voting.

Feature Importance

Contour Primitive of Interest Extraction Network Based on One-Shot Learning for Object-Agnostic Vision Measurement

no code implementations7 Oct 2020 Fangbo Qin, Jie Qin, Siyu Huang, De Xu

For the novel CPI extraction task, we built the Object Contour Primitives dataset using online public images, and the Robotic Object Contour Measurement dataset using a camera mounted on a robot.

Object One-Shot Learning +1

TP-LSD: Tri-Points Based Line Segment Detector

2 code implementations ECCV 2020 Siyu Huang, Fangbo Qin, Pengfei Xiong, Ning Ding, Yijia He, Xiao Liu

To realize one-step detection with a faster and more compact model, we introduce the tri-points representation, converting the line segment detection to the end-to-end prediction of a root-point and two endpoints for each line segment.

Line Segment Detection

SBAT: Video Captioning with Sparse Boundary-Aware Transformer

no code implementations23 Jul 2020 Tao Jin, Siyu Huang, Ming Chen, Yingming Li, Zhongfei Zhang

However, video captioning is a multimodal learning problem, and the video features have much redundancy between different time steps.

Machine Translation Text Generation +2

Generating Person Images with Appearance-aware Pose Stylizer

1 code implementation17 Jul 2020 Siyu Huang, Haoyi Xiong, Zhi-Qi Cheng, Qingzhong Wang, Xingran Zhou, Bihan Wen, Jun Huan, Dejing Dou

Generation of high-quality person images is challenging, due to the sophisticated entanglements among image factors, e. g., appearance, pose, foreground, background, local details, global structures, etc.

Image Generation

Effects of Regional Trade Agreement to Local and Global Trade Purity Relationships

no code implementations29 May 2020 Siyu Huang, Wensha Gou, Hongbo Cai, Xiaomeng Li, Qinghua Chen

In addition, we apply the network to reflect the purity of the trade relations among countries.

Parameter-Free Style Projection for Arbitrary Style Transfer

1 code implementation17 Mar 2020 Siyu Huang, Haoyi Xiong, Tianyang Wang, Bihan Wen, Qingzhong Wang, Zeyu Chen, Jun Huan, Dejing Dou

This paper further presents a real-time feed-forward model to leverage Style Projection for arbitrary image style transfer, which includes a regularization term for matching the semantics between input contents and stylized outputs.

Style Transfer

Text Guided Person Image Synthesis

no code implementations CVPR 2019 Xingran Zhou, Siyu Huang, Bin Li, Yingming Li, Jiachen Li, Zhongfei Zhang

This paper presents a novel method to manipulate the visual appearance (pose and attribute) of a person image according to natural language descriptions.

Attribute Image Generation +1

Perceiving Physical Equation by Observing Visual Scenarios

no code implementations29 Nov 2018 Siyu Huang, Zhi-Qi Cheng, Xi Li, Xiao Wu, Zhongfei Zhang, Alexander Hauptmann

To tackle this challenge, we present a novel pipeline comprised of an Observer Engine and a Physicist Engine by respectively imitating the actions of an observer and a physicist in the real world.

Stacked Pooling: Improving Crowd Counting by Boosting Scale Invariance

1 code implementation22 Aug 2018 Siyu Huang, Xi Li, Zhi-Qi Cheng, Zhongfei Zhang, Alexander Hauptmann

In this work, we explore the cross-scale similarity in crowd counting scenario, in which the regions of different scales often exhibit high visual similarity.

Crowd Counting Density Estimation

GNAS: A Greedy Neural Architecture Search Method for Multi-Attribute Learning

no code implementations19 Apr 2018 Siyu Huang, Xi Li, Zhi-Qi Cheng, Zhongfei Zhang, Alexander Hauptmann

A key problem in deep multi-attribute learning is to effectively discover the inter-attribute correlation structures.

Attribute Neural Architecture Search

Deep Learning Driven Visual Path Prediction from a Single Image

no code implementations27 Jan 2016 Siyu Huang, Xi Li, Zhongfei Zhang, Zhouzhou He, Fei Wu, Wei Liu, Jinhui Tang, Yueting Zhuang

The highly effective visual representation and deep context models ensure that our framework makes a deep semantic understanding of the scene and motion pattern, consequently improving the performance of the visual path prediction task.

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