Search Results for author: Shuchang Zhou

Found 43 papers, 23 papers with code

A Survey on Video Prediction: From Deterministic to Generative Approaches

no code implementations26 Jan 2024 Ruibo Ming, Zhewei Huang, Zhuoxuan Ju, Jianming Hu, Lihui Peng, Shuchang Zhou

Video prediction, a fundamental task in computer vision, aims to enable models to generate sequences of future frames based on existing video content.

Video Prediction

Scale-Adaptive Feature Aggregation for Efficient Space-Time Video Super-Resolution

1 code implementation26 Oct 2023 Zhewei Huang, Ailin Huang, Xiaotao Hu, Chen Hu, Jun Xu, Shuchang Zhou

The Space-Time Video Super-Resolution (STVSR) task aims to enhance the visual quality of videos, by simultaneously performing video frame interpolation (VFI) and video super-resolution (VSR).

Space-time Video Super-resolution Video Frame Interpolation +1

Editing 3D Scenes via Text Prompts without Retraining

1 code implementation10 Sep 2023 Shuangkang Fang, Yufeng Wang, Yi Yang, Yi-Hsuan Tsai, Wenrui Ding, Shuchang Zhou, Ming-Hsuan Yang

To tackle these issues, we introduce a text-driven editing method, termed DN2N, which allows for the direct acquisition of a NeRF model with universal editing capabilities, eliminating the requirement for retraining.

3D scene Editing 3D Scene Reconstruction +2

Proximal Policy Optimization Actual Combat: Manipulating Output Tokenizer Length

no code implementations10 Aug 2023 Miao Fan, Chen Hu, Shuchang Zhou

In this paper, we introduce a simple task designed to employ Gloden as a reward model that validates the effectiveness of PPO and inspires it, primarily explaining the task of utilizing PPO to manipulate the tokenizer length of the output generated by the model.

PVD-AL: Progressive Volume Distillation with Active Learning for Efficient Conversion Between Different NeRF Architectures

1 code implementation8 Apr 2023 Shuangkang Fang, Yufeng Wang, Yi Yang, Weixin Xu, Heng Wang, Wenrui Ding, Shuchang Zhou

To address this limitation and maximize the potential of each architecture, we propose Progressive Volume Distillation with Active Learning (PVD-AL), a systematic distillation method that enables any-to-any conversions between different architectures.

3D Reconstruction Novel View Synthesis

Three Guidelines You Should Know for Universally Slimmable Self-Supervised Learning

1 code implementation CVPR 2023 Yun-Hao Cao, Peiqin Sun, Shuchang Zhou

We propose universally slimmable self-supervised learning (dubbed as US3L) to achieve better accuracy-efficiency trade-offs for deploying self-supervised models across different devices.

Instance Segmentation object-detection +3

OccDepth: A Depth-Aware Method for 3D Semantic Scene Completion

1 code implementation27 Feb 2023 Ruihang Miao, Weizhou Liu, Mingrui Chen, Zheng Gong, Weixin Xu, Chen Hu, Shuchang Zhou

3D Semantic Scene Completion (SSC) can provide dense geometric and semantic scene representations, which can be applied in the field of autonomous driving and robotic systems.

3D Semantic Scene Completion Autonomous Driving +1

Occ^2Net: Robust Image Matching Based on 3D Occupancy Estimation for Occluded Regions

no code implementations ICCV 2023 Miao Fan, Mingrui Chen, Chen Hu, Shuchang Zhou

Image matching is a fundamental and critical task in various visual applications, such as Simultaneous Localization and Mapping (SLAM) and image retrieval, which require accurate pose estimation.

Image Retrieval Inductive Bias +3

One is All: Bridging the Gap Between Neural Radiance Fields Architectures with Progressive Volume Distillation

1 code implementation29 Nov 2022 Shuangkang Fang, Weixin Xu, Heng Wang, Yi Yang, Yufeng Wang, Shuchang Zhou

In this paper, we propose Progressive Volume Distillation (PVD), a systematic distillation method that allows any-to-any conversions between different architectures, including MLP, sparse or low-rank tensors, hashtables and their compositions.

 Ranked #1 on Novel View Synthesis on NeRF (Average PSNR metric)

3D Reconstruction Neural Rendering +1

Synergistic Self-supervised and Quantization Learning

1 code implementation12 Jul 2022 Yun-Hao Cao, Peiqin Sun, Yechang Huang, Jianxin Wu, Shuchang Zhou

In this paper, we propose a method called synergistic self-supervised and quantization learning (SSQL) to pretrain quantization-friendly self-supervised models facilitating downstream deployment.

Quantization Self-Supervised Learning

Perceptual Conversational Head Generation with Regularized Driver and Enhanced Renderer

1 code implementation26 Jun 2022 Ailin Huang, Zhewei Huang, Shuchang Zhou

This paper reports our solution for ACM Multimedia ViCo 2022 Conversational Head Generation Challenge, which aims to generate vivid face-to-face conversation videos based on audio and reference images.

Talking Head Generation

ML4CO-KIDA: Knowledge Inheritance in Dataset Aggregation

1 code implementation25 Jan 2022 Zixuan Cao, Yang Xu, Zhewei Huang, Shuchang Zhou

The Machine Learning for Combinatorial Optimization (ML4CO) NeurIPS 2021 competition aims to improve state-of-the-art combinatorial optimization solvers by replacing key heuristic components with machine learning models.

BIG-bench Machine Learning Combinatorial Optimization

FQ-ViT: Post-Training Quantization for Fully Quantized Vision Transformer

1 code implementation27 Nov 2021 Yang Lin, Tianyu Zhang, Peiqin Sun, Zheng Li, Shuchang Zhou

Network quantization significantly reduces model inference complexity and has been widely used in real-world deployments.

Quantization

Arch-Net: Model Distillation for Architecture Agnostic Model Deployment

1 code implementation1 Nov 2021 Weixin Xu, Zipeng Feng, Shuangkang Fang, Song Yuan, Yi Yang, Shuchang Zhou

For example, Transformer Networks do not have native support on many popular chips, and hence are difficult to deploy.

Image Classification Machine Translation +2

Optimal Quantization for Batch Normalization in Neural Network Deployments and Beyond

no code implementations30 Aug 2020 Dachao Lin, Peiqin Sun, Guangzeng Xie, Shuchang Zhou, Zhihua Zhang

Quantized Neural Networks (QNNs) use low bit-width fixed-point numbers for representing weight parameters and activations, and are often used in real-world applications due to their saving of computation resources and reproducibility of results.

Quantization

Learning to Paint With Model-based Deep Reinforcement Learning

6 code implementations ICCV 2019 Zhewei Huang, Wen Heng, Shuchang Zhou

We show how to teach machines to paint like human painters, who can use a small number of strokes to create fantastic paintings.

Position reinforcement-learning +1

Accelerated Value Iteration via Anderson Mixing

no code implementations27 Sep 2018 YuJun Li, Chengzhuo Ni, Guangzeng Xie, Wenhao Yang, Shuchang Zhou, Zhihua Zhang

A2VI is more efficient than the modified policy iteration, which is a classical approximate method for policy evaluation.

Atari Games Q-Learning +2

Harmonic Adversarial Attack Method

no code implementations18 Jul 2018 Wen Heng, Shuchang Zhou, Tingting Jiang

The property of edge-free guarantees that the generated adversarial images can still preserve visual quality, even when perturbations are of large magnitudes.

Adversarial Attack

Stroke-based Character Reconstruction

1 code implementation23 Jun 2018 Zhewei Huang, Wen Heng, Yuanzheng Tao, Shuchang Zhou

Background elimination for noisy character images or character images from real scene is still a challenging problem, due to the bewildering backgrounds, uneven illumination, low resolution and different distortions.

Interpolatron: Interpolation or Extrapolation Schemes to Accelerate Optimization for Deep Neural Networks

no code implementations17 May 2018 Guangzeng Xie, Yitan Wang, Shuchang Zhou, Zhihua Zhang

In this paper we explore acceleration techniques for large scale nonconvex optimization problems with special focuses on deep neural networks.

Learning to Run with Actor-Critic Ensemble

2 code implementations25 Dec 2017 Zhewei Huang, Shuchang Zhou, BoEr Zhuang, Xinyu Zhou

We introduce an Actor-Critic Ensemble(ACE) method for improving the performance of Deep Deterministic Policy Gradient(DDPG) algorithm.

Balanced Quantization: An Effective and Efficient Approach to Quantized Neural Networks

no code implementations22 Jun 2017 Shuchang Zhou, Yuzhi Wang, He Wen, Qinyao He, Yuheng Zou

Overall, our method improves the prediction accuracies of QNNs without introducing extra computation during inference, has negligible impact on training speed, and is applicable to both Convolutional Neural Networks and Recurrent Neural Networks.

Quantization

GeneGAN: Learning Object Transfiguration and Attribute Subspace from Unpaired Data

2 code implementations14 May 2017 Shuchang Zhou, Taihong Xiao, Yi Yang, Dieqiao Feng, Qinyao He, Weiran He

In this work, we propose a model that can learn object transfiguration from two unpaired sets of images: one set containing images that "have" that kind of object, and the other set being the opposite, with the mild constraint that the objects be located approximately at the same place.

Attribute Conditional Image Generation +1

Training Bit Fully Convolutional Network for Fast Semantic Segmentation

no code implementations1 Dec 2016 He Wen, Shuchang Zhou, Zhe Liang, Yuxiang Zhang, Dieqiao Feng, Xinyu Zhou, Cong Yao

Fully convolutional neural networks give accurate, per-pixel prediction for input images and have applications like semantic segmentation.

Segmentation Semantic Segmentation

Effective Quantization Methods for Recurrent Neural Networks

2 code implementations30 Nov 2016 Qinyao He, He Wen, Shuchang Zhou, Yuxin Wu, Cong Yao, Xinyu Zhou, Yuheng Zou

In addition, we propose balanced quantization methods for weights to further reduce performance degradation.

Quantization

Scene Text Detection via Holistic, Multi-Channel Prediction

no code implementations29 Jun 2016 Cong Yao, Xiang Bai, Nong Sang, Xinyu Zhou, Shuchang Zhou, Zhimin Cao

Recently, scene text detection has become an active research topic in computer vision and document analysis, because of its great importance and significant challenge.

Scene Text Detection Semantic Segmentation +1

DoReFa-Net: Training Low Bitwidth Convolutional Neural Networks with Low Bitwidth Gradients

12 code implementations20 Jun 2016 Shuchang Zhou, Yuxin Wu, Zekun Ni, Xinyu Zhou, He Wen, Yuheng Zou

We propose DoReFa-Net, a method to train convolutional neural networks that have low bitwidth weights and activations using low bitwidth parameter gradients.

Quantization

Exploiting Local Structures with the Kronecker Layer in Convolutional Networks

no code implementations31 Dec 2015 Shuchang Zhou, Jia-Nan Wu, Yuxin Wu, Xinyu Zhou

In this paper, we propose and study a technique to reduce the number of parameters and computation time in convolutional neural networks.

Scene Text Recognition

Incidental Scene Text Understanding: Recent Progresses on ICDAR 2015 Robust Reading Competition Challenge 4

no code implementations30 Nov 2015 Cong Yao, Jia-Nan Wu, Xinyu Zhou, Chi Zhang, Shuchang Zhou, Zhimin Cao, Qi Yin

Different from focused texts present in natural images, which are captured with user's intention and intervention, incidental texts usually exhibit much more diversity, variability and complexity, thus posing significant difficulties and challenges for scene text detection and recognition algorithms.

Scene Text Detection Text Detection

Multilinear Map Layer: Prediction Regularization by Structural Constraint

no code implementations30 Jul 2015 Shuchang Zhou, Yuxin Wu

In this paper we propose and study a technique to impose structural constraints on the output of a neural network, which can reduce amount of computation and number of parameters besides improving prediction accuracy when the output is known to approximately conform to the low-rankness prior.

Compression of Fully-Connected Layer in Neural Network by Kronecker Product

no code implementations21 Jul 2015 Shuchang Zhou, Jia-Nan Wu

In this paper we propose and study a technique to reduce the number of parameters and computation time in fully-connected layers of neural networks using Kronecker product, at a mild cost of the prediction quality.

ICDAR 2015 Text Reading in the Wild Competition

no code implementations10 Jun 2015 Xinyu Zhou, Shuchang Zhou, Cong Yao, Zhimin Cao, Qi Yin

Recently, text detection and recognition in natural scenes are becoming increasing popular in the computer vision community as well as the document analysis community.

Text Detection

Group Orbit Optimization: A Unified Approach to Data Normalization

no code implementations3 Oct 2014 Shuchang Zhou, Zhihua Zhang, Xiaobing Feng

In this paper we propose and study an optimization problem over a matrix group orbit that we call \emph{Group Orbit Optimization} (GOO).

Tensor Decomposition

Kinetic Energy Plus Penalty Functions for Sparse Estimation

no code implementations22 Jul 2013 Zhihua Zhang, Shibo Zhao, Zebang Shen, Shuchang Zhou

In this paper we propose and study a family of sparsity-inducing penalty functions.

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