Searcharxiv⌕ Search

arXiv subjects

Jing Liu

Publications and source records attributed to Jing Liu.

At least 469 records · Page 26Linked to original sources
arXiv2023

AgileGAN3D: Few-Shot 3D Portrait Stylization by Augmented Transfer Learning

While substantial progresses have been made in automated 2D portrait stylization, admirable 3D portrait stylization from a single user photo remains to be an unresolved challenge. One primary obstacle here is the lack of high quality stylized 3D training data. In this paper, we propose a novel framework \emph{AgileGAN3D} that can produce 3D artistically appealing and personalized portraits with detailed geometry. New stylization can be obtained with just a few (around 20) unpaired 2D exemplars. We achieve this by first leveraging existing 2D stylization capabilities, \emph{style prior creation}, to produce a large amount of augmented 2D style exemplars. These augmented exemplars are generated with accurate camera pose labels, as well as paired real face images, which prove to be critical for the downstream 3D stylization task. Capitalizing on the recent advancement of 3D-aware GAN models, we perform \emph{guided transfer learning} on a pretrained 3D GAN generator to produce multi-view-consistent stylized renderings. In order to achieve 3D GAN inversion that can preserve subject's identity well, we incorporate \emph{multi-view consistency loss} in the training of our encoder. Our pipeline demonstrates strong capability in turning user photos into a diverse range of 3D artistic portraits. Both qualitative results and quantitative evaluations have been conducted to show the superior performance of our method. Code and pretrained models will be released for reproduction purpose.

cs.CV↗
arXiv2023

Sharpness-aware Quantization for Deep Neural Networks

Network quantization is a dominant paradigm of model compression. However, the abrupt changes in quantized weights during training often lead to severe loss fluctuations and result in a sharp loss landscape, making the gradients unstable and thus degrading the performance. Recently, Sharpness-Aware Minimization (SAM) has been proposed to smooth the loss landscape and improve the generalization performance of the models. Nevertheless, directly applying SAM to the quantized models can lead to perturbation mismatch or diminishment issues, resulting in suboptimal performance. In this paper, we propose a novel method, dubbed Sharpness-Aware Quantization (SAQ), to explore the effect of SAM in model compression, particularly quantization for the first time. Specifically, we first provide a unified view of quantization and SAM by treating them as introducing quantization noises and adversarial perturbations to the model weights, respectively. According to whether the noise and perturbation terms depend on each other, SAQ can be formulated into three cases, which are analyzed and compared comprehensively. Furthermore, by introducing an efficient training strategy, SAQ only incurs a little additional training overhead compared with the default optimizer (e.g., SGD or AdamW). Extensive experiments on both convolutional neural networks and Transformers across various datasets (i.e., ImageNet, CIFAR-10/100, Oxford Flowers-102, Oxford-IIIT Pets) show that SAQ improves the generalization performance of the quantized models, yielding the SOTA results in uniform quantization. For example, on ImageNet, SAQ outperforms AdamW by 1.2% on the Top-1 accuracy for 4-bit ViT-B/16. Our 4-bit ResNet-50 surpasses the previous SOTA method by 0.9% on the Top-1 accuracy.

cs.CV↗
arXiv2023

Boosting Verified Training for Robust Image Classifications via Abstraction

This paper proposes a novel, abstraction-based, certified training method for robust image classifiers. Via abstraction, all perturbed images are mapped into intervals before feeding into neural networks for training. By training on intervals, all the perturbed images that are mapped to the same interval are classified as the same label, rendering the variance of training sets to be small and the loss landscape of the models to be smooth. Consequently, our approach significantly improves the robustness of trained models. For the abstraction, our training method also enables a sound and complete black-box verification approach, which is orthogonal and scalable to arbitrary types of neural networks regardless of their sizes and architectures. We evaluate our method on a wide range of benchmarks in different scales. The experimental results show that our method outperforms state of the art by (i) reducing the verified errors of trained models up to 95.64%; (ii) totally achieving up to 602.50x speedup; and (iii) scaling up to larger models with up to 138 million trainable parameters. The demo is available at https://github.com/zhangzhaodi233/ABSCERT.git.

cs.CV↗
arXiv2023

EcoFormer: Energy-Saving Attention with Linear Complexity

Transformer is a transformative framework that models sequential data and has achieved remarkable performance on a wide range of tasks, but with high computational and energy cost. To improve its efficiency, a popular choice is to compress the models via binarization which constrains the floating-point values into binary ones to save resource consumption owing to cheap bitwise operations significantly. However, existing binarization methods only aim at minimizing the information loss for the input distribution statistically, while ignoring the pairwise similarity modeling at the core of the attention. To this end, we propose a new binarization paradigm customized to high-dimensional softmax attention via kernelized hashing, called EcoFormer, to map the original queries and keys into low-dimensional binary codes in Hamming space. The kernelized hash functions are learned to match the ground-truth similarity relations extracted from the attention map in a self-supervised way. Based on the equivalence between the inner product of binary codes and the Hamming distance as well as the associative property of matrix multiplication, we can approximate the attention in linear complexity by expressing it as a dot-product of binary codes. Moreover, the compact binary representations of queries and keys enable us to replace most of the expensive multiply-accumulate operations in attention with simple accumulations to save considerable on-chip energy footprint on edge devices. Extensive experiments on both vision and language tasks show that EcoFormer consistently achieves comparable performance with standard attentions while consuming much fewer resources. For example, based on PVTv2-B0 and ImageNet-1K, Ecoformer achieves a 73% on-chip energy footprint reduction with only a 0.33% performance drop compared to the standard attention. Code is available at https://github.com/ziplab/EcoFormer.

cs.CV↗
arXiv2023

Maximal quantum Fisher information for phase estimation without initial parity

Mach-Zehnder interferometer is a common device in quantum phase estimation and the photon losses in it are an important issue for achieving a high phase accuracy. Here we thoroughly discuss the precision limit of the phase in the Mach-Zehnder interferometer with a coherent state and a superposition of coherent states as input states. By providing a general analytical expression of quantum Fisher information, the phase-matching condition and optimal initial parity are given. Especially, in the photon loss scenario, the sensitivity behaviors are analyzed and specific strategies are provided to restore the phase accuracies for symmetric and asymmetric losses.

quant-ph↗
arXiv2023

MOSO: Decomposing MOtion, Scene and Object for Video Prediction

Motion, scene and object are three primary visual components of a video. In particular, objects represent the foreground, scenes represent the background, and motion traces their dynamics. Based on this insight, we propose a two-stage MOtion, Scene and Object decomposition framework (MOSO) for video prediction, consisting of MOSO-VQVAE and MOSO-Transformer. In the first stage, MOSO-VQVAE decomposes a previous video clip into the motion, scene and object components, and represents them as distinct groups of discrete tokens. Then, in the second stage, MOSO-Transformer predicts the object and scene tokens of the subsequent video clip based on the previous tokens and adds dynamic motion at the token level to the generated object and scene tokens. Our framework can be easily extended to unconditional video generation and video frame interpolation tasks. Experimental results demonstrate that our method achieves new state-of-the-art performance on five challenging benchmarks for video prediction and unconditional video generation: BAIR, RoboNet, KTH, KITTI and UCF101. In addition, MOSO can produce realistic videos by combining objects and scenes from different videos.

cs.CV↗
arXiv2023

SMoA: Sparse Mixture of Adapters to Mitigate Multiple Dataset Biases

Recent studies reveal that various biases exist in different NLP tasks, and over-reliance on biases results in models' poor generalization ability and low adversarial robustness. To mitigate datasets biases, previous works propose lots of debiasing techniques to tackle specific biases, which perform well on respective adversarial sets but fail to mitigate other biases. In this paper, we propose a new debiasing method Sparse Mixture-of-Adapters (SMoA), which can mitigate multiple dataset biases effectively and efficiently. Experiments on Natural Language Inference and Paraphrase Identification tasks demonstrate that SMoA outperforms full-finetuning, adapter tuning baselines, and prior strong debiasing methods. Further analysis indicates the interpretability of SMoA that sub-adapter can capture specific pattern from the training data and specialize to handle specific bias.

cs.CL↗
arXiv2023

Graph-based Knowledge Distillation: A survey and experimental evaluation

Graph, such as citation networks, social networks, and transportation networks, are prevalent in the real world. Graph Neural Networks (GNNs) have gained widespread attention for their robust expressiveness and exceptional performance in various graph applications. However, the efficacy of GNNs is heavily reliant on sufficient data labels and complex network models, with the former obtaining hardly and the latter computing costly. To address the labeled data scarcity and high complexity of GNNs, Knowledge Distillation (KD) has been introduced to enhance existing GNNs. This technique involves transferring the soft-label supervision of the large teacher model to the small student model while maintaining prediction performance. This survey offers a comprehensive overview of Graph-based Knowledge Distillation methods, systematically categorizing and summarizing them while discussing their limitations and future directions. This paper first introduces the background of graph and KD. It then provides a comprehensive summary of three types of Graph-based Knowledge Distillation methods, namely Graph-based Knowledge Distillation for deep neural networks (DKD), Graph-based Knowledge Distillation for GNNs (GKD), and Self-Knowledge Distillation based Graph-based Knowledge Distillation (SKD). Each type is further divided into knowledge distillation methods based on the output layer, middle layer, and constructed graph. Subsequently, various algorithms' ideas are analyzed and compared, concluding with the advantages and disadvantages of each algorithm supported by experimental results. In addition, the applications of graph-based knowledge distillation in CV, NLP, RS, and other fields are listed. Finally, the graph-based knowledge distillation is summarized and prospectively discussed. We have also released related resources at https://github.com/liujing1023/Graph-based-Knowledge-Distillation.

cs.LG↗
arXiv2023

Planning-Assisted Context-Sensitive Autonomous Shepherding of Dispersed Robotic Swarms in Obstacle-Cluttered Environments

Robotic shepherding is a bio-inspired approach to autonomously guiding a swarm of agents towards a desired location. The research area has earned increasing research interest recently due to the efficacy of controlling a large number of agents in a swarm (sheep) using a smaller number of actuators (sheepdogs). However, shepherding a highly dispersed swarm in an obstacle-cluttered environment remains challenging for existing methods. To improve the efficacy of shepherding in complex environments with obstacles and dispersed sheep, this paper proposes a planning-assisted context-sensitive autonomous shepherding framework with collision avoidance abilities. The proposed approach models the swarm shepherding problem as a single Travelling Salesperson Problem (TSP), with two sheepdogs\textquoteright\ modes: no-interaction and interaction. An adaptive switching approach is integrated into the framework to guide real-time path planning for avoiding collisions with static and dynamic obstacles; the latter representing moving sheep swarms. We then propose an overarching hierarchical mission planning system, which is made of three sub-systems: a clustering approach to group and distinguish sheep sub-swarms, an Ant Colony Optimisation algorithm as a TSP solver for determining the optimal herding sequence of the sub-swarms, and an online path planner for calculating optimal paths for both sheepdogs and sheep. The experiments on various environments, both with and without obstacles, objectively demonstrate the effectiveness of the proposed shepherding framework and planning approaches.

cs.RO↗
arXiv2023

Constraints on ultra-slow-roll inflation from the third LIGO-Virgo observing run

The nonattractor evolution in ultra-slow-roll (USR) inflation results in the amplification of superhorizon curvature perturbations and then induces a strong and detectable stochastic gravitational wave background. In this letter, we search for such a stochastic gravitational wave background in data from the third LIGO-Virgo observing run and place constraints on the USR inflationary models. The $e$-folding number of the USR phase are constrained to be $ΔN \lesssim 2.9$ at the 95% confidence level and the power spectrum of curvature perturbations amplified during the USR phase is constrained to be $\log_{10}P_{R\mathrm{p}}<-1.7$ at the scales $2.9\times10^5 ~\mathrm{pc^{-1}} \lesssim k \lesssim 1.7\times10^{11}~\mathrm{pc^{-1}}$. Besides, we forecast the ability of future experiments to constrain USR inflation, and find $P_{R\mathrm{p}}\lesssim 10^{-3.6}$ for LISA and Taiji, $P_{R\mathrm{p}}\lesssim 10^{-3.3}$ for Cosmic Explore and Einstein Telescope, $P_{R\mathrm{p}}\lesssim 10^{-5.5}$ for DECIGO and Big Bang Observer and $P_{R\mathrm{p}}\lesssim 10^{-5.2}$ for Square Kilometre Array.

astro-ph.CO↗
arXiv2023

A novel efficient Multi-view traffic-related object detection framework

With the rapid development of intelligent transportation system applications, a tremendous amount of multi-view video data has emerged to enhance vehicle perception. However, performing video analytics efficiently by exploiting the spatial-temporal redundancy from video data remains challenging. Accordingly, we propose a novel traffic-related framework named CEVAS to achieve efficient object detection using multi-view video data. Briefly, a fine-grained input filtering policy is introduced to produce a reasonable region of interest from the captured images. Also, we design a sharing object manager to manage the information of objects with spatial redundancy and share their results with other vehicles. We further derive a content-aware model selection policy to select detection methods adaptively. Experimental results show that our framework significantly reduces response latency while achieving the same detection accuracy as the state-of-the-art methods.

cs.CV↗
arXiv2023

Characterization Of Inpaint Residuals In Interferometric Measurements of the Epoch Of Reionization

Radio Frequency Interference (RFI) is one of the systematic challenges preventing 21cm interferometric instruments from detecting the Epoch of Reionization. To mitigate the effects of RFI on data analysis pipelines, numerous inpaint techniques have been developed to restore RFI corrupted data. We examine the qualitative and quantitative errors introduced into the visibilities and power spectrum due to inpainting. We perform our analysis on simulated data as well as real data from the Hydrogen Epoch of Reionization Array (HERA) Phase 1 upper limits. We also introduce a convolutional neural network that capable of inpainting RFI corrupted data in interferometric instruments. We train our network on simulated data and show that our network is capable at inpainting real data without requiring to be retrained. We find that techniques that incorporate high wavenumbers in delay space in their modeling are best suited for inpainting over narrowband RFI. We also show that with our fiducial parameters Discrete Prolate Spheroidal Sequences (DPSS) and CLEAN provide the best performance for intermittent ``narrowband'' RFI while Gaussian Progress Regression (GPR) and Least Squares Spectral Analysis (LSSA) provide the best performance for larger RFI gaps. However we caution that these qualitative conclusions are sensitive to the chosen hyperparameters of each inpainting technique. We find these results to be consistent in both simulated and real visibilities. We show that all inpainting techniques reliably reproduce foreground dominated modes in the power spectrum. Since the inpainting techniques should not be capable of reproducing noise realizations, we find that the largest errors occur in the noise dominated delay modes. We show that in the future, as the noise level of the data comes down, CLEAN and DPSS are most capable of reproducing the fine frequency structure in the visibilities of HERA data.

astro-ph.IM↗
arXiv2023

Tag-based annotation creates better avatars

Avatar creation from human images allows users to customize their digital figures in different styles. Existing rendering systems like Bitmoji, MetaHuman, and Google Cartoonset provide expressive rendering systems that serve as excellent design tools for users. However, twenty-plus parameters, some including hundreds of options, must be tuned to achieve ideal results. Thus it is challenging for users to create the perfect avatar. A machine learning model could be trained to predict avatars from images, however the annotators who label pairwise training data have the same difficulty as users, causing high label noise. In addition, each new rendering system or version update requires thousands of new training pairs. In this paper, we propose a Tag-based annotation method for avatar creation. Compared to direct annotation of labels, the proposed method: produces higher annotator agreements, causes machine learning to generates more consistent predictions, and only requires a marginal cost to add new rendering systems.

cs.CV↗
arXiv2023

Tensor networks for unsupervised machine learning

Modeling the joint distribution of high-dimensional data is a central task in unsupervised machine learning. In recent years, many interests have been attracted to developing learning models based on tensor networks, which have the advantages of a principle understanding of the expressive power using entanglement properties, and as a bridge connecting classical computation and quantum computation. Despite the great potential, however, existing tensor network models for unsupervised machine learning only work as a proof of principle, as their performance is much worse than the standard models such as restricted Boltzmann machines and neural networks. In this Letter, we present autoregressive matrix product states (AMPS), a tensor network model combining matrix product states from quantum many-body physics and autoregressive modeling from machine learning. Our model enjoys the exact calculation of normalized probability and unbiased sampling. We demonstrate the performance of our model using two applications, generative modeling on synthetic and real-world data, and reinforcement learning in statistical physics. Using extensive numerical experiments, we show that the proposed model significantly outperforms the existing tensor network models and the restricted Boltzmann machines, and is competitive with state-of-the-art neural network models.

cond-mat.stat-mech↗
arXiv2023

LGN-Net: Local-Global Normality Network for Video Anomaly Detection

Video anomaly detection (VAD) has been intensively studied for years because of its potential applications in intelligent video systems. Existing unsupervised VAD methods tend to learn normality from training sets consisting of only normal videos and regard instances deviating from such normality as anomalies. However, they often consider only local or global normality in the temporal dimension. Some of them focus on learning local spatiotemporal representations from consecutive frames to enhance the representation for normal events. But powerful representation allows these methods to represent some anomalies and causes miss detection. In contrast, the other methods are devoted to memorizing prototypical normal patterns of whole training videos to weaken the generalization for anomalies, which also restricts them from representing diverse normal patterns and causes false alarm. To this end, we propose a two-branch model, Local-Global Normality Network (LGN-Net), to simultaneously learn local and global normality. Specifically, one branch learns the evolution regularities of appearance and motion from consecutive frames as local normality utilizing a spatiotemporal prediction network, while the other branch memorizes prototype features of the whole videos as global normality by a memory module. LGN-Net achieves a balance of representing normal and abnormal instances by fusing local and global normality. In addition, the fused normality enables LGN-Net to generalize to various scenes more than exploiting single normality. Experiments demonstrate the effectiveness and superior performance of our method. The code is available online: https://github.com/Myzhao1999/LGN-Net.

cs.CV↗
arXiv2022

Advantage of quantum coherence in postselected metrology

In conventional measurement, to reach the greatest accuracy of parameter estimation, all samples must be measured since each independent sample contains the same quantum Fisher information. In postselected metrology, postselection can concentrate the quantum Fisher information of the initial samples into a tiny post-selected sub-ensemble. It has been proven that this quantum advantage can not be realized in any classically commuting theory. In this work, we present that the advantage of postselection in weak value amplification (WVA) can not be achieved without quantum coherence. The quantum coherence of the initial system is closely related to the preparation costs and measurement costs in parameter estimation. With the increase of initial quantum coherence, the joint values of preparation costs and measurement costs can be optimized to smaller. Moreover, we derive an analytical tradeoff relation between the preparation, measurement and the quantum coherence. We further experimentally test the tradeoff relation in a linear optical setup. The experimental and theoretical results are in good agreement and show that the quantum coherence plays a key role in bounding the resource costs in the postselected metrology process.

quant-ph↗
arXiv2022

Robust Mean Estimation in High Dimensions: An Outlier Fraction Agnostic and Efficient Algorithm

The problem of robust mean estimation in high dimensions is studied, in which a certain fraction (less than half) of the datapoints can be arbitrarily corrupted. Motivated by compressive sensing, the robust mean estimation problem is formulated as the minimization of the $\ell_0$-`norm' of an \emph{outlier indicator vector}, under a second moment constraint on the datapoints. The $\ell_0$-`norm' is then relaxed to the $\ell_p$-norm ($0<p\leq 1$) in the objective, and it is shown that the global minima for each of these objectives are order-optimal and have optimal breakdown point for the robust mean estimation problem. Furthermore, a computationally tractable iterative $\ell_p$-minimization and hard thresholding algorithm is proposed that outputs an order-optimal robust estimate of the population mean. The proposed algorithm (with breakdown point $\approx 0.3$) does not require prior knowledge of the fraction of outliers, in contrast with most existing algorithms, and for $p=1$ it has near-linear time complexity. Both synthetic and real data experiments demonstrate that the proposed algorithm outperforms state-of-the-art robust mean estimation methods.

stat.AP↗
arXiv2022

Higher-order Knowledge Transfer for Dynamic Community Detection with Great Changes

Network structure evolves with time in the real world, and the discovery of changing communities in dynamic networks is an important research topic that poses challenging tasks. Most existing methods assume that no significant change in the network occurs; namely, the difference between adjacent snapshots is slight. However, great change exists in the real world usually. The great change in the network will result in the community detection algorithms are difficulty obtaining valuable information from the previous snapshot, leading to negative transfer for the next time steps. This paper focuses on dynamic community detection with substantial changes by integrating higher-order knowledge from the previous snapshots to aid the subsequent snapshots. Moreover, to improve search efficiency, a higher-order knowledge transfer strategy is designed to determine first-order and higher-order knowledge by detecting the similarity of the adjacency matrix of snapshots. In this way, our proposal can better keep the advantages of previous community detection results and transfer them to the next task. We conduct the experiments on four real-world networks, including the networks with great or minor changes. Experimental results in the low-similarity datasets demonstrate that higher-order knowledge is more valuable than first-order knowledge when the network changes significantly and keeps the advantage even if handling the high-similarity datasets. Our proposal can also guide other dynamic optimization problems with great changes.

cs.NE↗