arXiv subjects

Pan Gao

Publications and source records attributed to Pan Gao.

66 records · Page 4Linked to original sources

arXiv2022

SSformer: A Lightweight Transformer for Semantic Segmentation

It is well believed that Transformer performs better in semantic segmentation compared to convolutional neural networks. Nevertheless, the original Vision Transformer may lack of inductive biases of local neighborhoods and possess a high time complexity. Recently, Swin Transformer sets a new record in various vision tasks by using hierarchical architecture and shifted windows while being more efficient. However, as Swin Transformer is specifically designed for image classification, it may achieve suboptimal performance on dense prediction-based segmentation task. Further, simply combing Swin Transformer with existing methods would lead to the boost of model size and parameters for the final segmentation model. In this paper, we rethink the Swin Transformer for semantic segmentation, and design a lightweight yet effective transformer model, called SSformer. In this model, considering the inherent hierarchical design of Swin Transformer, we propose a decoder to aggregate information from different layers, thus obtaining both local and global attentions. Experimental results show the proposed SSformer yields comparable mIoU performance with state-of-the-art models, while maintaining a smaller model size and lower compute.

cs.CV↗

arXiv2022

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

Automatic smoky vehicle detection in videos is a superior solution to the traditional expensive remote sensing one with ultraviolet-infrared light devices for environmental protection agencies. However, it is challenging to distinguish vehicle smoke from shadow and wet regions coming from rear vehicle or clutter roads, and could be worse due to limited annotated data. In this paper, we first introduce a real-world large-scale smoky vehicle dataset with 75,000 annotated smoky vehicle images, facilitating the effective training of advanced deep learning models. To enable fair algorithm comparison, we also build a smoky vehicle video dataset including 163 long videos with segment-level annotations. Moreover, we present a new Coarse-to-fine Deep Smoky vehicle detection (CoDeS) framework for efficient smoky vehicle detection. The CoDeS first leverages a light-weight YOLO detector for fast smoke detection with high recall rate, and then applies a smoke-vehicle matching strategy to eliminate non-vehicle smoke, and finally uses a elaborately-designed 3D model to further refine the results in spatial temporal space. Extensive experiments in four metrics demonstrate that our framework is significantly superior to those hand-crafted feature based methods and recent advanced methods. The code and dataset will be released at https://github.com/pengxj/smokyvehicle.

cs.CV↗

arXiv2022

Video Frame Interpolation Based on Deformable Kernel Region

Video frame interpolation task has recently become more and more prevalent in the computer vision field. At present, a number of researches based on deep learning have achieved great success. Most of them are either based on optical flow information, or interpolation kernel, or a combination of these two methods. However, these methods have ignored that there are grid restrictions on the position of kernel region during synthesizing each target pixel. These limitations result in that they cannot well adapt to the irregularity of object shape and uncertainty of motion, which may lead to irrelevant reference pixels used for interpolation. 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. Experiments are conducted on four datasets to demonstrate the superior performance of the proposed model in comparison to the state-of-the-art alternatives.

cs.CV↗

arXiv2022

Dilated convolutional neural network-based deep reference picture generation for video compression

Motion estimation and motion compensation are indispensable parts of inter prediction in video coding. Since the motion vector of objects is mostly in fractional pixel units, original reference pictures may not accurately provide a suitable reference for motion compensation. In this paper, we propose a deep reference picture generator which can create a picture that is more relevant to the current encoding frame, thereby further reducing temporal redundancy and improving video compression efficiency. Inspired by the recent progress of Convolutional Neural Network(CNN), this paper proposes to use a dilated CNN to build the generator. Moreover, we insert the generated deep picture into Versatile Video Coding(VVC) as a reference picture and perform a comprehensive set of experiments to evaluate the effectiveness of our network on the latest VVC Test Model VTM. The experimental results demonstrate that our proposed method achieves on average 9.7% bit saving compared with VVC under low-delay P configuration.

eess.IV↗

arXiv2021

Patch-Based Deep Autoencoder for Point Cloud Geometry Compression

The ever-increasing 3D application makes the point cloud compression unprecedentedly important and needed. In this paper, we propose a patch-based compression process using deep learning, focusing on the lossy point cloud geometry compression. 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. In the decoding process, we finally assemble the decompressed patches into a complete point cloud. In addition, we train our network by a patch-to-patch criterion, i.e., use the local reconstruction loss for optimization, to approximate the global reconstruction optimality. Our method outperforms the state-of-the-art in terms of rate-distortion performance, especially at low bitrates. Moreover, the compression process we proposed can guarantee to generate the same number of points as the input. The network model of this method can be easily applied to other point cloud reconstruction problems, such as upsampling.

cs.CV↗

arXiv2021

Countering Adversarial Examples: Combining Input Transformation and Noisy Training

Recent studies have shown that neural network (NN) based image classifiers are highly vulnerable to adversarial examples, which poses a threat to security-sensitive image recognition task. Prior work has shown that JPEG compression can combat the drop in classification accuracy on adversarial examples to some extent. But, as the compression ratio increases, traditional JPEG compression is insufficient to defend those attacks but can cause an abrupt accuracy decline to the benign images. In this paper, with the aim of fully filtering the adversarial perturbations, we firstly make modifications to traditional JPEG compression algorithm which becomes more favorable for NN. Specifically, based on an analysis of the frequency coefficient, we design a NN-favored quantization table for compression. Considering compression as a data augmentation strategy, we then combine our model-agnostic preprocess with noisy training. We fine-tune the pre-trained model by training with images encoded at different compression levels, thus generating multiple classifiers. Finally, since lower (higher) compression ratio can remove both perturbations and original features slightly (aggressively), we use these trained multiple models for model ensemble. The majority vote of the ensemble of models is adopted as final predictions. Experiments results show our method can improve defense efficiency while maintaining original accuracy.

cs.CV↗

arXiv2021

Optimizing a Polynomial Function on a Quantum Simulator

Gradient descent method, as one of the major methods in numerical optimization, is the key ingredient in many machine learning algorithms. As one of the most fundamental way to solve the optimization problems, it promises the function value to move along the direction of steepest descent. For the vast resource consumption when dealing with high-dimensional problems, a quantum version of this iterative optimization algorithm has been proposed recently[arXiv:1612.01789]. Here, we develop this protocol and implement it on a quantum simulator with limited resource. Moreover, a prototypical experiment was shown with a 4-qubit Nuclear Magnetic Resonance quantum processor, demonstrating a optimization process of polynomial function iteratively. In each iteration, we achieved an average fidelity of 94\% compared with theoretical calculation via full-state tomography. In particular, the iterative point gradually converged to the local minimum. We apply our method to multidimensional scaling problem, further showing the potentially capability to yields an exponentially improvement compared with classical counterparts. With the onrushing tendency of quantum information, our work could provide a subroutine for the application of future practical quantum computers.

quant-ph↗

arXiv2020

Identification of Repurposable Drugs and Adverse Drug Reactions for Various Courses of COVID-19 Based on Single-Cell RNA Sequencing Data

Coronavirus disease 2019 (COVID-19) has impacted almost every part of human life worldwide, posing a massive threat to human health. There is no specific drug for COVID-19, highlighting the urgent need for the development of effective therapeutics. To identify potentially repurposable drugs, we employed a systematic approach to mine candidates from U.S. FDA-approved drugs and preclinical small-molecule compounds by integrating the gene expression perturbation data for chemicals from the Library of Integrated Network-Based Cellular Signatures project with a publicly available single-cell RNA sequencing dataset from mild and severe COVID-19 patients. We identified 281 FDA-approved drugs that have the potential to be effective against SARS-CoV-2 infection, 16 of which are currently undergoing clinical trials to evaluate their efficacy against COVID-19. We experimentally tested the inhibitory effects of tyrphostin-AG-1478 and brefeldin-a on the replication of the single-stranded ribonucleic acid (ssRNA) virus influenza A virus. In conclusion, we have identified a list of repurposable anti-SARS-CoV-2 drugs using a systems biology approach.

q-bio.GN↗

arXiv2020

Quantum Gradient Algorithm for General Polynomials

Gradient-based algorithms, popular strategies to optimization problems, are essential for many modern machine-learning techniques. Theoretically, extreme points of certain cost functions can be found iteratively along the directions of the gradient. The time required to calculating the gradient of $d$-dimensional problems is at a level of $\mathcal{O}(poly(d))$, which could be boosted by quantum techniques, benefiting the high-dimensional data processing, especially the modern machine-learning engineering with the number of optimized parameters being in billions. Here, we propose a quantum gradient algorithm for optimizing general polynomials with the dressed amplitude encoding, aiming at solving fast-convergence polynomials problems within both time and memory consumption in $\mathcal{O}(poly (\log{d}))$. Furthermore, numerical simulations are carried out to inspect the performance of this protocol by considering the noises or perturbations from initialization, operation and truncation. For the potential values in high-dimension optimizations, this quantum gradient algorithm is supposed to facilitate the polynomial-optimizations, being a subroutine for future practical quantum computer.

quant-ph↗

arXiv2018

Optimization of Occlusion-Inducing Depth Pixels in 3-D Video Coding

The optimization of occlusion-inducing depth pixels in depth map coding has received little attention in the literature, since their associated texture pixels are occluded in the synthesized view and their effect on the synthesized view is considered negligible. However, the occlusion-inducing depth pixels still need to consume the bits to be transmitted, and will induce geometry distortion that inherently exists in the synthesized view. In this paper, we propose an efficient depth map coding scheme specifically for the occlusion-inducing depth pixels by using allowable depth distortions. Firstly, we formulate a problem of minimizing the overall geometry distortion in the occlusion subject to the bit rate constraint, for which the depth distortion is properly adjusted within the set of allowable depth distortions that introduce the same disparity error as the initial depth distortion. Then, we propose a dynamic programming solution to find the optimal depth distortion vector for the occlusion. The proposed algorithm can improve the coding efficiency without alteration of the occlusion order. Simulation results confirm the performance improvement compared to other existing algorithms.

cs.MM↗

arXiv2013

Numerical study of magnetic and pairing correlation in bilayer triangular lattice

By using the determinant Quantum Monte Carlo method, the magnetic and pairing correlation of the Na$_{x}$CoO$_{2}\cdot$yH$_{2}$O system are studied within the Hubbard model on a bilayer triangular lattice. The temperature dependence of spin correlation function and pairing susceptibility with several kinds of symmetries at different electron fillings and inter layer coupling terms are investigated. It is found that the system shows an antiferromagnetic correlation around the half filling, and the $fn$-wave pairing correlation dominates over other kinds of pairing symmetry in the low doping region. As the electron filling decreases away from the half filling, both the ferromagnetic correlation and the $f$-wave paring susceptibility are enhanced and tend to dominate. It is also shown that both the magnetic susceptibility and paring susceptibility decrease as the inter layer coupling increases.

cond-mat.str-el↗

arXiv2007

A limited resource model of fault-tolerant capability against cascading failure of complex network

We propose a novel capacity model for complex networks against cascading failure. In this model, vertices with both higher loads and larger degrees should be paid more extra capacities, i.e. the allocation of extra capacity on vertex $i$ will be proportional to $ k_{i}^γ $, where $ k_{i}$ is the degree of vertex $i$ and $γ>0$ is a free parameter. We have applied this model on Barabási-Albert network as well as two real transportation networks, and found that under the same amount of available resource, this model can achieve better network robustness than previous models.

physics.soc-ph↗