Search Results for author: Pan Gao

Found 9 papers, 6 papers with code

UperFormer: A Multi-scale Transformer-based Decoder for Semantic Segmentation

1 code implementation25 Nov 2022 Jing Xu, Wentao Shi, Pan Gao, Zhengwei Wang, Qizhu Li

On the more challenging ADE20K dataset, our best model yields a single-scale mIoU of 50. 18, and a multi-scale mIoU of 51. 8, which is on-par with the current state-of-art model, while we drastically cut the number of FLOPs by 53. 5%.

Object Localization Semantic Segmentation

IPDAE: Improved Patch-Based Deep Autoencoder for Lossy Point Cloud Geometry Compression

1 code implementation4 Aug 2022 Kang You, Pan Gao, Qing Li

Point cloud is a crucial representation of 3D contents, which has been widely used in many areas such as virtual reality, mixed reality, autonomous driving, etc.

Autonomous Driving Mixed Reality

SSformer: A Lightweight Transformer for Semantic Segmentation

1 code implementation3 Aug 2022 Wentao Shi, Jing Xu, Pan Gao

It is well believed that Transformer performs better in semantic segmentation compared to convolutional neural networks.

Image Classification Semantic Segmentation

Video-based Smoky Vehicle Detection with A Coarse-to-Fine Framework

no code implementations8 Jul 2022 Xiaojiang Peng, Xiaomao Fan, Qingyang Wu, Jieyan Zhao, Pan Gao

Moreover, we present a new Coarse-to-fine Deep Smoky vehicle detection (CoDeS) framework for efficient smoky vehicle detection.

Video Frame Interpolation Based on Deformable Kernel Region

1 code implementation25 Apr 2022 Haoyue Tian, Pan Gao, Xiaojiang Peng

In order to solve this problem, we revisit the deformable convolution for video interpolation, which can break the fixed grid restrictions on the kernel region, making the distribution of reference points more suitable for the shape of the object, and thus warp a more accurate interpolation frame.

Optical Flow Estimation Video Frame Interpolation

Patch-Based Deep Autoencoder for Point Cloud Geometry Compression

1 code implementation18 Oct 2021 Kang You, Pan Gao

Unlike existing point cloud compression networks, which apply feature extraction and reconstruction on the entire point cloud, we divide the point cloud into patches and compress each patch independently.

Point cloud reconstruction

Countering Adversarial Examples: Combining Input Transformation and Noisy Training

no code implementations25 Jun 2021 Cheng Zhang, Pan Gao

Prior work has shown that JPEG compression can combat the drop in classification accuracy on adversarial examples to some extent.

Data Augmentation Quantization

Defending Adversaries Using Unsupervised Feature Clustering VAE

no code implementations ICML Workshop AML 2021 Cheng Zhang, Pan Gao

We propose a modified VAE (variational autoencoder) as a denoiser to remove adversarial perturbations for image classification.

Image Classification

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