arXiv subjects

Qi Yu

Publications and source records attributed to Qi Yu.

At least 55 records · Page 3Linked to original sources

arXiv2022

Towards Open Set Video Anomaly Detection

Open Set Video Anomaly Detection (OpenVAD) aims to identify abnormal events from video data where both known anomalies and novel ones exist in testing. Unsupervised models learned solely from normal videos are applicable to any testing anomalies but suffer from a high false positive rate. In contrast, weakly supervised methods are effective in detecting known anomalies but could fail in an open world. We develop a novel weakly supervised method for the OpenVAD problem by integrating evidential deep learning (EDL) and normalizing flows (NFs) into a multiple instance learning (MIL) framework. Specifically, we propose to use graph neural networks and triplet loss to learn discriminative features for training the EDL classifier, where the EDL is capable of identifying the unknown anomalies by quantifying the uncertainty. Moreover, we develop an uncertainty-aware selection strategy to obtain clean anomaly instances and a NFs module to generate the pseudo anomalies. Our method is superior to existing approaches by inheriting the advantages of both the unsupervised NFs and the weakly-supervised MIL framework. Experimental results on multiple real-world video datasets show the effectiveness of our method.

cs.CV↗

arXiv2022

Spiking Graph Convolutional Networks

Graph Convolutional Networks (GCNs) achieve an impressive performance due to the remarkable representation ability in learning the graph information. However, GCNs, when implemented on a deep network, require expensive computation power, making them difficult to be deployed on battery-powered devices. In contrast, Spiking Neural Networks (SNNs), which perform a bio-fidelity inference process, offer an energy-efficient neural architecture. In this work, we propose SpikingGCN, an end-to-end framework that aims to integrate the embedding of GCNs with the biofidelity characteristics of SNNs. The original graph data are encoded into spike trains based on the incorporation of graph convolution. We further model biological information processing by utilizing a fully connected layer combined with neuron nodes. In a wide range of scenarios (e.g. citation networks, image graph classification, and recommender systems), our experimental results show that the proposed method could gain competitive performance against state-of-the-art approaches. Furthermore, we show that SpikingGCN on a neuromorphic chip can bring a clear advantage of energy efficiency into graph data analysis, which demonstrates its great potential to construct environment-friendly machine learning models.

cs.LG↗

arXiv2022

Balancing Bias and Variance for Active Weakly Supervised Learning

As a widely used weakly supervised learning scheme, modern multiple instance learning (MIL) models achieve competitive performance at the bag level. However, instance-level prediction, which is essential for many important applications, remains largely unsatisfactory. We propose to conduct novel active deep multiple instance learning that samples a small subset of informative instances for annotation, aiming to significantly boost the instance-level prediction. A variance regularized loss function is designed to properly balance the bias and variance of instance-level predictions, aiming to effectively accommodate the highly imbalanced instance distribution in MIL and other fundamental challenges. Instead of directly minimizing the variance regularized loss that is non-convex, we optimize a distributionally robust bag level likelihood as its convex surrogate. The robust bag likelihood provides a good approximation of the variance based MIL loss with a strong theoretical guarantee. It also automatically balances bias and variance, making it effective to identify the potentially positive instances to support active sampling. The robust bag likelihood can be naturally integrated with a deep architecture to support deep model training using mini-batches of positive-negative bag pairs. Finally, a novel P-F sampling function is developed that combines a probability vector and predicted instance scores, obtained by optimizing the robust bag likelihood. By leveraging the key MIL assumption, the sampling function can explore the most challenging bags and effectively detect their positive instances for annotation, which significantly improves the instance-level prediction. Experiments conducted over multiple real-world datasets clearly demonstrate the state-of-the-art instance-level prediction achieved by the proposed model.

cs.LG↗

arXiv2022

Quantum calculations on a new CCSD(T) machine-learned PES reveal the leaky nature of gas-phase $trans$ and $gauche$ ethanol conformers

Ethanol is a molecule of fundamental interest in combustion, astrochemistry, and condensed phase as a solvent. It is characterized by two methyl rotors and $trans$ ($anti$) and $gauche$ conformers, which are known to be very close in energy. Here we show that based on rigorous quantum calculations of the vibrational zero-point state, using a new ab initio potential energy surface (PES), the ground state resembles the $trans$ conformer but substantial delocalization to the $gauche$ conformer is present. This explains experimental issues about the identification and isolation of the two conformers. This "leak" effect is partially quenched when deuterating the OH group, which further demonstrates the need for a quantum mechanical approach. Diffusion Monte Carlo (DMC) and full-dimensional semiclassical dynamics calculations are employed. The new PES is obtained by means of a $Δ$-Machine learning approach starting from a pre-existing low level (LL) density functional theory (DFT) surface. This surface is brought to the CCSD(T) level of theory using a relatively small number of $ab$ $initio$ CCSD(T) energies. Agreement between the corrected PES and direct $ab$ $initio$ results for standard fidelity tests is excellent. One- and two-dimensional discrete variable representation calculations focusing on the $trans$-$gauche$ torsional motion are also reported, in reasonable agreement with the experiment.

physics.chem-ph↗

arXiv2022

A $Δ$-Machine Learning Approach for Force Fields, Illustrated by a CCSD(T) 4-body Correction to the MB-pol Water Potential

$Δ$-Machine Learning ($Δ$-ML) has been shown to effectively and efficiently bring a low-level ML potential energy surface to CCSD(T) quality. Here we propose extending this approach to general force fields, which implicitly or explicitly contain many-body effects. After describing this general approach, we illustrate it for the MB-pol water potential which contains CCSD(T) 2-body and 3-body interactions but relies on the TTM4-F 4-body and higher body interactions. The 4-body MB-pol (TTM4-F) interaction fails at a very short range and for the water hexamer errors up to 0.84 kcal/mol are seen for some isomers, owing mainly to 4-body errors. We apply $Δ$-ML for the 4-body interaction, using a recent dataset of CCSD(T) 4-body energies that we used to develop a new water potential, q-AQUA. This 4-body correction is shown to improve the accuracy of the MB-pol potential for the relative energies of 8 isomers of the water hexamer as well as the harmonic frequencies. The new potential is robust in the very short range and so should be reliable for simulations at high pressure and/or high temperature.

physics.chem-ph↗

arXiv2022

The MD17 Datasets from the Perspective of Datasets for Gas-Phase "Small" Molecule Potentials

There has been great progress in developing methods for machine-learned potential energy surfaces. There have also been important assessments of these methods by comparing so-called learning curves on datasets of electronic energies and forces, notably the MD17 database. The dataset for each molecule in this database generally consists of tens of thousands of energies and forces obtained from DFT direct dynamics at 500 K. We contrast the datasets from this database for three "small" molecules, ethanol, malonaldehyde, and glycine, with datasets we have generated with specific targets for the PESs in mind: a rigorous calculation of the zero-point energy and wavefunction, the tunneling splitting in malonaldehyde and in the case of glycine a description of all eight low-lying conformers. We found that the MD17 datasets are too limited for these targets. We also examine recent datasets for several PESs that describe small-molecule but complex chemical reactions. Finally, we introduce a new database, "QM-22", which contains datasets of molecules ranging from 4 to 15 atoms that extend to high energies and a large span of configurations.

physics.chem-ph↗

arXiv2022

Multidimensional quantum calculation of the infrared spectra under polaritonic vibrational strong and ultrastrong coupling

Recent experiments and theory demonstrate that the the ground state properties and chemical reactivity of molecules can be modified inside an optical cavity. The vibrational strong or ultrastrong coupling results in the formation of vibrational polaritons which are usually observed through infrared spectra (IR). Here, we provide a theoretical framework to conduct multidimensional quantum simulations of the infrared spectra when the molecule is interacting with cavity modes. Taking single water molecule as an example, combing with accurate potential energy and dipole moment surfaces, our implemented cavity vibrational self-consistent field/virtual state configuration interaction (cVSCF/VCI) is shown to be able to provide quantitative predictions of the IR spectra when the molecule is inside or outside the cavity. The spectral signatures of resonance splittings and blue/red shift of certain bands are found to be highly related with the frequency and polarization direction of the cavity modes. Further analyses of the simulated spectra shows that polaritonic strong vibrational coupling greatly induce the coupling between molecule's vibrational modes, indicating the intramolecular vibrational energy transfer may be significantly accelerated by the cavity.

physics.chem-ph↗

arXiv2022

q-AQUA: a many-body CCSD(T) water potential, including 4-body interactions, demonstrates the quantum nature of water from clusters to the liquid phase

Many model potential energy surfaces (PESs) have been reported for water; however, none are strictly from "first principles". Here we report such a potential, based on a many-body representation at the CCSD(T) level of theory up to the ultimate 4-body interaction. The new PES is benchmarked for the isomers of the water hexamer for dissociation energies, harmonic frequencies, and unrestricted diffusion Monte Carlo (DMC) calculations of the zero-point energies of the Prism, Book, and Cage isomers. Dissociation energies of several isomers of the 20-mer agree well with recent benchmark energies. Exploratory DMC calculations on this cluster verify the robustness of the new PES for quantum simulations. The accuracy and speed of the new PES are demonstrated for standard condensed phase properties, i.e., the radial distribution function and the self-diffusion constant. Quantum effects are shown to be substantial for these observables and also needed to bring theory into an excellent agreement with experiment.

physics.chem-ph↗

arXiv2022

A Dynamic Meta-Learning Model for Time-Sensitive Cold-Start Recommendations

We present a novel dynamic recommendation model that focuses on users who have interactions in the past but turn relatively inactive recently. Making effective recommendations to these time-sensitive cold-start users is critical to maintain the user base of a recommender system. Due to the sparse recent interactions, it is challenging to capture these users' current preferences precisely. Solely relying on their historical interactions may also lead to outdated recommendations misaligned with their recent interests. The proposed model leverages historical and current user-item interactions and dynamically factorizes a user's (latent) preference into time-specific and time-evolving representations that jointly affect user behaviors. These latent factors further interact with an optimized item embedding to achieve accurate and timely recommendations. Experiments over real-world data help demonstrate the effectiveness of the proposed time-sensitive cold-start recommendation model.

cs.IR↗

arXiv2022

Bayesian Nonparametric Submodular Video Partition for Robust Anomaly Detection

Multiple-instance learning (MIL) provides an effective way to tackle the video anomaly detection problem by modeling it as a weakly supervised problem as the labels are usually only available at the video level while missing for frames due to expensive labeling cost. We propose to conduct novel Bayesian non-parametric submodular video partition (BN-SVP) to significantly improve MIL model training that can offer a highly reliable solution for robust anomaly detection in practical settings that include outlier segments or multiple types of abnormal events. BN-SVP essentially performs dynamic non-parametric hierarchical clustering with an enhanced self-transition that groups segments in a video into temporally consistent and semantically coherent hidden states that can be naturally interpreted as scenes. Each segment is assumed to be generated through a non-parametric mixture process that allows variations of segments within the same scenes to accommodate the dynamic and noisy nature of many real-world surveillance videos. The scene and mixture component assignment of BN-SVP also induces a pairwise similarity among segments, resulting in non-parametric construction of a submodular set function. Integrating this function with an MIL loss effectively exposes the model to a diverse set of potentially positive instances to improve its training. A greedy algorithm is developed to optimize the submodular function and support efficient model training. Our theoretical analysis ensures a strong performance guarantee of the proposed algorithm. The effectiveness of the proposed approach is demonstrated over multiple real-world anomaly video datasets with robust detection performance.

cs.CV↗

arXiv2022

Multidimensional Belief Quantification for Label-Efficient Meta-Learning

Optimization-based meta-learning offers a promising direction for few-shot learning that is essential for many real-world computer vision applications. However, learning from few samples introduces uncertainty, and quantifying model confidence for few-shot predictions is essential for many critical domains. Furthermore, few-shot tasks used in meta training are usually sampled randomly from a task distribution for an iterative model update, leading to high labeling costs and computational overhead in meta-training. We propose a novel uncertainty-aware task selection model for label efficient meta-learning. The proposed model formulates a multidimensional belief measure, which can quantify the known uncertainty and lower bound the unknown uncertainty of any given task. Our theoretical result establishes an important relationship between the conflicting belief and the incorrect belief. The theoretical result allows us to estimate the total uncertainty of a task, which provides a principled criterion for task selection. A novel multi-query task formulation is further developed to improve both the computational and labeling efficiency of meta-learning. Experiments conducted over multiple real-world few-shot image classification tasks demonstrate the effectiveness of the proposed model.

cs.CV↗

arXiv2022

OpenTAL: Towards Open Set Temporal Action Localization

Temporal Action Localization (TAL) has experienced remarkable success under the supervised learning paradigm. However, existing TAL methods are rooted in the closed set assumption, which cannot handle the inevitable unknown actions in open-world scenarios. In this paper, we, for the first time, step toward the Open Set TAL (OSTAL) problem and propose a general framework OpenTAL based on Evidential Deep Learning (EDL). Specifically, the OpenTAL consists of uncertainty-aware action classification, actionness prediction, and temporal location regression. With the proposed importance-balanced EDL method, classification uncertainty is learned by collecting categorical evidence majorly from important samples. To distinguish the unknown actions from background video frames, the actionness is learned by the positive-unlabeled learning. The classification uncertainty is further calibrated by leveraging the guidance from the temporal localization quality. The OpenTAL is general to enable existing TAL models for open set scenarios, and experimental results on THUMOS14 and ActivityNet1.3 benchmarks show the effectiveness of our method. The code and pre-trained models are released at https://www.rit.edu/actionlab/opental.

cs.CV↗

arXiv2021

Permutationally invariant polynomial regression for energies and gradients, using reverse differentiation, achieves orders of magnitude speed-up with high precision compared to other machine learning methods

Permutationally invariant polynomial (PIP) regression has been used to obtain machine-learned (ML) potential energy surfaces, including analytical gradients, for many molecules and chemical reactions. Recently, the approach has been extended to moderate size molecules and applied to systems up to 15 atoms. The algorithm, including "purification of the basis", is computationally efficient for energies; however, we found that the recent extension to obtain analytical gradients, despite being a remarkable advance over previous methods, could be further improved. Here we report developments to compact further a purified basis and, more significantly, to use the reverse gradient approach to greatly speed up gradient evaluation. We demonstrate this for our recent 4-body water interaction potential. Comparisons of training and testing precision on the MD17 database of energies and gradients (forces) for ethanol against GP-SOAP, ANI, sGDML, PhysNet, pKREG, KRR, and other methods, which were recently assessed by Dral and co-workers, are given. The PIP fits are as precise as those using these methods, but the PIP computation time for energy and force evaluation is shown to be 10 to 1000 times faster. Finally, a new PIP PES is reported for ethanol based on a more extensive dataset of energies and gradients than in the MD17 database. Diffusion Monte Carlo calculations which fail on MD17-based PESs are successful using the new PES.

physics.chem-ph↗

arXiv2021

Uncertainty-Aware Multiple Instance Learning from Large-Scale Long Time Series Data

We propose a novel framework to classify large-scale time series data with long duration. Long time seriesclassification (L-TSC) is a challenging problem because the dataoften contains a large amount of irrelevant information to theclassification target. The irrelevant period degrades the classifica-tion performance while the relevance is unknown to the system.This paper proposes an uncertainty-aware multiple instancelearning (MIL) framework to identify the most relevant periodautomatically. The predictive uncertainty enables designing anattention mechanism that forces the MIL model to learn from thepossibly discriminant period. Moreover, the predicted uncertaintyyields a principled estimator to identify whether a prediction istrustworthy or not. We further incorporate another modality toaccommodate unreliable predictions by training a separate modelbased on its availability and conduct uncertainty aware fusion toproduce the final prediction. Systematic evaluation is conductedon the Automatic Identification System (AIS) data, which is col-lected to identify and track real-world vessels. Empirical resultsdemonstrate that the proposed method can effectively detect thetypes of vessels based on the trajectory and the uncertainty-awarefusion with other available data modality (Synthetic-ApertureRadar or SAR imagery is used in our experiments) can furtherimprove the detection accuracy.

cs.AI↗

arXiv2021

Deep Reinforced Attention Regression for Partial Sketch Based Image Retrieval

Fine-Grained Sketch-Based Image Retrieval (FG-SBIR) aims at finding a specific image from a large gallery given a query sketch. Despite the widespread applicability of FG-SBIR in many critical domains (e.g., crime activity tracking), existing approaches still suffer from a low accuracy while being sensitive to external noises such as unnecessary strokes in the sketch. The retrieval performance will further deteriorate under a more practical on-the-fly setting, where only a partially complete sketch with only a few (noisy) strokes are available to retrieve corresponding images. We propose a novel framework that leverages a uniquely designed deep reinforcement learning model that performs a dual-level exploration to deal with partial sketch training and attention region selection. By enforcing the model's attention on the important regions of the original sketches, it remains robust to unnecessary stroke noises and improve the retrieval accuracy by a large margin. To sufficiently explore partial sketches and locate the important regions to attend, the model performs bootstrapped policy gradient for global exploration while adjusting a standard deviation term that governs a locator network for local exploration. The training process is guided by a hybrid loss that integrates a reinforcement loss and a supervised loss. A dynamic ranking reward is developed to fit the on-the-fly image retrieval process using partial sketches. The extensive experimentation performed on three public datasets shows that our proposed approach achieves the state-of-the-art performance on partial sketch based image retrieval.

cs.CV↗

arXiv2021

Simultaneous estimation of parameters and the state of an optical parametric oscillator system

In this paper, we consider the filtering problem of an optical parametric oscillator (OPO). The OPO pump power may fluctuate due to environmental disturbances, resulting in uncertainty in the system modeling. Thus, both the state and the unknown parameter may need to be estimated simultaneously. We formulate this problem using a state-space representation of the OPO dynamics. Under the assumption of Gaussianity and proper constraints, the dual Kalman filter method and the joint extended Kalman filter method are employed to simultaneously estimate the system state and the pump power. Numerical examples demonstrate the effectiveness of the proposed algorithms.

eess.SY↗

arXiv2021

DRIVE: Deep Reinforced Accident Anticipation with Visual Explanation

Traffic accident anticipation aims to accurately and promptly predict the occurrence of a future accident from dashcam videos, which is vital for a safety-guaranteed self-driving system. To encourage an early and accurate decision, existing approaches typically focus on capturing the cues of spatial and temporal context before a future accident occurs. However, their decision-making lacks visual explanation and ignores the dynamic interaction with the environment. In this paper, we propose Deep ReInforced accident anticipation with Visual Explanation, named DRIVE. The method simulates both the bottom-up and top-down visual attention mechanism in a dashcam observation environment so that the decision from the proposed stochastic multi-task agent can be visually explained by attentive regions. Moreover, the proposed dense anticipation reward and sparse fixation reward are effective in training the DRIVE model with our improved reinforcement learning algorithm. Experimental results show that the DRIVE model achieves state-of-the-art performance on multiple real-world traffic accident datasets. Code and pre-trained model are available at \url{https://www.rit.edu/actionlab/drive}.

cs.CV↗

arXiv2021

Evidential Deep Learning for Open Set Action Recognition

In a real-world scenario, human actions are typically out of the distribution from training data, which requires a model to both recognize the known actions and reject the unknown. Different from image data, video actions are more challenging to be recognized in an open-set setting due to the uncertain temporal dynamics and static bias of human actions. In this paper, we propose a Deep Evidential Action Recognition (DEAR) method to recognize actions in an open testing set. Specifically, we formulate the action recognition problem from the evidential deep learning (EDL) perspective and propose a novel model calibration method to regularize the EDL training. Besides, to mitigate the static bias of video representation, we propose a plug-and-play module to debias the learned representation through contrastive learning. Experimental results show that our DEAR method achieves consistent performance gain on multiple mainstream action recognition models and benchmarks. Code and pre-trained models are available at {\small{\url{https://www.rit.edu/actionlab/dear}}}.

cs.CV↗