arXiv subjects

Haosen Yang

Publications and source records attributed to Haosen Yang.

27 records · Page 2Linked to original sources

arXiv2023

Leveraging Foundation models for Unsupervised Audio-Visual Segmentation

Audio-Visual Segmentation (AVS) aims to precisely outline audible objects in a visual scene at the pixel level. Existing AVS methods require fine-grained annotations of audio-mask pairs in supervised learning fashion. This limits their scalability since it is time consuming and tedious to acquire such cross-modality pixel level labels. To overcome this obstacle, in this work we introduce unsupervised audio-visual segmentation with no need for task-specific data annotations and model training. For tackling this newly proposed problem, we formulate a novel Cross-Modality Semantic Filtering (CMSF) approach to accurately associate the underlying audio-mask pairs by leveraging the off-the-shelf multi-modal foundation models (e.g., detection [1], open-world segmentation [2] and multi-modal alignment [3]). Guiding the proposal generation by either audio or visual cues, we design two training-free variants: AT-GDINO-SAM and OWOD-BIND. Extensive experiments on the AVS-Bench dataset show that our unsupervised approach can perform well in comparison to prior art supervised counterparts across complex scenarios with multiple auditory objects. Particularly, in situations where existing supervised AVS methods struggle with overlapping foreground objects, our models still excel in accurately segmenting overlapped auditory objects. Our code will be publicly released.

cs.CV↗

arXiv2022

Self-supervised Video Representation Learning with Motion-Aware Masked Autoencoders

Masked autoencoders (MAEs) have emerged recently as art self-supervised spatiotemporal representation learners. Inheriting from the image counterparts, however, existing video MAEs still focus largely on static appearance learning whilst are limited in learning dynamic temporal information hence less effective for video downstream tasks. To resolve this drawback, in this work we present a motion-aware variant -- MotionMAE. Apart from learning to reconstruct individual masked patches of video frames, our model is designed to additionally predict the corresponding motion structure information over time. This motion information is available at the temporal difference of nearby frames. As a result, our model can extract effectively both static appearance and dynamic motion spontaneously, leading to superior spatiotemporal representation learning capability. Extensive experiments show that our MotionMAE outperforms significantly both supervised learning baseline and state-of-the-art MAE alternatives, under both domain-specific and domain-generic pretraining-then-finetuning settings. In particular, when using ViT-B as the backbone our MotionMAE surpasses the prior art model by a margin of 1.2% on Something-Something V2 and 3.2% on UCF101 in domain-specific pretraining setting. Encouragingly, it also surpasses the competing MAEs by a large margin of over 3% on the challenging video object segmentation task. The code is available at https://github.com/happy-hsy/MotionMAE.

cs.CV↗

arXiv2022

NSNet: Non-saliency Suppression Sampler for Efficient Video Recognition

It is challenging for artificial intelligence systems to achieve accurate video recognition under the scenario of low computation costs. Adaptive inference based efficient video recognition methods typically preview videos and focus on salient parts to reduce computation costs. Most existing works focus on complex networks learning with video classification based objectives. Taking all frames as positive samples, few of them pay attention to the discrimination between positive samples (salient frames) and negative samples (non-salient frames) in supervisions. To fill this gap, in this paper, we propose a novel Non-saliency Suppression Network (NSNet), which effectively suppresses the responses of non-salient frames. Specifically, on the frame level, effective pseudo labels that can distinguish between salient and non-salient frames are generated to guide the frame saliency learning. On the video level, a temporal attention module is learned under dual video-level supervisions on both the salient and the non-salient representations. Saliency measurements from both two levels are combined for exploitation of multi-granularity complementary information. Extensive experiments conducted on four well-known benchmarks verify our NSNet not only achieves the state-of-the-art accuracy-efficiency trade-off but also present a significantly faster (2.4~4.3x) practical inference speed than state-of-the-art methods. Our project page is at https://lawrencexia2008.github.io/projects/nsnet .

cs.CV↗

arXiv2021

Temporal Action Proposal Generation with Background Constraint

Temporal action proposal generation (TAPG) is a challenging task that aims to locate action instances in untrimmed videos with temporal boundaries. To evaluate the confidence of proposals, the existing works typically predict action score of proposals that are supervised by the temporal Intersection-over-Union (tIoU) between proposal and the ground-truth. In this paper, we innovatively propose a general auxiliary Background Constraint idea to further suppress low-quality proposals, by utilizing the background prediction score to restrict the confidence of proposals. In this way, the Background Constraint concept can be easily plug-and-played into existing TAPG methods (e.g., BMN, GTAD). From this perspective, we propose the Background Constraint Network (BCNet) to further take advantage of the rich information of action and background. Specifically, we introduce an Action-Background Interaction module for reliable confidence evaluation, which models the inconsistency between action and background by attention mechanisms at the frame and clip levels. Extensive experiments are conducted on two popular benchmarks, i.e., ActivityNet-1.3 and THUMOS14. The results demonstrate that our method outperforms state-of-the-art methods. Equipped with the existing action classifier, our method also achieves remarkable performance on the temporal action localization task.

cs.CV↗

arXiv2021

Temporal Action Proposal Generation with Transformers

Transformer networks are effective at modeling long-range contextual information and have recently demonstrated exemplary performance in the natural language processing domain. Conventionally, the temporal action proposal generation (TAPG) task is divided into two main sub-tasks: boundary prediction and proposal confidence prediction, which rely on the frame-level dependencies and proposal-level relationships separately. To capture the dependencies at different levels of granularity, this paper intuitively presents a unified temporal action proposal generation framework with original Transformers, called TAPG Transformer, which consists of a Boundary Transformer and a Proposal Transformer. Specifically, the Boundary Transformer captures long-term temporal dependencies to predict precise boundary information and the Proposal Transformer learns the rich inter-proposal relationships for reliable confidence evaluation. Extensive experiments are conducted on two popular benchmarks: ActivityNet-1.3 and THUMOS14, and the results demonstrate that TAPG Transformer outperforms state-of-the-art methods. Equipped with the existing action classifier, our method achieves remarkable performance on the temporal action localization task. Codes and models will be available.

cs.CV↗

arXiv2020

Improving Power System State Estimation Based on Matrix-Level Cleaning

Power system state estimation is heavily subjected to measurement error, which comes from the noise of measuring instruments, communication noise, and some unclear randomness. Traditional weighted least square (WLS), as the most universal state estimation method, attempts to minimize the residual between measurements and the estimation of measured variables, but it is unable to handle the measurement error. To solve this problem, based on random matrix theory, this paper proposes a data-driven approach to clean measurement error in matrix-level. Our method significantly reduces the negative effect of measurement error, and conducts a two-stage state estimation scheme combined with WLS. In this method, a Hermitian matrix is constructed to establish an invertible relationship between the eigenvalues of measurements and their covariance matrix. Random matrix tools, combined with an optimization scheme, are used to clean measurement error by shrinking the eigenvalues of the covariance matrix. With great robustness and generality, our approach is particularly suitable for large interconnected power grids. Our method has been numerically evaluated using different testing systems, multiple models of measured noise and matrix size ratios.

eess.SP↗

arXiv2020

Unsupervised Feature Learning for Online Voltage Stability Evaluation and Monitoring Based on Variational Autoencoder

With the increase of uncertain elements in power systems and extensive deployment of online monitoring devices, it is necessary to search a more real-time and robust voltage stability assessment method. This study, using PMU monitoring data, explores a novel data-driven approach for long-term voltage stability assessment based on variational autoencoder (VAE). Our method is capable of extracting the most representative features by an unsupervised data mining method in a probabilistic learning way. Different from most of familiar feature extraction methods, it regularizes latent features in an expected stochastic distribution. Furthermore, a statistical indicator by sampling latent features after variance reduction is proposed to assess long-term voltage stability. Our approach is tested in various simulated power systems with different load increment models. Other cases show the accuracy and speed of our approach for estimating voltage collapse point. These testing cases successfully demonstrate the accuracy and effectiveness of our approach.

eess.SP↗

arXiv2020

Early Anomaly Detection and Location in Distribution Network: A Data-Driven Approach

The measurement data collected from the supervisory control and data acquisition (SCADA) system installed in distribution network can reflect the operational state of the network effectively. In this paper, a random matrix theory (RMT) based approach is developed for early anomaly detection and localization by using the data. For every feeder in the distribution network, a corresponding data matrix is formed. Based on the Marchenko-Pastur Law for the empirical spectral analysis of covariance `signal+noise' matrix, the linear eigenvalue statistics are introduced to indicate the anomaly, and the outliers and their corresponding eigenvectors are analyzed for locating the anomaly. As for the low observability feeders in the distribution network, an increasing data dimension algorithm is designed for the formulated low-dimensional matrices being more accurately analyzed. The developed approach can detect and localize the anomaly at an early stage, and it is robust to random disturbance and measurement error. Cases on Matpower simulation data and real SCADA data corroborate the feasibility of the approach.

stat.AP↗

arXiv2019

Spatio-Temporal Correlation Analysis of Online Monitoring Data for Anomaly Detection and Location in Distribution Networks

The online monitoring data in distribution networks contain rich information on the running states of the networks. By leveraging the data, this paper proposes a spatio-temporal correlation analysis approach for anomaly detection and location in distribution networks. First, spatio-temporal matrix for each feeder line in a distribution network is formulated and the spectrum of its covariance matrix is analyzed. The spectrum is complex and exhibits two aspects: 1) bulk, which arises from random noise or fluctuations and 2) spikes, which represents factors caused by anomaly signals or fault disturbances. Then, by connecting the estimation of the number of factors to the limiting empirical spectral density of covariance matrices of residuals, the spatio-temporal parameters are accurately estimated, during which free random variable techniques are used. Based on the estimators, anomaly indicators are designed to detect and locate the anomalies by exploring the variations of spatio-temporal correlations in the data. The proposed approach is sensitive to the anomalies and robust to random fluctuations, which makes it possible for detecting early anomalies and reducing false alarming rate. Case studies on both synthetic data and real-world online monitoring data verify the effectiveness and advantages of the proposed approach.

eess.SP↗