Search Results for author: Dawei Yang

Found 21 papers, 9 papers with code

Panoptic-FlashOcc: An Efficient Baseline to Marry Semantic Occupancy with Panoptic via Instance Center

1 code implementation15 Jun 2024 Zichen Yu, Changyong Shu, Qianpu Sun, Yifan Bian, Xiaobao Wei, Jiangyong Yu, Zongdai Liu, Dawei Yang, Hui Li, Yan Chen

On the Occ3D-nuScenes benchmark, it achieves exceptional performance, with 38. 5 RayIoU and 29. 1 mIoU for semantic occupancy, operating at a rapid speed of 43. 9 FPS.

M&M VTO: Multi-Garment Virtual Try-On and Editing

1 code implementation CVPR 2024 Luyang Zhu, Yingwei Li, Nan Liu, Hao Peng, Dawei Yang, Ira Kemelmacher-Shlizerman

We present M&M VTO, a mix and match virtual try-on method that takes as input multiple garment images, text description for garment layout and an image of a person.

Denoising Super-Resolution +1

PillarHist: A Quantization-aware Pillar Feature Encoder based on Height-aware Histogram

no code implementations29 May 2024 Sifan Zhou, Zhihang Yuan, Dawei Yang, Xubin Wen, Xing Hu, Yuguang Shi, Ziyu Zhao, Xiaobo Lu

To address above issue, we first unveil the importance of different input information during PFE and identify the height dimension as a key factor in enhancing 3D detection performance.

3D Object Detection Autonomous Driving +2

I-LLM: Efficient Integer-Only Inference for Fully-Quantized Low-Bit Large Language Models

no code implementations28 May 2024 Xing Hu, Yuan Cheng, Dawei Yang, Zhihang Yuan, Jiangyong Yu, Chen Xu, Sifan Zhou

Post-training quantization (PTQ) serves as a potent technique to accelerate the inference of large language models (LLMs).

Quantization

Post-Training Quantization for Re-parameterization via Coarse & Fine Weight Splitting

1 code implementation17 Dec 2023 Dawei Yang, Ning He, Xing Hu, Zhihang Yuan, Jiangyong Yu, Chen Xu, Zhe Jiang

Although neural networks have made remarkable advancements in various applications, they require substantial computational and memory resources.

Quantization

FlashOcc: Fast and Memory-Efficient Occupancy Prediction via Channel-to-Height Plugin

1 code implementation18 Nov 2023 Zichen Yu, Changyong Shu, Jiajun Deng, Kangjie Lu, Zongdai Liu, Jiangyong Yu, Dawei Yang, Hui Li, Yan Chen

We apply the FlashOCC to diverse occupancy prediction baselines on the challenging Occ3D-nuScenes benchmarks and conduct extensive experiments to validate the effectiveness.

3D Object Detection Autonomous Driving +1

Unpaired Optical Coherence Tomography Angiography Image Super-Resolution via Frequency-Aware Inverse-Consistency GAN

no code implementations29 Sep 2023 Weiwen Zhang, Dawei Yang, Haoxuan Che, An Ran Ran, Carol Y. Cheung, Hao Chen

For optical coherence tomography angiography (OCTA) images, a limited scanning rate leads to a trade-off between field-of-view (FOV) and imaging resolution.

Generative Adversarial Network Image Super-Resolution

TryOnDiffusion: A Tale of Two UNets

1 code implementation CVPR 2023 Luyang Zhu, Dawei Yang, Tyler Zhu, Fitsum Reda, William Chan, Chitwan Saharia, Mohammad Norouzi, Ira Kemelmacher-Shlizerman

Given two images depicting a person and a garment worn by another person, our goal is to generate a visualization of how the garment might look on the input person.

Virtual Try-on

Reference-based OCT Angiogram Super-resolution with Learnable Texture Generation

no code implementations10 May 2023 Yuyan Ruan, Dawei Yang, Ziqi Tang, An Ran Ran, Carol Y. Cheung, Hao Chen

The key difference between the proposed method and traditional RefSR models is that the textures used during inference are generated by the LTG instead of being searched from a single reference image.

Reference-based Super-Resolution Texture Synthesis

Benchmarking the Reliability of Post-training Quantization: a Particular Focus on Worst-case Performance

no code implementations23 Mar 2023 Zhihang Yuan, Jiawei Liu, Jiaxiang Wu, Dawei Yang, Qiang Wu, Guangyu Sun, Wenyu Liu, Xinggang Wang, Bingzhe Wu

Post-training quantization (PTQ) is a popular method for compressing deep neural networks (DNNs) without modifying their original architecture or training procedures.

Benchmarking Data Augmentation +1

Foreground-Background Distribution Modeling Transformer for Visual Object Tracking

no code implementations ICCV 2023 Dawei Yang, Jianfeng He, Yinchao Ma, Qianjin Yu, Tianzhu Zhang

To address the above limitations, we propose a novel foreground-background distribution modeling transformer for visual object tracking (F-BDMTrack), including a fore-background agent learning (FBAL) module and a distribution-aware attention (DA2) module in a unified transformer architecture.

Object Visual Object Tracking

PD-Quant: Post-Training Quantization based on Prediction Difference Metric

1 code implementation CVPR 2023 Jiawei Liu, Lin Niu, Zhihang Yuan, Dawei Yang, Xinggang Wang, Wenyu Liu

It determines the quantization parameters by using the information of differences between network prediction before and after quantization.

Neural Network Compression Quantization

Rel3D: A Minimally Contrastive Benchmark for Grounding Spatial Relations in 3D

2 code implementations NeurIPS 2020 Ankit Goyal, Kaiyu Yang, Dawei Yang, Jia Deng

The 3D scenes in our dataset come in minimally contrastive pairs: two scenes in a pair are almost identical, but a spatial relation holds in one and fails in the other.

Relation Spatial Relation Recognition

Learning to Generate 3D Training Data Through Hybrid Gradient

no code implementations CVPR 2020 Dawei Yang, Jia Deng

We parametrize the design decisions as a real vector, and combine the approximate gradient and the analytical gradient to obtain the hybrid gradient of the network performance with respect to this vector.

Computational Efficiency

Adversarial Objects Against LiDAR-Based Autonomous Driving Systems

no code implementations11 Jul 2019 Yulong Cao, Chaowei Xiao, Dawei Yang, Jing Fang, Ruigang Yang, Mingyan Liu, Bo Li

Deep neural networks (DNNs) are found to be vulnerable against adversarial examples, which are carefully crafted inputs with a small magnitude of perturbation aiming to induce arbitrarily incorrect predictions.

Autonomous Driving

Learning to Generate Synthetic 3D Training Data through Hybrid Gradient

no code implementations29 Jun 2019 Dawei Yang, Jia Deng

We parametrize the design decisions as a real vector, and combine the approximate gradient and the analytical gradient to obtain the hybrid gradient of the network performance with respect to this vector.

Computational Efficiency

MeshAdv: Adversarial Meshes for Visual Recognition

no code implementations CVPR 2019 Chaowei Xiao, Dawei Yang, Bo Li, Jia Deng, Mingyan Liu

Highly expressive models such as deep neural networks (DNNs) have been widely applied to various applications.

Decorrelated Batch Normalization

6 code implementations CVPR 2018 Lei Huang, Dawei Yang, Bo Lang, Jia Deng

Batch Normalization (BN) is capable of accelerating the training of deep models by centering and scaling activations within mini-batches.

Shape from Shading through Shape Evolution

no code implementations CVPR 2018 Dawei Yang, Jia Deng

The evolution generates better shapes guided by the network training, while the training improves by using the evolved shapes.

Single-Image Depth Perception in the Wild

4 code implementations NeurIPS 2016 Weifeng Chen, Zhao Fu, Dawei Yang, Jia Deng

This paper studies single-image depth perception in the wild, i. e., recovering depth from a single image taken in unconstrained settings.

Depth Estimation

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