Search Results for author:
Found 443 papers, 174 papers with code
Relative Pose Estimation of Calibrated Cameras with Known SE(3) Invariants
In this paper, we present a complete comprehensive study of the relative pose estimation problem for a calibrated camera constrained by known $\mathrm{SE}(3)$ invariant, which involves 5 minimal problems in total.
Alibaba Speech Translation Systems for IWSLT 2018
This work describes the En→De Alibaba speech translation system developed for the evaluation campaign of the International Workshop on Spoken Language Translation (IWSLT) 2018.
SemanticAdv: Generating Adversarial Examples via Attribute-conditioned Image Editing
Deep neural networks (DNNs) have achieved great successes in various vision applications due to their strong expressive power.
Profanity-Avoiding Training Framework for Seq2seq Models with Certified Robustness
To address this problem, we propose a training framework with certified robustness to eliminate the causes that trigger the generation of profanity.
Invertible Convolution with Symmetric Paddings
We show that symmetrically padded convolution can be analytically inverted via DFT.
Efficient Decision-based Black-box Patch Attacks on Video Recognition
First, STDE introduces target videos as patch textures and only adds patches on keyframes that are adaptively selected by temporal difference.
Graph Transformer GANs for Graph-Constrained House Generation
We present a novel graph Transformer generative adversarial network (GTGAN) to learn effective graph node relations in an end-to-end fashion for the challenging graph-constrained house generation task.
TrojDiff: Trojan Attacks on Diffusion Models with Diverse Targets
To answer these questions, we propose an effective Trojan attack against diffusion models, TrojDiff, which optimizes the Trojan diffusion and generative processes during training.
Google USM: Scaling Automatic Speech Recognition Beyond 100 Languages
We introduce the Universal Speech Model (USM), a single large model that performs automatic speech recognition (ASR) across 100+ languages.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+3
Pose-Controllable 3D Facial Animation Synthesis using Hierarchical Audio-Vertex Attention
In this paper, a novel pose-controllable 3D facial animation synthesis method is proposed by utilizing hierarchical audio-vertex attention.
Decoupling the All-Reduce Primitive for Accelerating Distributed Deep Learning
Communication scheduling has been shown to be effective in accelerating distributed training, which enables all-reduce communications to be overlapped with backpropagation computations.
UML: A Universal Monolingual Output Layer for Multilingual ASR
Consequently, the UML enables to switch in the interpretation of each output node depending on the language of the input speech.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+1
Delving into the Adversarial Robustness of Federated Learning
In this work, we propose a novel algorithm called Decision Boundary based Federated Adversarial Training (DBFAT), which consists of two components (local re-weighting and global regularization) to improve both accuracy and robustness of FL systems.
Massively Multilingual Shallow Fusion with Large Language Models
In this work, we propose to train a single multilingual language model (LM) for shallow fusion in multiple languages.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
JEIT: Joint End-to-End Model and Internal Language Model Training for Speech Recognition
We propose JEIT, a joint end-to-end (E2E) model and internal language model (ILM) training method to inject large-scale unpaired text into ILM during E2E training which improves rare-word speech recognition.
PerAda: Parameter-Efficient and Generalizable Federated Learning Personalization with Guarantees
Personalized Federated Learning (pFL) has emerged as a promising solution to tackle data heterogeneity across clients in FL.
3D Colored Shape Reconstruction from a Single RGB Image through Diffusion
In shape prediction module, the reference RGB image is first encoded into a high-level shape feature and then the shape feature is utilized as a condition to predict the reverse geometric noise in diffusion model.
Re-ViLM: Retrieval-Augmented Visual Language Model for Zero and Few-Shot Image Captioning
Augmenting pretrained language models (LMs) with a vision encoder (e. g., Flamingo) has obtained state-of-the-art results in image-to-text generation.
Interpolation for Robust Learning: Data Augmentation on Geodesics
Our work provides a new perspective of model robustness through the lens of Wasserstein geodesic-based interpolation with a practical off-the-shelf strategy that can be combined with existing robust training methods.
Defensive ML: Defending Architectural Side-channels with Adversarial Obfuscation
To address this problem, this paper explores using Adversarial Machine Learning (AML) methods as a defense at the computer architecture layer to obfuscate side channels.
Efficient Domain Adaptation for Speech Foundation Models
The FM encoder adapter and decoder are then finetuned to the target domain with a small amount of supervised in-domain data.
Automatic Intrinsic Reward Shaping for Exploration in Deep Reinforcement Learning
We present AIRS: Automatic Intrinsic Reward Shaping that intelligently and adaptively provides high-quality intrinsic rewards to enhance exploration in reinforcement learning (RL).
From English to More Languages: Parameter-Efficient Model Reprogramming for Cross-Lingual Speech Recognition
In this work, we propose a new parameter-efficient learning framework based on neural model reprogramming for cross-lingual speech recognition, which can \textbf{re-purpose} well-trained English automatic speech recognition (ASR) models to recognize the other languages.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+1
Proportional Fairness in Obnoxious Facility Location
On the other hand, in the randomized setting, we identify proportionally fair and strategyproof mechanisms that give an expected welfare within a constant factor of the optimal welfare.
A Bertrand duopoly game with differentiated products reconsidered
In this paper, we explore a dynamic Bertrand duopoly game with differentiated products, where firms are boundedly rational and consumers are assumed to possess an underlying CES utility function.
Reviewing Labels: Label Graph Network with Top-k Prediction Set for Relation Extraction
Specifically, for a given sample, we build a label graph to review candidate labels in the Top-k prediction set and learn the connections between them.
Ranked #1 on
Relation Extraction
on TACRED-Revisited
Sequence Generation with Label Augmentation for Relation Extraction
Sequence generation demonstrates promising performance in recent information extraction efforts, by incorporating large-scale pre-trained Seq2Seq models.
Ranked #1 on
Relation Extraction
on sciERC-sent
EDoG: Adversarial Edge Detection For Graph Neural Networks
In this paper, we propose a general adversarial edge detection pipeline EDoG without requiring knowledge of the attack strategies based on graph generation.
Forecasting West Nile Virus with Graph Neural Networks: Harnessing Spatial Dependence in Irregularly Sampled Geospatial Data
Machine learning methods have seen increased application to geospatial environmental problems, such as precipitation nowcasting, haze forecasting, and crop yield prediction.
Are Multimodal Models Robust to Image and Text Perturbations?
Multimodal image-text models have shown remarkable performance in the past few years.
Partial Variance Reduction improves Non-Convex Federated learning on heterogeneous data
In this paper, we first revisit the widely used FedAvg algorithm in a deep neural network to understand how data heterogeneity influences the gradient updates across the neural network layers.
Logic and Commonsense-Guided Temporal Knowledge Graph Completion
To address these challenges, we propose a Logic and Commonsense-Guided Embedding model (LCGE) to jointly learn the time-sensitive representation involving timeliness and causality of events, together with the time-independent representation of events from the perspective of commonsense.
Rethinking Disparity: A Depth Range Free Multi-View Stereo Based on Disparity
Existing learning-based multi-view stereo (MVS) methods rely on the depth range to build the 3D cost volume and may fail when the range is too large or unreliable.
Tackling Visual Control via Multi-View Exploration Maximization
We present MEM: Multi-view Exploration Maximization for tackling complex visual control tasks.
Confounder Balancing for Instrumental Variable Regression with Latent Variable
This paper studies the confounding effects from the unmeasured confounders and the imbalance of observed confounders in IV regression and aims at unbiased causal effect estimation.
AnimeRun: 2D Animation Visual Correspondence from Open Source 3D Movies
Existing correspondence datasets for two-dimensional (2D) cartoon suffer from simple frame composition and monotonic movements, making them insufficient to simulate real animations.
HFedMS: Heterogeneous Federated Learning with Memorable Data Semantics in Industrial Metaverse
Federated Learning (FL), as a rapidly evolving privacy-preserving collaborative machine learning paradigm, is a promising approach to enable edge intelligence in the emerging Industrial Metaverse.
Resource-Efficient Transfer Learning From Speech Foundation Model Using Hierarchical Feature Fusion
Experimental results show that the proposed method can achieve better performance on speech recognition task than existing algorithms with fewer number of trainable parameters, less computational memory cost and faster training speed.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
Fairness in Federated Learning via Core-Stability
Nonetheless, the heterogeneity nature of distributed data makes it challenging to define and ensure fairness among local agents.
A Quantum Kernel Learning Approach to Acoustic Modeling for Spoken Command Recognition
We propose a quantum kernel learning (QKL) framework to address the inherent data sparsity issues often encountered in training large-scare acoustic models in low-resource scenarios.
DensePure: Understanding Diffusion Models towards Adversarial Robustness
By using the highest density point in the conditional distribution as the reversed sample, we identify the robust region of a given instance under the diffusion model's reverse process.
Unified End-to-End Speech Recognition and Endpointing for Fast and Efficient Speech Systems
In this work, we propose a method to jointly train the ASR and EP tasks in a single end-to-end (E2E) multitask model, improving EP quality by optionally leveraging information from the ASR audio encoder.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+1
Shape Matters: Deformable Patch Attack
Though deep neural networks (DNNs) have demonstrated excellent performance in computer vision, they are susceptible and vulnerable to carefully crafted adversarial examples which can mislead DNNs to incorrect outputs.
CU-Net: LiDAR Depth-Only Completion With Coupled U-Net
We find that existing depth-only methods can obtain satisfactory results in the areas where the measurement points are almost accurate and evenly distributed (denoted as normal areas), while the performance is limited in the areas where the foreground and background points are overlapped due to occlusion (denoted as overlap areas) and the areas where there are no measurement points around (denoted as blank areas) since the methods have no reliable input information in these areas.
Group Distributionally Robust Reinforcement Learning with Hierarchical Latent Variables
One key challenge for multi-task Reinforcement learning (RL) in practice is the absence of task indicators.
LOT: Layer-wise Orthogonal Training on Improving $\ell_2$ Certified Robustness
On the other hand, as existing works show that semi-supervised training helps improve empirical robustness, we aim to bridge the gap and prove that semi-supervised learning also improves the certified robustness of Lipschitz-bounded models.
Joint Plasticity Learning for Camera Incremental Person Re-Identification
This is challenging as the new data only have local supervision in new cameras with no access to the old data due to privacy issues, and they may also contain persons seen by previous cameras.
Product Ranking for Revenue Maximization with Multiple Purchases
In this paper, we assume that each consumer can purchase multiple products at will.
OpenOOD: Benchmarking Generalized Out-of-Distribution Detection
Out-of-distribution (OOD) detection is vital to safety-critical machine learning applications and has thus been extensively studied, with a plethora of methods developed in the literature.
JOIST: A Joint Speech and Text Streaming Model For ASR
In addition, we explore JOIST using a streaming E2E model with an order of magnitude more data, which are also novelties compared to previous works.
Feature Reconstruction Attacks and Countermeasures of DNN training in Vertical Federated Learning
To address this problem, we develop a novel feature protection scheme against the reconstruction attack that effectively misleads the search to some pre-specified random values.
Scaling Up Deliberation for Multilingual ASR
In this work, we investigate second-pass deliberation for multilingual speech recognition.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+1
The Equalization Losses: Gradient-Driven Training for Long-tailed Object Recognition
Long-tail distribution is widely spread in real-world applications.
Improving Long-tailed Object Detection with Image-Level Supervision by Multi-Task Collaborative Learning
Specifically, there are an object detection task (consisting of an instance-classification task and a localization task) and an image-classification task in our framework, responsible for utilizing the two types of supervision.
Semantics-Consistent Cross-domain Summarization via Optimal Transport Alignment
Multimedia summarization with multimodal output (MSMO) is a recently explored application in language grounding.
Untargeted Backdoor Watermark: Towards Harmless and Stealthy Dataset Copyright Protection
In this paper, we revisit dataset ownership verification.
Towards Stable Co-saliency Detection and Object Co-segmentation
In this paper, we present a novel model for simultaneous stable co-saliency detection (CoSOD) and object co-segmentation (CoSEG).
Attributed Network Embedding Model for Exposing COVID-19 Spread Trajectory Archetypes
To this end, this study creates a network embedding model capturing cross-county visitation networks, as well as heterogeneous features to uncover clusters of counties in the United States based on their pandemic spread transmission trajectories.
Rewarding Episodic Visitation Discrepancy for Exploration in Reinforcement Learning
Exploration is critical for deep reinforcement learning in complex environments with high-dimensional observations and sparse rewards.
Trustworthy Reinforcement Learning Against Intrinsic Vulnerabilities: Robustness, Safety, and Generalizability
A trustworthy reinforcement learning algorithm should be competent in solving challenging real-world problems, including {robustly} handling uncertainties, satisfying {safety} constraints to avoid catastrophic failures, and {generalizing} to unseen scenarios during deployments.
Graph Contrastive Learning with Personalized Augmentation
Thus, blindly augmenting all graphs without considering their individual characteristics may undermine the performance of GCL arts. To deal with this, we propose the first principled framework, termed as \textit{G}raph contrastive learning with \textit{P}ersonalized \textit{A}ugmentation (GPA), to advance conventional GCL by allowing each graph to choose its own suitable augmentation operations. In essence, GPA infers tailored augmentation strategies for each graph based on its topology and node attributes via a learnable augmentation selector, which is a plug-and-play module and can be effectively trained with downstream GCL models end-to-end.
Streaming End-to-End Multilingual Speech Recognition with Joint Language Identification
Language identification is critical for many downstream tasks in automatic speech recognition (ASR), and is beneficial to integrate into multilingual end-to-end ASR as an additional task.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
CARE: Certifiably Robust Learning with Reasoning via Variational Inference
In particular, we propose a certifiably robust learning with reasoning pipeline (CARE), which consists of a learning component and a reasoning component.
Privacy of Autonomous Vehicles: Risks, Protection Methods, and Future Directions
However, training AVs usually requires a large amount of training data collected from different driving environments (e. g., cities) as well as different types of personal information (e. g., working hours and routes).
Uncovering the Connection Between Differential Privacy and Certified Robustness of Federated Learning against Poisoning Attacks
We then provide two robustness certification criteria: certified prediction and certified attack cost for DPFL on both levels.
Synergistic Redundancy: Towards Verifiable Safety for Autonomous Vehicles
The synergistic safety layer uses only verifiable and logically analyzable software to fulfill its tasks.
Federated Learning with Label Distribution Skew via Logits Calibration
Extensive experiments on federated datasets and real-world datasets demonstrate that FedLC leads to a more accurate global model and much improved performance.
Verifiable Obstacle Detection
Perception of obstacles remains a critical safety concern for autonomous vehicles.
SphereDepth: Panorama Depth Estimation from Spherical Domain
The panorama image can simultaneously demonstrate complete information of the surrounding environment and has many advantages in virtual tourism, games, robotics, etc.
Ranked #17 on
Depth Estimation
on Stanford2D3D Panoramic
Light-YOLOv5: A Lightweight Algorithm for Improved YOLOv5 in Complex Fire Scenarios
Fire-detection technology is of great importance for successful fire-prevention measures.
Streaming Intended Query Detection using E2E Modeling for Continued Conversation
In voice-enabled applications, a predetermined hotword isusually used to activate a device in order to attend to the query. However, speaking queries followed by a hotword each timeintroduces a cognitive burden in continued conversations.
Turn-Taking Prediction for Natural Conversational Speech
This makes doing speech recognition with conversational speech, including one with multiple queries, a challenging task.
A Language Agnostic Multilingual Streaming On-Device ASR System
On-device end-to-end (E2E) models have shown improvements over a conventional model on English Voice Search tasks in both quality and latency.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+1
Learning Instrumental Variable from Data Fusion for Treatment Effect Estimation
The advent of the big data era brought new opportunities and challenges to draw treatment effect in data fusion, that is, a mixed dataset collected from multiple sources (each source with an independent treatment assignment mechanism).
Where is VALDO? VAscular Lesions Detection and segmentatiOn challenge at MICCAI 2021
This challenge aimed to promote the development of methods for automated detection and segmentation of small and sparse imaging markers of cerebral small vessel disease, namely enlarged perivascular spaces (EPVS) (Task 1), cerebral microbleeds (Task 2) and lacunes of presumed vascular origin (Task 3) while leveraging weak and noisy labels.
General Cutting Planes for Bound-Propagation-Based Neural Network Verification
Our generalized bound propagation method, GCP-CROWN, opens up the opportunity to apply general cutting plane methods for neural network verification while benefiting from the efficiency and GPU acceleration of bound propagation methods.
Understanding the stochastic dynamics of sequential decision-making processes: A path-integral analysis of Multi-armed Bandits
In this paper, we employ techniques in statistical physics to analyze the MAB model, which facilitates to characterize the distribution of cumulative regrets at a finite short time, the central quantity of interest in an MAB algorithm, as well as the intricate dynamical behaviours of the model.
An Empirical Exploration of Cross-domain Alignment between Language and Electroencephalogram
In addition, we provide interpretations of the performance improvement by: (1) visualizing the original feature distribution and the transformed feature distribution, showing the effectiveness of the alignment module for discovering and encoding the relationship between EEG and language; (2) visualizing word-level and sentence-level EEG-language alignment weights, showing the influence of different language semantics as well as EEG frequency features; and (3) visualizing brain topographical maps to provide an intuitive demonstration of the connectivity of EEG and language response in the brain regions.
Large vocabulary speech recognition for languages of Africa: multilingual modeling and self-supervised learning
Almost none of the 2, 000+ languages spoken in Africa have widely available automatic speech recognition systems, and the required data is also only available for a few languages.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
GeoECG: Data Augmentation via Wasserstein Geodesic Perturbation for Robust Electrocardiogram Prediction
In this paper, we propose a physiologically-inspired data augmentation method to improve performance and increase the robustness of heart disease detection based on ECG signals.
SecretGen: Privacy Recovery on Pre-Trained Models via Distribution Discrimination
We first explore different statistical information which can discriminate the private training distribution from other distributions.
FOCUS: Fairness via Agent-Awareness for Federated Learning on Heterogeneous Data
However, due to the heterogeneous nature of local data, it is challenging to optimize or even define fairness of the trained global model for the agents.
UniFed: A Benchmark for Federated Learning Frameworks
Federated Learning (FL) has become a practical and popular paradigm in machine learning.
Improving Privacy-Preserving Vertical Federated Learning by Efficient Communication with ADMM
Moreover, we show that a byproduct of our framework is that the weights of learned linear heads reflect the importance of local clients.
Generalizing Goal-Conditioned Reinforcement Learning with Variational Causal Reasoning
As a pivotal component to attaining generalizable solutions in human intelligence, reasoning provides great potential for reinforcement learning (RL) agents' generalization towards varied goals by summarizing part-to-whole arguments and discovering cause-and-effect relations.
Is Vertical Logistic Regression Privacy-Preserving? A Comprehensive Privacy Analysis and Beyond
We provide a comprehensive and rigorous privacy analysis of VLR in a class of open-source Federated Learning frameworks, where the protocols might differ between one another, yet a procedure of obtaining local gradients is implicitly shared.
Game of Trojans: A Submodular Byzantine Approach
The results show that (i) with Submodular Trojan algorithm, the adversary needs to embed a Trojan trigger into a very small fraction of samples to achieve high accuracy on both Trojan and clean samples, and (ii) the MM Trojan algorithm yields a trained Trojan model that evades detection with probability 1.
Scalable K-FAC Training for Deep Neural Networks with Distributed Preconditioning
The second-order optimization methods, notably the D-KFAC (Distributed Kronecker Factored Approximate Curvature) algorithms, have gained traction on accelerating deep neural network (DNN) training on GPU clusters.
How to Steer Your Adversary: Targeted and Efficient Model Stealing Defenses with Gradient Redirection
To meet these challenges, we present a new approach to model stealing defenses called gradient redirection.
Your Autoregressive Generative Model Can be Better If You Treat It as an Energy-Based One
Autoregressive generative models are commonly used, especially for those tasks involving sequential data.
Pisces: Efficient Federated Learning via Guided Asynchronous Training
Current FL systems employ a participant selection strategy to select fast clients with quality data in each iteration.
Double Sampling Randomized Smoothing
To overcome this hurdle, we propose a Double Sampling Randomized Smoothing (DSRS) framework, which exploits the sampled probability from an additional smoothing distribution to tighten the robustness certification of the previous smoothed classifier.
MixGen: A New Multi-Modal Data Augmentation
Data augmentation is a necessity to enhance data efficiency in deep learning.
Can pruning improve certified robustness of neural networks?
Given the fact that neural networks are often over-parameterized, one effective way to reduce such computational overhead is neural network pruning, by removing redundant parameters from trained neural networks.
Sparse Mixture-of-Experts are Domain Generalizable Learners
It is motivated by an empirical finding that transformer-based models trained with empirical risk minimization (ERM) outperform CNN-based models employing state-of-the-art (SOTA) DG algorithms on multiple DG datasets.
Ranked #7 on
Domain Generalization
on DomainNet
(using extra training data)
Distributionally Invariant Learning: Rationalization and Practical Algorithms
We reformulate the invariant learning problem under latent heterogeneity into a relaxed form that pursues the distributional invariance, based on which we propose our novel Distributionally Invariant Learning (DIL) framework as well as two implementations named DIL-MMD and DIL-KL.
Towards Practical Differential Privacy in Data Analysis: Understanding the Effect of Epsilon on Utility in Private ERM
In this paper, we focus our attention on private Empirical Risk Minimization (ERM), which is one of the most commonly used data analysis method.
Certifying Some Distributional Fairness with Subpopulation Decomposition
In this paper, we first formulate the certified fairness of an ML model trained on a given data distribution as an optimization problem based on the model performance loss bound on a fairness constrained distribution, which is within bounded distributional distance with the training distribution.
On the Robustness of Safe Reinforcement Learning under Observational Perturbations
One interesting and counter-intuitive finding is that the maximum reward attack is strong, as it can both induce unsafe behaviors and make the attack stealthy by maintaining the reward.
Efficient Federated Learning with Spike Neural Networks for Traffic Sign Recognition
However, for machine learning-based traffic sign recognition on the Internet of Vehicles (IoV), a large amount of traffic sign data from distributed vehicles is needed to be gathered in a centralized server for model training, which brings serious privacy leakage risk because of traffic sign data containing lots of location privacy information.
VeriFi: Towards Verifiable Federated Unlearning
One desirable property for FL is the implementation of the right to be forgotten (RTBF), i. e., a leaving participant has the right to request to delete its private data from the global model.
BBDM: Image-to-image Translation with Brownian Bridge Diffusion Models
In this paper, a novel image-to-image translation method based on the Brownian Bridge Diffusion Model (BBDM) is proposed, which models image-to-image translation as a stochastic Brownian bridge process, and learns the translation between two domains directly through the bidirectional diffusion process rather than a conditional generation process.
SemAttack: Natural Textual Attacks via Different Semantic Spaces
In particular, SemAttack optimizes the generated perturbations constrained on generic semantic spaces, including typo space, knowledge space (e. g., WordNet), contextualized semantic space (e. g., the embedding space of BERT clusterings), or the combination of these spaces.
Cross Domain Object Detection by Target-Perceived Dual Branch Distillation
It can adaptively enhance source detector to perceive objects in a target image, by leveraging target proposal contexts from iterative cross-attention.
Data Debugging with Shapley Importance over End-to-End Machine Learning Pipelines
We present DataScope (ease. ml/datascope), the first system that efficiently computes Shapley values of training examples over an end-to-end ML pipeline, and illustrate its applications in data debugging for ML training.
Graph neural networks and attention-based CNN-LSTM for protein classification
This paper proposes three models for protein classification.
Understanding Gradual Domain Adaptation: Improved Analysis, Optimal Path and Beyond
Gradual domain adaptation (GDA), on the other hand, assumes a path of $(T-1)$ unlabeled intermediate domains bridging the source and target, and aims to provide better generalization in the target domain by leveraging the intermediate ones.
Target-Relevant Knowledge Preservation for Multi-Source Domain Adaptive Object Detection
Specifically, TRKP adopts the teacher-student framework, where the multi-head teacher network is built to extract knowledge from labeled source domains and guide the student network to learn detectors in unlabeled target domain.
MHMS: Multimodal Hierarchical Multimedia Summarization
Multimedia summarization with multimodal output can play an essential role in real-world applications, i. e., automatically generating cover images and titles for news articles or providing introductions to online videos.
Unsupervised Learning of Accurate Siamese Tracking
As unlimited self-supervision signals can be obtained by tracking a video along a cycle in time, we investigate evolving a Siamese tracker by tracking videos forward-backward.
Test Against High-Dimensional Uncertainties: Accelerated Evaluation of Autonomous Vehicles with Deep Importance Sampling
In this work, we present Deep Importance Sampling (Deep IS) framework that utilizes a deep neural network to obtain an efficient IS that is on par with the state-of-the-art, capable of reducing the required sample size 43 times smaller than the naive sampling method to achieve 10% relative error and while producing an estimate that is much less conservative.
A thermoelectric generation system using waste heat recovery from petrochemical pipeline to power wireless sensor
This work describes a thermoelectric generation system with an optimized heat sink for wireless monitoring sensor power supply at high temperature.
PhysioMTL: Personalizing Physiological Patterns using Optimal Transport Multi-Task Regression
The proposed method learns an individual-specific predictive model from heterogeneous observations, and enables estimation of an optimal transport map that yields a push forward operation onto the demographic features for each task.
Global Convergence of MAML and Theory-Inspired Neural Architecture Search for Few-Shot Learning
We show that the performance of MetaNTK-NAS is comparable or better than the state-of-the-art NAS method designed for few-shot learning while enjoying more than 100x speedup.
COPA: Certifying Robust Policies for Offline Reinforcement Learning against Poisoning Attacks
We leverage COPA to certify three RL environments trained with different algorithms and conclude: (1) The proposed robust aggregation protocols such as temporal aggregation can significantly improve the certifications; (2) Our certification for both per-state action stability and cumulative reward bound are efficient and tight; (3) The certification for different training algorithms and environments are different, implying their intrinsic robustness properties.
Towards Practical Certifiable Patch Defense with Vision Transformer
To move towards a practical certifiable patch defense, we introduce Vision Transformer (ViT) into the framework of Derandomized Smoothing (DS).
The Right to be Forgotten in Federated Learning: An Efficient Realization with Rapid Retraining
Existing machine unlearning techniques focus on centralized training, where access to all holders' training data is a must for the server to conduct the unlearning process.
Backbone is All Your Need: A Simplified Architecture for Visual Object Tracking
Exploiting a general-purpose neural architecture to replace hand-wired designs or inductive biases has recently drawn extensive interest.
Domain Generalization using Pretrained Models without Fine-tuning
Fine-tuning pretrained models is a common practice in domain generalization (DG) tasks.
Ranked #3 on
Domain Generalization
on VLCS
Machine Learning Empowered Intelligent Data Center Networking: A Survey
To support the needs of ever-growing cloud-based services, the number of servers and network devices in data centers is increasing exponentially, which in turn results in high complexities and difficulties in network optimization.
Raman Spectrum Matching with Contrastive Representation Learning
We propose a new machine learning technique for Raman spectrum matching, based on contrastive representation learning, that requires no preprocessing and works with as little as a single reference spectrum from each class.
CAKE: A Scalable Commonsense-Aware Framework For Multi-View Knowledge Graph Completion
The previous knowledge graph embedding (KGE) techniques suffer from invalid negative sampling and the uncertainty of fact-view link prediction, limiting KGC's performance.
Regulatory Instruments for Fair Personalized Pricing
Personalized pricing is a business strategy to charge different prices to individual consumers based on their characteristics and behaviors.
Multi-model Ensemble Analysis with Neural Network Gaussian Processes
Multi-model ensemble analysis integrates information from multiple climate models into a unified projection.
Exploring the Limits of Domain-Adaptive Training for Detoxifying Large-Scale Language Models
In this work, we systematically explore domain-adaptive training to reduce the toxicity of language models.
Certifying Out-of-Domain Generalization for Blackbox Functions
As a result, the wider application of these techniques is currently limited by its scalability and flexibility -- these techniques often do not scale to large-scale datasets with modern deep neural networks or cannot handle loss functions which may be non-smooth such as the 0-1 loss.
Adversarially Robust Models may not Transfer Better: Sufficient Conditions for Domain Transferability from the View of Regularization
We propose a general theoretical framework proving that factors involving the model function class regularization are sufficient conditions for relative domain transferability.
TPC: Transformation-Specific Smoothing for Point Cloud Models
In this paper, we propose a transformation-specific smoothing framework TPC, which provides tight and scalable robustness guarantees for point cloud models against semantic transformation attacks.
Provable Domain Generalization via Invariant-Feature Subspace Recovery
Our first algorithm, ISR-Mean, can identify the subspace spanned by invariant features from the first-order moments of the class-conditional distributions, and achieve provable domain generalization with $d_s+1$ training environments under the data model of Rosenfeld et al. (2021).
Constrained Variational Policy Optimization for Safe Reinforcement Learning
Safe reinforcement learning (RL) aims to learn policies that satisfy certain constraints before deploying them to safety-critical applications.
Improving the fusion of acoustic and text representations in RNN-T
The recurrent neural network transducer (RNN-T) has recently become the mainstream end-to-end approach for streaming automatic speech recognition (ASR).
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+1
Which Style Makes Me Attractive? Interpretable Control Discovery and Counterfactual Explanation on StyleGAN
First, we propose a novel approach to disentangle latent subspace semantics by exploiting existing face analysis models, e. g., face parsers and face landmark detectors.
Dual Perceptual Loss for Single Image Super-Resolution Using ESRGAN
The proposal of perceptual loss solves the problem that per-pixel difference loss function causes the reconstructed image to be overly-smooth, which acquires a significant progress in the field of single image super-resolution reconstruction.
Equalized Focal Loss for Dense Long-Tailed Object Detection
The conventional focal loss balances the training process with the same modulating factor for all categories, thus failing to handle the long-tailed problem.
Towards Efficient Data Free Black-Box Adversarial Attack
The proposed method can efficiently imitate the target model through a small number of queries and achieve high attack success rate.
Efficient Multi-View Stereo by Iterative Dynamic Cost Volume
Specifically, a lightweight 3D CNN is utilized to generate the coarsest initial depth map which is essential to launch the GRU and guarantee a fast convergence.
Detecting Camouflaged Object in Frequency Domain
We first design a novel frequency enhancement module (FEM) to dig clues of camouflaged objects in the frequency domain.
DENSE: Data-Free One-Shot Federated Learning
One-shot Federated Learning (FL) has recently emerged as a promising approach, which allows the central server to learn a model in a single communication round.
Imagine by Reasoning: A Reasoning-Based Implicit Semantic Data Augmentation for Long-Tailed Classification
Since the covariance matrix of each category represents the feature transformation directions, we can sample new directions from similar categories to generate definitely different instances.
Ranked #47 on
Long-tail Learning
on CIFAR-10-LT (ρ=10)
PixMix: Dreamlike Pictures Comprehensively Improve Safety Measures
In real-world applications of machine learning, reliable and safe systems must consider measures of performance beyond standard test set accuracy.
Perform Like an Engine: A Closed-Loop Neural-Symbolic Learning Framework for Knowledge Graph Inference
Knowledge graph (KG) inference aims to address the natural incompleteness of KGs, including rule learning-based and KG embedding (KGE) models.
Integrated Latent Heterogeneity and Invariance Learning in Kernel Space
The ability to generalize under distributional shifts is essential to reliable machine learning, while models optimized with empirical risk minimization usually fail on non-$i. i. d$ testing data.
Fair Scheduling for Time-dependent Resources
We study a fair resource scheduling problem, where a set of interval jobs are to be allocated to heterogeneous machines controlled by intellectual agents. Each job is associated with release time, deadline, and processing time such that it can be processed if its complete processing period is between its release time and deadline.
Towards Efficiently Evaluating the Robustness of Deep Neural Networks in IoT Systems: A GAN-based Method
Through extensive experiments, AI-GAN achieves high attack success rates, outperforming existing methods, and reduces generation time significantly.
Joint Unsupervised and Supervised Training for Multilingual ASR
Our average WER of all languages outperforms average monolingual baseline by 33. 3%, and the state-of-the-art 2-stage XLSR by 32%.
SAFA: Structure Aware Face Animation
On the other hand, some area of the generated image might be occluded in the source image, which makes it difficult for GAN to generate realistic appearance.
Adversarial GLUE: A Multi-Task Benchmark for Robustness Evaluation of Language Models
In this paper, we present Adversarial GLUE (AdvGLUE), a new multi-task benchmark to quantitatively and thoroughly explore and evaluate the vulnerabilities of modern large-scale language models under various types of adversarial attacks.
Ranked #1 on
Adversarial Robustness
on AdvGLUE
CausalAF: Causal Autoregressive Flow for Safety-Critical Driving Scenario Generation
Generating safety-critical scenarios, which are crucial yet difficult to collect, provides an effective way to evaluate the robustness of autonomous driving systems.
What Would Jiminy Cricket Do? Towards Agents That Behave Morally
When making everyday decisions, people are guided by their conscience, an internal sense of right and wrong.
Highly Efficient Natural Image Matting
With a lightweight basic convolution block, we build a two-stages framework: Segmentation Network (SN) is designed to capture sufficient semantics and classify the pixels into unknown, foreground and background regions; Matting Refine Network (MRN) aims at capturing detailed texture information and regressing accurate alpha values.
Kernelized Heterogeneous Risk Minimization
The ability to generalize under distributional shifts is essential to reliable machine learning, while models optimized with empirical risk minimization usually fail on non-$i. i. d$ testing data.
Anti-Backdoor Learning: Training Clean Models on Poisoned Data
From this view, we identify two inherent characteristics of backdoor attacks as their weaknesses: 1) the models learn backdoored data much faster than learning with clean data, and the stronger the attack the faster the model converges on backdoored data; 2) the backdoor task is tied to a specific class (the backdoor target class).
Multi-branch Neural Networks for Video Anomaly Detection in Adverse Lighting and Weather Conditions
Automated anomaly detection in surveillance videos has attracted much interest as it provides a scalable alternative to manual monitoring.
Anomaly Detection In Surveillance Videos
Video Anomaly Detection
Trustworthy AI: From Principles to Practices
In this review, we provide AI practitioners with a comprehensive guide for building trustworthy AI systems.
CARD: Certifiably Robust Machine Learning Pipeline via Domain Knowledge Integration
In particular, we express the domain knowledge as first-order logic rules and embed these logic rules in a probabilistic graphical model.
I-PGD-AT: Efficient Adversarial Training via Imitating Iterative PGD Attack
Finally, to demonstrate the generality of I-PGD-AT, we integrate it into PGD adversarial training and show that it can even further improve the robustness.
Certified Robustness for Free in Differentially Private Federated Learning
Federated learning (FL) provides an efficient training paradigm to jointly train a global model leveraging data from distributed users.
RVFR: Robust Vertical Federated Learning via Feature Subspace Recovery
Vertical Federated Learning (VFL) is a distributed learning paradigm that allows multiple agents to jointly train a global model when each agent holds a different subset of features for the same sample(s).
BigSSL: Exploring the Frontier of Large-Scale Semi-Supervised Learning for Automatic Speech Recognition
We summarize the results of a host of efforts using giant automatic speech recognition (ASR) models pre-trained using large, diverse unlabeled datasets containing approximately a million hours of audio.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+1
DOODLER: Determining Out-Of-Distribution Likelihood from Encoder Reconstructions
Deep Learning models possess two key traits that, in combination, make their use in the real world a risky prospect.
Towards Efficient Synchronous Federated Training: A Survey on System Optimization Strategies
The increasing demand for privacy-preserving collaborative learning has given rise to a new computing paradigm called federated learning (FL), in which clients collaboratively train a machine learning (ML) model without revealing their private training data.
Eliciting Truthful Reports with Partial Signals in Repeated Games
Namely, besides charging the player the reported value, the mechanism charges a penalty proportional to her inconsistent reports.
Spatially and Robustly Hybrid Mixture Regression Model for Inference of Spatial Dependence
Compared with existing spatial regression models, our proposed model assumes the existence a few distinct regression models that are estimated based on observations that exhibit similar response-predictor relationships.
Full-Cycle Energy Consumption Benchmark for Low-Carbon Computer Vision
The energy consumption of deep learning models is increasing at a breathtaking rate, which raises concerns due to potential negative effects on carbon neutrality in the context of global warming and climate change.