Search Results for author: Yibo Yang

Found 67 papers, 42 papers with code

GenView: Enhancing View Quality with Pretrained Generative Model for Self-Supervised Learning

1 code implementation18 Mar 2024 Xiaojie Li, Yibo Yang, Xiangtai Li, Jianlong Wu, Yue Yu, Bernard Ghanem, Min Zhang

To tackle these challenges, we present GenView, a controllable framework that augments the diversity of positive views leveraging the power of pretrained generative models while preserving semantics.

Contrastive Learning Data Augmentation +1

Towards Demystifying the Generalization Behaviors When Neural Collapse Emerges

no code implementations12 Oct 2023 Peifeng Gao, Qianqian Xu, Yibo Yang, Peisong Wen, Huiyang Shao, Zhiyong Yang, Bernard Ghanem, Qingming Huang

While there have been extensive studies on optimization characteristics showing the global optimality of neural collapse, little research has been done on the generalization behaviors during the occurrence of NC.

ShadowNet for Data-Centric Quantum System Learning

no code implementations22 Aug 2023 Yuxuan Du, Yibo Yang, Tongliang Liu, Zhouchen Lin, Bernard Ghanem, DaCheng Tao

Understanding the dynamics of large quantum systems is hindered by the curse of dimensionality.

Quantum State Tomography

Deformable Mixer Transformer with Gating for Multi-Task Learning of Dense Prediction

1 code implementation10 Aug 2023 Yangyang Xu, Yibo Yang, Bernard Ghanem, Lefei Zhang, Du Bo, DaCheng Tao

In this work, we present a novel MTL model by combining both merits of deformable CNN and query-based Transformer with shared gating for multi-task learning of dense prediction.

Multi-Task Learning

Neural Collapse Terminus: A Unified Solution for Class Incremental Learning and Its Variants

2 code implementations3 Aug 2023 Yibo Yang, Haobo Yuan, Xiangtai Li, Jianlong Wu, Lefei Zhang, Zhouchen Lin, Philip Torr, DaCheng Tao, Bernard Ghanem

Beyond the normal case, long-tail class incremental learning and few-shot class incremental learning are also proposed to consider the data imbalance and data scarcity, respectively, which are common in real-world implementations and further exacerbate the well-known problem of catastrophic forgetting.

Few-Shot Class-Incremental Learning Incremental Learning

Computationally-Efficient Neural Image Compression with Shallow Decoders

1 code implementation ICCV 2023 Yibo Yang, Stephan Mandt

We theoretically formalize the intuition behind, and our experimental results establish a new frontier in the trade-off between rate-distortion and decoding complexity for neural image compression.

Image Compression

Neural Collapse Inspired Federated Learning with Non-iid Data

no code implementations27 Mar 2023 Chenxi Huang, Liang Xie, Yibo Yang, Wenxiao Wang, Binbin Lin, Deng Cai

One of the challenges in federated learning is the non-independent and identically distributed (non-iid) characteristics between heterogeneous devices, which cause significant differences in local updates and affect the performance of the central server.

Federated Learning

Neural Collapse Inspired Feature-Classifier Alignment for Few-Shot Class Incremental Learning

1 code implementation6 Feb 2023 Yibo Yang, Haobo Yuan, Xiangtai Li, Zhouchen Lin, Philip Torr, DaCheng Tao

In this paper, we deal with this misalignment dilemma in FSCIL inspired by the recently discovered phenomenon named neural collapse, which reveals that the last-layer features of the same class will collapse into a vertex, and the vertices of all classes are aligned with the classifier prototypes, which are formed as a simplex equiangular tight frame (ETF).

Few-Shot Class-Incremental Learning Incremental Learning

Neural Collapse Inspired Feature-Classifier Alignment for Few-Shot Class-Incremental Learning

1 code implementation ICLR 2023 Yibo Yang, Haobo Yuan, Xiangtai Li, Zhouchen Lin, Philip Torr, DaCheng Tao

In this paper, we deal with this misalignment dilemma in FSCIL inspired by the recently discovered phenomenon named neural collapse, which reveals that the last-layer features of the same class will collapse into a vertex, and the vertices of all classes are aligned with the classifier prototypes, which are formed as a simplex equiangular tight frame (ETF).

Few-Shot Class-Incremental Learning Incremental Learning

DeMT: Deformable Mixer Transformer for Multi-Task Learning of Dense Prediction

2 code implementations9 Jan 2023 Yangyang Xu, Yibo Yang, Lefei Zhang

In this work, we present a novel MTL model by combining both merits of deformable CNN and query-based Transformer for multi-task learning of dense prediction.

Multi-Task Learning

Understanding Imbalanced Semantic Segmentation Through Neural Collapse

2 code implementations CVPR 2023 Zhisheng Zhong, Jiequan Cui, Yibo Yang, Xiaoyang Wu, Xiaojuan Qi, Xiangyu Zhang, Jiaya Jia

Based on our empirical and theoretical analysis, we point out that semantic segmentation naturally brings contextual correlation and imbalanced distribution among classes, which breaks the equiangular and maximally separated structure of neural collapse for both feature centers and classifiers.

3D Semantic Segmentation Segmentation

PanopticPartFormer++: A Unified and Decoupled View for Panoptic Part Segmentation

1 code implementation3 Jan 2023 Xiangtai Li, Shilin Xu, Yibo Yang, Haobo Yuan, Guangliang Cheng, Yunhai Tong, Zhouchen Lin, Ming-Hsuan Yang, DaCheng Tao

Third, inspired by Mask2Former, based on our meta-architecture, we propose Panoptic-PartFormer++ and design a new part-whole cross-attention scheme to boost part segmentation qualities further.

Panoptic Segmentation Segmentation

Multi-Task Learning with Knowledge Distillation for Dense Prediction

no code implementations ICCV 2023 Yangyang Xu, Yibo Yang, Lefei Zhang

With the less sensitive divergence, our knowledge distillation with an alternative match is applied for capturing inter-task and intra-task information between the teacher model and the student model of each task, thereby learning more "dark knowledge" for effective distillation.

Boundary Detection Depth Estimation +4

Problem-Dependent Power of Quantum Neural Networks on Multi-Class Classification

no code implementations29 Dec 2022 Yuxuan Du, Yibo Yang, DaCheng Tao, Min-Hsiu Hsieh

Using these findings, we propose a method that uses loss dynamics to probe whether a QC may be more effective than a classical classifier on a particular learning task.

Multi-class Classification

Towards Theoretically Inspired Neural Initialization Optimization

1 code implementation12 Oct 2022 Yibo Yang, Hong Wang, Haobo Yuan, Zhouchen Lin

With NIO, we improve the classification performance of a variety of neural architectures on CIFAR-10, CIFAR-100, and ImageNet.

Eliminating Gradient Conflict in Reference-based Line-Art Colorization

1 code implementation13 Jul 2022 Zekun Li, Zhengyang Geng, Zhao Kang, Wenyu Chen, Yibo Yang

To understand the instability in training, we detect the gradient flow of attention and observe gradient conflict among attention branches.

Line Art Colorization SSIM

EATFormer: Improving Vision Transformer Inspired by Evolutionary Algorithm

1 code implementation19 Jun 2022 Jiangning Zhang, Xiangtai Li, Yabiao Wang, Chengjie Wang, Yibo Yang, Yong liu, DaCheng Tao

Motivated by biological evolution, this paper explains the rationality of Vision Transformer by analogy with the proven practical Evolutionary Algorithm (EA) and derives that both have consistent mathematical formulation.

Image Classification

ART-Point: Improving Rotation Robustness of Point Cloud Classifiers via Adversarial Rotation

1 code implementation CVPR 2022 Robin Wang, Yibo Yang, DaCheng Tao

Specifically, our proposed framework named ART-Point regards the rotation of the point cloud as an attack and improves rotation robustness by training the classifier on inputs with Adversarial RoTations.

Scalable Uncertainty Quantification for Deep Operator Networks using Randomized Priors

1 code implementation6 Mar 2022 Yibo Yang, Georgios Kissas, Paris Perdikaris

Finally, we provide an optimized JAX library called {\em UQDeepONet} that can accommodate large model architectures, large ensemble sizes, as well as large data-sets with excellent parallel performance on accelerated hardware, thereby enabling uncertainty quantification for DeepONets in realistic large-scale applications.

Uncertainty Quantification

An Introduction to Neural Data Compression

2 code implementations14 Feb 2022 Yibo Yang, Stephan Mandt, Lucas Theis

Neural compression is the application of neural networks and other machine learning methods to data compression.

BIG-bench Machine Learning Data Compression +1

TransVOD: End-to-End Video Object Detection with Spatial-Temporal Transformers

3 code implementations13 Jan 2022 Qianyu Zhou, Xiangtai Li, Lu He, Yibo Yang, Guangliang Cheng, Yunhai Tong, Lizhuang Ma, DaCheng Tao

Detection Transformer (DETR) and Deformable DETR have been proposed to eliminate the need for many hand-designed components in object detection while demonstrating good performance as previous complex hand-crafted detectors.

Ranked #4 on Video Object Detection on ImageNet VID (using extra training data)

Object object-detection +2

Dual-Flow Transformation Network for Deformable Image Registration with Region Consistency Constraint

no code implementations4 Dec 2021 Xinke Ma, Yibo Yang, Yong Xia, DaCheng Tao

In this paper, we present a novel dual-flow transformation network with region consistency constraint which maximizes the similarity of ROIs within a pair of images and estimates both global and region spatial transformations simultaneously.

Image Registration

Towards Empirical Sandwich Bounds on the Rate-Distortion Function

2 code implementations ICLR 2022 Yibo Yang, Stephan Mandt

By contrast, this paper makes the first attempt at an algorithm for sandwiching the R-D function of a general (not necessarily discrete) source requiring only i. i. d.

Data Compression Image Compression

Improving Video Instance Segmentation via Temporal Pyramid Routing

1 code implementation28 Jul 2021 Xiangtai Li, Hao He, Yibo Yang, Henghui Ding, Kuiyuan Yang, Guangliang Cheng, Yunhai Tong, DaCheng Tao

To incorporate both temporal and scale information, we propose a Temporal Pyramid Routing (TPR) strategy to conditionally align and conduct pixel-level aggregation from a feature pyramid pair of two adjacent frames.

Instance Segmentation Panoptic Segmentation +2

Insights from Generative Modeling for Neural Video Compression

1 code implementation28 Jul 2021 Ruihan Yang, Yibo Yang, Joseph Marino, Stephan Mandt

While recent machine learning research has revealed connections between deep generative models such as VAEs and rate-distortion losses used in learned compression, most of this work has focused on images.

Video Compression

BoundarySqueeze: Image Segmentation as Boundary Squeezing

1 code implementation25 May 2021 Hao He, Xiangtai Li, Yibo Yang, Guangliang Cheng, Yunhai Tong, Lubin Weng, Zhouchen Lin, Shiming Xiang

This module is used to squeeze the object boundary from both inner and outer directions, which contributes to precise mask representation.

Image Segmentation Instance Segmentation +2

Lower Bounding Rate-Distortion From Samples

no code implementations ICLR Workshop Neural_Compression 2021 Yibo Yang, Stephan Mandt

The rate-distortion function tells us the minimal number of bits on average to compress a random object within a given distortion tolerance.

Stochastic Optimization

SCALE SPACE FLOW WITH AUTOREGRESSIVE PRIORS

no code implementations ICLR Workshop Neural_Compression 2021 Ruihan Yang, Yibo Yang, Joseph Marino, Stephan Mandt

There has been a recent surge of interest in neural video compression models that combines data-driven dimensionality reduction with learned entropy coding.

Dimensionality Reduction Open-Ended Question Answering +1

Output-Weighted Sampling for Multi-Armed Bandits with Extreme Payoffs

1 code implementation19 Feb 2021 Yibo Yang, Antoine Blanchard, Themistoklis Sapsis, Paris Perdikaris

We present a new type of acquisition functions for online decision making in multi-armed and contextual bandit problems with extreme payoffs.

Decision Making Gaussian Processes +1

Towards Improving the Consistency, Efficiency, and Flexibility of Differentiable Neural Architecture Search

no code implementations CVPR 2021 Yibo Yang, Shan You, Hongyang Li, Fei Wang, Chen Qian, Zhouchen Lin

Our method enables differentiable sparsification, and keeps the derived architecture equivalent to that of Engine-cell, which further improves the consistency between search and evaluation.

Neural Architecture Search

Explicit Learning Topology for Differentiable Neural Architecture Search

no code implementations1 Jan 2021 Tao Huang, Shan You, Yibo Yang, Zhuozhuo Tu, Fei Wang, Chen Qian, ChangShui Zhang

Differentiable neural architecture search (NAS) has gained much success in discovering more flexible and diverse cell types.

Neural Architecture Search

EnTranNAS: Towards Closing the Gap between the Architectures in Search and Evaluation

no code implementations1 Jan 2021 Yibo Yang, Shan You, Hongyang Li, Fei Wang, Chen Qian, Zhouchen Lin

The Engine-cell is differentiable for architecture search, while the Transit-cell only transits the current sub-graph by architecture derivation.

Neural Architecture Search

Generative Video Compression as Hierarchical Variational Inference

no code implementations pproximateinference AABI Symposium 2021 Ruihan Yang, Yibo Yang, Joseph Marino, Stephan Mandt

Recent work by Marino et al. (2020) showed improved performance in sequential density estimation by combining masked autoregressive flows with hierarchical latent variable models.

Density Estimation Variational Inference +1

Stretchable Cells Help DARTS Search Better

no code implementations18 Nov 2020 Tao Huang, Shan You, Yibo Yang, Zhuozhuo Tu, Fei Wang, Chen Qian, ChangShui Zhang

However, even for this consistent search, the searched cells often suffer from poor performance, especially for the supernet with fewer layers, as current DARTS methods are prone to wide and shallow cells, and this topology collapse induces sub-optimal searched cells.

Neural Architecture Search

Hierarchical Autoregressive Modeling for Neural Video Compression

3 code implementations ICLR 2021 Ruihan Yang, Yibo Yang, Joseph Marino, Stephan Mandt

Recent work by Marino et al. (2020) showed improved performance in sequential density estimation by combining masked autoregressive flows with hierarchical latent variable models.

Density Estimation Video Compression

Bayesian differential programming for robust systems identification under uncertainty

1 code implementation15 Apr 2020 Yibo Yang, Mohamed Aziz Bhouri, Paris Perdikaris

This paper presents a machine learning framework for Bayesian systems identification from noisy, sparse and irregular observations of nonlinear dynamical systems.

Bayesian Inference Model Discovery

Spatial Pyramid Based Graph Reasoning for Semantic Segmentation

no code implementations CVPR 2020 Xia Li, Yibo Yang, Qijie Zhao, Tiancheng Shen, Zhouchen Lin, Hong Liu

The convolution operation suffers from a limited receptive filed, while global modeling is fundamental to dense prediction tasks, such as semantic segmentation.

Segmentation Semantic Segmentation

Variational Bayesian Quantization

2 code implementations ICML 2020 Yibo Yang, Robert Bamler, Stephan Mandt

Our experimental results demonstrate the importance of taking into account posterior uncertainties, and show that image compression with the proposed algorithm outperforms JPEG over a wide range of bit rates using only a single standard VAE.

Image Compression Model Compression +2

Lifted Hybrid Variational Inference

1 code implementation8 Jan 2020 Yuqiao Chen, Yibo Yang, Sriraam Natarajan, Nicholas Ruozzi

We demonstrate that the proposed variational methods are both scalable and can take advantage of approximate model symmetries, even in the presence of a large amount of continuous evidence.

Variational Inference

Dynamical System Inspired Adaptive Time Stepping Controller for Residual Network Families

no code implementations23 Nov 2019 Yibo Yang, Jianlong Wu, Hongyang Li, Xia Li, Tiancheng Shen, Zhouchen Lin

We establish a stability condition for ResNets with step sizes and weight parameters, and point out the effects of step sizes on the stability and performance.

SOGNet: Scene Overlap Graph Network for Panoptic Segmentation

1 code implementation18 Nov 2019 Yibo Yang, Hongyang Li, Xia Li, Qijie Zhao, Jianlong Wu, Zhouchen Lin

In order to overcome the lack of supervision, we introduce a differentiable module to resolve the overlap between any pair of instances.

Instance Segmentation Panoptic Segmentation +1

Machine learning in cardiovascular flows modeling: Predicting arterial blood pressure from non-invasive 4D flow MRI data using physics-informed neural networks

1 code implementation13 May 2019 Georgios Kissas, Yibo Yang, Eileen Hwuang, Walter R. Witschey, John A. Detre, Paris Perdikaris

Such models can be nowadays deployed on large patient-specific topologies of systemic arterial networks and return detailed predictions on flow patterns, wall shear stresses, and pulse wave propagation.

Conditional deep surrogate models for stochastic, high-dimensional, and multi-fidelity systems

2 code implementations15 Jan 2019 Yibo Yang, Paris Perdikaris

We present a probabilistic deep learning methodology that enables the construction of predictive data-driven surrogates for stochastic systems.

Probabilistic Deep Learning Variational Inference

Physics-informed deep generative models

no code implementations9 Dec 2018 Yibo Yang, Paris Perdikaris

We consider the application of deep generative models in propagating uncertainty through complex physical systems.

Variational Inference

Adversarial Uncertainty Quantification in Physics-Informed Neural Networks

2 code implementations9 Nov 2018 Yibo Yang, Paris Perdikaris

We present a deep learning framework for quantifying and propagating uncertainty in systems governed by non-linear differential equations using physics-informed neural networks.

Uncertainty Quantification

Optimization Algorithm Inspired Deep Neural Network Structure Design

no code implementations3 Oct 2018 Huan Li, Yibo Yang, Dongmin Chen, Zhouchen Lin

In this paper, we propose the hypothesis that the neural network structure design can be inspired by optimization algorithms and a faster optimization algorithm may lead to a better neural network structure.

Joint Sub-bands Learning with Clique Structures for Wavelet Domain Super-Resolution

no code implementations NeurIPS 2018 Zhisheng Zhong, Tiancheng Shen, Yibo Yang, Zhouchen Lin, Chao Zhang

To solve these problems, we propose the Super-Resolution CliqueNet (SRCliqueNet) to reconstruct the high resolution (HR) image with better textural details in the wavelet domain.

Image Super-Resolution

Scalable Neural Network Compression and Pruning Using Hard Clustering and L1 Regularization

no code implementations14 Jun 2018 Yibo Yang, Nicholas Ruozzi, Vibhav Gogate

We propose a simple and easy to implement neural network compression algorithm that achieves results competitive with more complicated state-of-the-art methods.

Clustering Neural Network Compression +1

Convolutional Neural Networks with Alternately Updated Clique

3 code implementations CVPR 2018 Yibo Yang, Zhisheng Zhong, Tiancheng Shen, Zhouchen Lin

In contrast to prior networks, there are both forward and backward connections between any two layers in the same block.

Automatic Parameter Tying in Neural Networks

no code implementations ICLR 2018 Yibo Yang, Nicholas Ruozzi, Vibhav Gogate

Recently, there has been growing interest in methods that perform neural network compression, namely techniques that attempt to substantially reduce the size of a neural network without significant reduction in performance.

L2 Regularization Neural Network Compression +1

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