Search Results for author:
Found 176 papers, 77 papers with code
Instance-hiding Schemes for Private Distributed Learning
The new ideas in the current paper are: (a) new variants of mixup with negative as well as positive coefficients, and extend the sample-wise mixup to be pixel-wise.
EAGLE: An Efficient Global Attention Lesion Segmentation Model for Hepatic Echinococcosis
Hepatic echinococcosis (HE) is a widespread parasitic disease in underdeveloped pastoral areas with limited medical resources.
Synergizing Reinforcement Learning and Genetic Algorithms for Neural Combinatorial Optimization
Combinatorial optimization problems are notoriously challenging due to their discrete structure and exponentially large solution space.
Segment Concealed Objects with Incomplete Supervision
To mitigate the effect of low-quality segmentation masks, we introduce a series of strategies for pseudo-label generation, storage, and supervision.
DrSR: LLM based Scientific Equation Discovery with Dual Reasoning from Data and Experience
Symbolic regression is a fundamental tool for discovering interpretable mathematical expressions from data, with broad applications across scientific and engineering domains.
Zero-Trust Foundation Models: A New Paradigm for Secure and Collaborative Artificial Intelligence for Internet of Things
This paper focuses on Zero-Trust Foundation Models (ZTFMs), a novel paradigm that embeds zero-trust security principles into the lifecycle of foundation models (FMs) for Internet of Things (IoT) systems.
SoloSpeech: Enhancing Intelligibility and Quality in Target Speech Extraction through a Cascaded Generative Pipeline
On the other hand, generative models for TSE lag in perceptual quality and intelligibility.
AudioTrust: Benchmarking the Multifaceted Trustworthiness of Audio Large Language Models
We introduce AudioTrust-the first multifaceted trustworthiness evaluation framework and benchmark specifically designed for ALLMs.
MMAR: A Challenging Benchmark for Deep Reasoning in Speech, Audio, Music, and Their Mix
Each item in the benchmark demands multi-step deep reasoning beyond surface-level understanding.
Time-Frequency-Based Attention Cache Memory Model for Real-Time Speech Separation
Existing causal speech separation models often underperform compared to non-causal models due to difficulties in retaining historical information.
DIMM: Decoupled Multi-hierarchy Kalman Filter for 3D Object Tracking
First, DIMM extends the model combination solution space of conventional IMM from a hyperplane to a hypercube by designing a 3D-decoupled multi-hierarchy filter bank, which describes the target's motion with various-order linear models.
SepPrune: Structured Pruning for Efficient Deep Speech Separation
Although deep learning has substantially advanced speech separation in recent years, most existing studies continue to prioritize separation quality while overlooking computational efficiency, an essential factor for low-latency speech processing in real-time applications.
Undermining Federated Learning Accuracy in EdgeIoT via Variational Graph Auto-Encoders
EdgeIoT represents an approach that brings together mobile edge computing with Internet of Things (IoT) devices, allowing for data processing close to the data source.
Using machine learning method for variable star classification using the TESS Sectors 1-57 data
The Transiting Exoplanet Survey Satellite (TESS) is a wide-field all-sky survey mission designed to detect Earth-sized exoplanets.
LRSCLIP: A Vision-Language Foundation Model for Aligning Remote Sensing Image with Longer Text
We propose a novel vision-language foundation model, LRSCLIP, and a multimodal dataset, LRS2M.
Repurposing 2D Diffusion Models with Gaussian Atlas for 3D Generation
Recent advances in text-to-image diffusion models have been driven by the increasing availability of paired 2D data.
Automatic Operator-level Parallelism Planning for Distributed Deep Learning -- A Mixed-Integer Programming Approach
We propose a bi-level solution framework balancing optimality with computational efficiency, automatically generating effective distributed plans that capture both the heterogeneous structure of modern neural networks and the underlying hardware constraints.
Dynamic Dictionary Learning for Remote Sensing Image Segmentation
Remote sensing image segmentation faces persistent challenges in distinguishing morphologically similar categories and adapting to diverse scene variations.
Feature-EndoGaussian: Feature Distilled Gaussian Splatting in Surgical Deformable Scene Reconstruction
On the EndoNeRF dataset, FEG achieves superior performance (SSIM of 0. 97, PSNR of 39. 08, and LPIPS of 0. 03) compared to leading methods.
ARS: Automatic Routing Solver with Large Language Models
Real-world Vehicle Routing Problems (VRPs) are characterized by a variety of practical constraints, making manual solver design both knowledge-intensive and time-consuming.
SayAnything: Audio-Driven Lip Synchronization with Conditional Video Diffusion
Recent advances in diffusion models have led to significant progress in audio-driven lip synchronization.
Hybrid Offline-online Scheduling Method for Large Language Model Inference Optimization
A 100-cases study shows that our method consistently outperforms the baseline method and improves the utilization rate by 8. 0% on average.
RUN: Reversible Unfolding Network for Concealed Object Segmentation
To address this, we propose the Reversible Unfolding Network (RUN), which applies reversible strategies across both mask and RGB domains through a theoretically grounded framework, enabling accurate segmentation.
Complementary Subspace Low-Rank Adaptation of Vision-Language Models for Few-Shot Classification
We conduct comparison experiments of the proposed Comp-LoRA method and other PEFT methods on fine-tuning VLM for few shot classification.
Diffusion Models for Smarter UAVs: Decision-Making and Modeling
By combining the data generation capabilities of DMs with the decision-making framework of RL and the modeling accuracy of DT, the integration improves the adaptability and real-time performance of UAV communication.
Facial Attractiveness Prediction in Live Streaming: A New Benchmark and Multi-modal Method
Furthermore, a multi-modal FAP method is proposed to measure the facial attractiveness in live streaming.
GDSR: Global-Detail Integration through Dual-Branch Network with Wavelet Losses for Remote Sensing Image Super-Resolution
In addition, we propose Wavelet Loss, a loss function that effectively captures high-frequency detail information in images, thereby enhancing the visual quality of SR, particularly in terms of detail reconstruction.
LLM4AD: A Platform for Algorithm Design with Large Language Model
We introduce LLM4AD, a unified Python platform for algorithm design (AD) with large language models (LLMs).
Knowledge Transfer and Domain Adaptation for Fine-Grained Remote Sensing Image Segmentation
FMM further adapts the knowledge to the specific domain to address domain shift.
HES-UNet: A U-Net for Hepatic Echinococcosis Lesion Segmentation
Due to the distinct regional characteristics of HE, there is currently no publicly available high-quality dataset for training our model.
InstantSwap: Fast Customized Concept Swapping across Sharp Shape Differences
They struggle to maintain consistency in both the foreground and background during concept swapping, especially when the shape difference is large between objects.
Adapting Vision Foundation Models for Robust Cloud Segmentation in Remote Sensing Images
Cloud segmentation is a critical challenge in remote sensing image interpretation, as its accuracy directly impacts the effectiveness of subsequent data processing and analysis.
Exploiting VLM Localizability and Semantics for Open Vocabulary Action Detection
Existing approaches focus on the closed-set setting where an action detector is trained and tested on videos from a fixed set of action categories.
Diverse Policies Recovering via Pointwise Mutual Information Weighted Imitation Learning
Recovering a spectrum of diverse policies from a set of expert trajectories is an important research topic in imitation learning.
Adapter-dependent Adapter Methylation Assay
Sensitive and reliable methylation assay is important for oncogentic studies and clinical applications.
SonicSim: A customizable simulation platform for speech processing in moving sound source scenarios
Additionally, to investigate the differences between synthetic and real-world data, we selected 5 hours of raw, non-reverberant data from the SonicSet validation set and recorded a real-world speech separation dataset, providing a reference for comparing SonicSet with other synthetic datasets.
TIGER: Time-frequency Interleaved Gain Extraction and Reconstruction for Efficient Speech Separation
On EchoSet and real-world data, TIGER significantly reduces the number of parameters by 94. 3% and the MACs by 95. 3% while achieving performance surpassing the state-of-the-art (SOTA) model TF-GridNet.
A Novel Framework of Horizontal-Vertical Hybrid Federated Learning for EdgeIoT
This letter puts forth a new hybrid horizontal-vertical federated learning (HoVeFL) for mobile edge computing-enabled Internet of Things (EdgeIoT).
Subjective and Objective Quality-of-Experience Evaluation Study for Live Video Streaming
For the subjective QoE study, we introduce the first live video streaming QoE dataset, TaoLive QoE, which consists of $42$ source videos collected from real live broadcasts and $1, 155$ corresponding distorted ones degraded due to a variety of streaming distortions, including conventional streaming distortions such as compression, stalling, as well as live streaming-specific distortions like frame skipping, variable frame rate, etc.
Learning to Localize Actions in Instructional Videos with LLM-Based Multi-Pathway Text-Video Alignment
Learning to localize temporal boundaries of procedure steps in instructional videos is challenging due to the limited availability of annotated large-scale training videos.
SafeEar: Content Privacy-Preserving Audio Deepfake Detection
To overcome the challenge of identifying diverse deepfake audio without semantic clues, we enhance our deepfake detector with real-world codec augmentation.
Apollo: Band-sequence Modeling for High-Quality Audio Restoration
Audio restoration has become increasingly significant in modern society, not only due to the demand for high-quality auditory experiences enabled by advanced playback devices, but also because the growing capabilities of generative audio models necessitate high-fidelity audio.
Machine Anomalous Sound Detection Using Spectral-temporal Modulation Representations Derived from Machine-specific Filterbanks
The quantification results from the training set of the Malfunctioning Industrial Machine Investigation and Inspection dataset with a signal-to-noise (SNR) of 6 dB reveal that the distinguishing information between normal and anomalous sounds of different machines is encoded non-uniformly in the frequency domain.
Enhancing Multi-Stream Beamforming Through CQIs For 5G NR FDD Massive MIMO Communications: A Tuning-Free Scheme
In such schemes, the performance of downlink beamforming is determined by the codebook design and the codebook indicator feedback.
Superimposed Hi-C: A Solution Proposed for Identifying Single Cell's Chromosomal Interactions
Hi-C sequencing is widely used for analyzing chromosomal interactions.
Human-In-The-Loop Machine Learning for Safe and Ethical Autonomous Vehicles: Principles, Challenges, and Opportunities
Ethical principles must be embedded in AVs to align their behavior with societal values and norms.
Extracting polygonal footprints in off-nadir images with Segment Anything Model
Building Footprint Extraction (BFE) from off-nadir aerial images often involves roof segmentation and offset prediction to adjust roof boundaries to the building footprint.
A Course Shared Task on Evaluating LLM Output for Clinical Questions
This paper presents a shared task that we organized at the Foundations of Language Technology (FoLT) course in 2023/2024 at the Technical University of Darmstadt, which focuses on evaluating the output of Large Language Models (LLMs) in generating harmful answers to health-related clinical questions.
Rethinking Video-Text Understanding: Retrieval from Counterfactually Augmented Data
In order to narrow the gap between video-text models and human performance on RCAD, we identify a key limitation of current contrastive approaches on video-text data and introduce LLM-teacher, a more effective approach to learn action semantics by leveraging knowledge obtained from a pretrained large language model.
Fusion Flow-enhanced Graph Pooling Residual Networks for Unmanned Aerial Vehicles Surveillance in Day and Night Dual Visions
Recognizing unauthorized Unmanned Aerial Vehicles (UAVs) within designated no-fly zones throughout the day and night is of paramount importance, where the unauthorized UAVs pose a substantial threat to both civil and military aviation safety.
Mind the Interference: Retaining Pre-trained Knowledge in Parameter Efficient Continual Learning of Vision-Language Models
To address this problem efficiently, we propose the Distribution-aware Interference-free Knowledge Integration (DIKI) framework, retaining pre-trained knowledge of VLMs from a perspective of avoiding information interference.
Timely Requesting for Time-Critical Content Users in Decentralized F-RANs
We study two general classes of policies: (i) oblivious policies, where decision-making is independent of historical information, and (ii) non-oblivious policies, where decisions are influenced by historical information.
Deep Reinforcement Learning for Adverse Garage Scenario Generation
Autonomous vehicles need to travel over 11 billion miles to ensure their safety.
Evaluating Copyright Takedown Methods for Language Models
Language models (LMs) derive their capabilities from extensive training on diverse data, including potentially copyrighted material.
SORRY-Bench: Systematically Evaluating Large Language Model Safety Refusal Behaviors
First, existing methods often use coarse-grained taxonomies of unsafe topics, and are over-representing some fine-grained topics.
Real-world Image Dehazing with Coherence-based Pseudo Labeling and Cooperative Unfolding Network
Real-world Image Dehazing (RID) aims to alleviate haze-induced degradation in real-world settings.
A Novel Defense Against Poisoning Attacks on Federated Learning: LayerCAM Augmented with Autoencoder
The autoencoder is designed to process the LayerCAM heat maps from the local model updates, improving their distinctiveness and thereby increasing the accuracy in spotting anomalous maps and malicious local models.
BERP: A Blind Estimator of Room Parameters for Single-Channel Noisy Speech Signals
In this paper, we propose a new universal blind estimation framework called the blind estimator of room parameters (BERP) to estimate RAPs, RGPs and occupancy level via a unified methodology.
Age of Information Minimization using Multi-agent UAVs based on AI-Enhanced Mean Field Resource Allocation
Unmanned Aerial Vehicle (UAV) swarms play an effective role in timely data collection from ground sensors in remote and hostile areas.
Leverage Variational Graph Representation For Model Poisoning on Federated Learning
This paper puts forth a new training data-untethered model poisoning (MP) attack on federated learning (FL).
Minimizing Weighted Counterfactual Regret with Optimistic Online Mirror Descent
Counterfactual regret minimization (CFR) is a family of algorithms for effectively solving imperfect-information games.
MultiBooth: Towards Generating All Your Concepts in an Image from Text
MultiBooth addresses these issues by dividing the multi-concept generation process into two phases: a single-concept learning phase and a multi-concept integration phase.
DistriFusion: Distributed Parallel Inference for High-Resolution Diffusion Models
To overcome this dilemma, we observe the high similarity between the input from adjacent diffusion steps and propose displaced patch parallelism, which takes advantage of the sequential nature of the diffusion process by reusing the pre-computed feature maps from the previous timestep to provide context for the current step.
BitDelta: Your Fine-Tune May Only Be Worth One Bit
Large Language Models (LLMs) are typically trained in two phases: pre-training on large internet-scale datasets, and fine-tuning for downstream tasks.
Failure Analysis in Next-Generation Critical Cellular Communication Infrastructures
The advent of communication technologies marks a transformative phase in critical infrastructure construction, where the meticulous analysis of failures becomes paramount in achieving the fundamental objectives of continuity, security, and availability.
TDFNet: An Efficient Audio-Visual Speech Separation Model with Top-down Fusion
TDANet serves as the architectural foundation for the auditory and visual networks within TDFNet, offering an efficient model with fewer parameters.
Ranked #2 on
Speech Separation
on LRS2
Not All Tasks Are Equally Difficult: Multi-Task Deep Reinforcement Learning with Dynamic Depth Routing
Multi-task reinforcement learning endeavors to accomplish a set of different tasks with a single policy.
Apparate: Rethinking Early Exits to Tame Latency-Throughput Tensions in ML Serving
Machine learning (ML) inference platforms are tasked with balancing two competing goals: ensuring high throughput given many requests, and delivering low-latency responses to support interactive applications.
Subnetwork-to-go: Elastic Neural Network with Dynamic Training and Customizable Inference
Deploying neural networks to different devices or platforms is in general challenging, especially when the model size is large or model complexity is high.
Detection and Mitigation of Position Spoofing Attacks on Cooperative UAV Swarm Formations
Detecting spoofing attacks on the positions of unmanned aerial vehicles (UAVs) within a swarm is challenging.
Interpretable Subgraph Feature Extraction for Hyperlink Prediction
In this study, we present SSF, an innovative hyperlink prediction methodology based on Subgraph Structural Features.
Data-Agnostic Model Poisoning against Federated Learning: A Graph Autoencoder Approach
The attacker then adversarially regenerates the graph structural correlations while maximizing the FL training loss, and subsequently generates malicious local models using the adversarial graph structure and the training data features of the benign ones.
PanBench: Towards High-Resolution and High-Performance Pansharpening
Pansharpening, a pivotal task in remote sensing, involves integrating low-resolution multispectral images with high-resolution panchromatic images to synthesize an image that is both high-resolution and retains multispectral information.
Reti-Diff: Illumination Degradation Image Restoration with Retinex-based Latent Diffusion Model
These priors are subsequently utilized by RGformer to guide the decomposition of image features into their respective reflectance and illumination components.
Prompt-Driven Building Footprint Extraction in Aerial Images with Offset-Building Model
More accurate extraction of invisible building footprints from very-high-resolution (VHR) aerial images relies on roof segmentation and roof-to-footprint offset extraction.
Catastrophic Jailbreak of Open-source LLMs via Exploiting Generation
Finally, we propose an effective alignment method that explores diverse generation strategies, which can reasonably reduce the misalignment rate under our attack.
RTFS-Net: Recurrent Time-Frequency Modelling for Efficient Audio-Visual Speech Separation
This is the first time-frequency domain audio-visual speech separation method to outperform all contemporary time-domain counterparts.
Ranked #2 on
Speech Separation
on VoxCeleb2
Gastro-Intestinal Tract Segmentation Using an Explainable 3D Unet
This paper proposes a deep learning pipeline that incorporates XAI to address the challenges of organ segmentation.
IIANet: An Intra- and Inter-Modality Attention Network for Audio-Visual Speech Separation
Recent research has made significant progress in designing fusion modules for audio-visual speech separation.
Ranked #1 on
Speech Separation
on LRS3
High-Fidelity Lake Extraction via Two-Stage Prompt Enhancement: Establishing a Novel Baseline and Benchmark
Lake extraction from remote sensing imagery is a complex challenge due to the varied lake shapes and data noise.
The Sound Demixing Challenge 2023 $\unicode{x2013}$ Cinematic Demixing Track
A significant source of this improvement was making the simulated data better match real cinematic audio, which we further investigate in detail.
DiffCR: A Fast Conditional Diffusion Framework for Cloud Removal from Optical Satellite Images
Optical satellite images are a critical data source; however, cloud cover often compromises their quality, hindering image applications and analysis.
Ranked #2 on
Cloud Removal
on SEN12MS-CR
LEFormer: A Hybrid CNN-Transformer Architecture for Accurate Lake Extraction from Remote Sensing Imagery
LEFormer contains three main modules: CNN encoder, Transformer encoder, and cross-encoder fusion.
Strategic Preys Make Acute Predators: Enhancing Camouflaged Object Detectors by Generating Camouflaged Objects
On the prey side, we propose an adversarial training framework, Camouflageator, which introduces an auxiliary generator to generate more camouflaged objects that are harder for a COD method to detect.
Consistency Regularization for Generalizable Source-free Domain Adaptation
In this paper, we propose a consistency regularization framework to develop a more generalizable SFDA method, which simultaneously boosts model performance on both target training and testing datasets.
NTIRE 2023 Quality Assessment of Video Enhancement Challenge
61 participating teams submitted their prediction results during the development phase, with a total of 3168 submissions.
How do software citation formats evolve over time? A longitudinal analysis of R programming language packages
However, software is hardly consistently cited: one software entity can be cited as different objects, and the citations can change over time.
HQG-Net: Unpaired Medical Image Enhancement with High-Quality Guidance
Specifically, we extract features from an HQ image and explicitly insert the features, which are expected to encode HQ cues, into the enhancement network to guide the LQ enhancement with the variational normalization module.
Source-Free Domain Adaptive Fundus Image Segmentation with Class-Balanced Mean Teacher
This paper aims to address these two issues by proposing the Class-Balanced Mean Teacher (CBMT) model.
Towards Ubiquitous Semantic Metaverse: Challenges, Approaches, and Opportunities
In recent years, ubiquitous semantic Metaverse has been studied to revolutionize immersive cyber-virtual experiences for augmented reality (AR) and virtual reality (VR) users, which leverages advanced semantic understanding and representation to enable seamless, context-aware interactions within mixed-reality environments.
PCG-based Static Underground Garage Scenario Generation
The key to crossing these levels lies in training the autonomous driving model.
Audio-Visual Speech Separation in Noisy Environments with a Lightweight Iterative Model
We propose Audio-Visual Lightweight ITerative model (AVLIT), an effective and lightweight neural network that uses Progressive Learning (PL) to perform audio-visual speech separation in noisy environments.
A Neural State-Space Model Approach to Efficient Speech Separation
In this work, we introduce S4M, a new efficient speech separation framework based on neural state-space models (SSM).
Privacy Implications of Retrieval-Based Language Models
Crucially, we find that $k$NN-LMs are more susceptible to leaking private information from their private datastore than parametric models.
PruMUX: Augmenting Data Multiplexing with Model Compression
As language models increase in size by the day, methods for efficient inference are critical to leveraging their capabilities for various applications.
Weakly-Supervised Concealed Object Segmentation with SAM-based Pseudo Labeling and Multi-scale Feature Grouping
It remains a challenging task since (1) it is hard to distinguish concealed objects from the background due to the intrinsic similarity and (2) the sparsely-annotated training data only provide weak supervision for model learning.
Exploring Compositional Visual Generation with Latent Classifier Guidance
We show that this paradigm based on latent classifier guidance is agnostic to pre-trained generative models, and present competitive results for both image generation and sequential manipulation of real and synthetic images.
Towards Realizing the Value of Labeled Target Samples: a Two-Stage Approach for Semi-Supervised Domain Adaptation
We further propose a consistency learning based mean teacher model to effectively adapt the learned UDA model using labeled and unlabeled target samples.
Semi-supervised Domain Adaptation
Unsupervised Domain Adaptation
PMAA: A Progressive Multi-scale Attention Autoencoder Model for High-performance Cloud Removal from Multi-temporal Satellite Imagery
Satellite imagery analysis plays a pivotal role in remote sensing; however, information loss due to cloud cover significantly impedes its application.
Conditional Image-to-Video Generation with Latent Flow Diffusion Models
In this paper, we propose an approach for cI2V using novel latent flow diffusion models (LFDM) that synthesize an optical flow sequence in the latent space based on the given condition to warp the given image.
Learning Trustworthy Model from Noisy Labels based on Rough Set for Surface Defect Detection
In the surface defect detection, there are some suspicious regions that cannot be uniquely classified as abnormal or normal.
Adversarial Alignment for Source Free Object Detection
Source-free object detection (SFOD) aims to transfer a detector pre-trained on a label-rich source domain to an unlabeled target domain without seeing source data.
Degradation-Resistant Unfolding Network for Heterogeneous Image Fusion
Heterogeneous image fusion (HIF) techniques aim to enhance image quality by merging complementary information from images captured by different sensors.
Few-Shot Video Classification via Representation Fusion and Promotion Learning
This operation maximizes the contribution of discriminative frames to further capture the similarity of support and query samples from the same category.
Personalized Semantics Excitation for Federated Image Classification
Federated learning casts a light on the collaboration of distributed local clients with privacy protected to attain a more generic global model.
Camouflaged Object Detection With Feature Decomposition and Edge Reconstruction
COD is a challenging task due to the intrinsic similarity of camouflaged objects with the background, as well as their ambiguous boundaries.
Source-Free Video Domain Adaptation With Spatial-Temporal-Historical Consistency Learning
Source-free domain adaptation (SFDA) is an emerging research topic that studies how to adapt a pretrained source model using unlabeled target data.
Source-Free Domain Adaptation
Unsupervised Domain Adaptation
An Audio-Visual Speech Separation Model Inspired by Cortico-Thalamo-Cortical Circuits
Then, inspired by the large number of connections between cortical regions and the thalamus, the model fuses the auditory and visual information in a thalamic subnetwork through top-down connections.
Ranked #3 on
Speech Separation
on VoxCeleb2
SSDNeRF: Semantic Soft Decomposition of Neural Radiance Fields
Neural Radiance Fields (NeRFs) encode the radiance in a scene parameterized by the scene's plenoptic function.
Machine Learning-Aided Operations and Communications of Unmanned Aerial Vehicles: A Contemporary Survey
It is also unveiled that the reliability and trust of ML in UAV operations and applications require significant attention before full automation of UAVs and potential cooperation between UAVs and humans come to fruition.
Deep Spectro-temporal Artifacts for Detecting Synthesized Speech
The Audio Deep Synthesis Detection (ADD) Challenge has been held to detect generated human-like speech.
An efficient encoder-decoder architecture with top-down attention for speech separation
In addition, a large-size version of TDANet obtained SOTA results on three datasets, with MACs still only 10\% of Sepformer and the CPU inference time only 24\% of Sepformer.
Ranked #4 on
Speech Separation
on WHAM!
A Review on Method Entities in the Academic Literature: Extraction, Evaluation, and Application
With the advancement of sciences, many scientific methods are being proposed, modified, and used in academic literature.
A Multi-scale Video Denoising Algorithm for Raw Image
Video denoising for raw image has always been the difficulty of camera image processing.
Designs, Motion Mechanism, Motion Coordination, and Communication of Bionic Robot Fishes: A Survey
Various methods are needed to narrow the gap in swimming performance between robot fishes and fish.
Multi-Agent Feedback Enabled Neural Networks for Intelligent Communications
The design of MAFENN framework and algorithm are dedicated to enhance the learning capability of the feedfoward DL networks or their variations with the simple data feedback.
Recovering Private Text in Federated Learning of Language Models
For the first time, we show the feasibility of recovering text from large batch sizes of up to 128 sentences.
Fast Few-shot Debugging for NLU Test Suites
We study few-shot debugging of transformer based natural language understanding models, using recently popularized test suites to not just diagnose but correct a problem.
Downlink Channel Covariance Matrix Reconstruction for FDD Massive MIMO Systems with Limited Feedback
The downlink channel covariance matrix (CCM) acquisition is the key step for the practical performance of massive multiple-input and multiple-output (MIMO) systems, including beamforming, channel tracking, and user scheduling.
Exploring Deep Reinforcement Learning-Assisted Federated Learning for Online Resource Allocation in Privacy-Persevering EdgeIoT
Federated learning (FL) has been increasingly considered to preserve data training privacy from eavesdropping attacks in mobile edge computing-based Internet of Thing (EdgeIoT).
Evaluating Gradient Inversion Attacks and Defenses in Federated Learning
Gradient inversion attack (or input recovery from gradient) is an emerging threat to the security and privacy preservation of Federated learning, whereby malicious eavesdroppers or participants in the protocol can recover (partially) the clients' private data.
DRL-Clusters: Buffer Management with Clustering based Deep Reinforcement Learning
Buffer cache has been widely implemented in database systems to reduce disk I/Os.
Actor-Critic Policy Optimization in a Large-Scale Imperfect-Information Game
The deep policy gradient method has demonstrated promising results in many large-scale games, where the agent learns purely from its own experience.
Rethinking Lightweight Convolutional Neural Networks for Efficient and High-quality Pavement Crack Detection
For the second issue, we reconsider how to improve detection efficiency with excellent performance, and then propose our lightweight encoder-decoder architecture termed CarNet.
EMA: Auditing Data Removal from Trained Models
In this paper, we propose a new method called Ensembled Membership Auditing (EMA) for auditing data removal to overcome these limitations.
Plot2Spectra: an Automatic Spectra Extraction Tool
In scientific literature, XANES/Raman data are usually plotted in line graphs which is a visually appropriate way to represent the information when the end-user is a human reader.
Fast and Accurate Road Crack Detection Based on Adaptive Cost-Sensitive Loss Function
Numerous detection problems in computer vision, including road crack detection, suffer from exceedingly foreground-background imbalance.
MR Image Super-Resolution With Squeeze and Excitation Reasoning Attention Network
They also fail to sense the entire space of the input, which is critical for high-quality MR image SR. To address those problems, we propose squeeze and excitation reasoning attention networks (SERAN) for accurate MR image SR. We propose to squeeze attention from global spatial information of the input and obtain global descriptors.
Ranked #2 on
Image Super-Resolution
on IXI
Cooperative Multi-Agent Transfer Learning with Level-Adaptive Credit Assignment
In addition, we use a novel agent network named Population Invariant agent with Transformer (PIT) to realize the coordination transfer in more varieties of scenarios.
Cooperative Multi-Agent Reinforcement Learning with Sequential Credit Assignment
In this paper, we propose a cooperative MARL method with sequential credit assignment (SeCA) that deduces each agent's contribution to the team's success one by one to learn better cooperation.
ECACL: A Holistic Framework for Semi-Supervised Domain Adaptation
This paper studies Semi-Supervised Domain Adaptation (SSDA), a practical yet under-investigated research topic that aims to learn a model of good performance using unlabeled samples and a few labeled samples in the target domain, with the help of labeled samples from a source domain.
RPCL: A Framework for Improving Cross-Domain Detection with Auxiliary Tasks
Contrasted with prior work, this paper provides a complementary solution to align domains by learning the same auxiliary tasks in both domains simultaneously.
L2E: Learning to Exploit Your Opponent
In this work, we propose a novel Learning to Exploit (L2E) framework for implicit opponent modeling.
VINS: Visual Search for Mobile User Interface Design
By utilizing this dataset, we propose an object-detection based image retrieval framework that models the UI context and hierarchical structure.
Bridge the Vision Gap from Field to Command: A Deep Learning Network Enhancing Illumination and Details
With the goal of tuning up the brightness, low-light image enhancement enjoys numerous applications, such as surveillance, remote sensing and computational photography.
Shed Various Lights on a Low-Light Image: Multi-Level Enhancement Guided by Arbitrary References
This paper proposes a neural network for multi-level low-light image enhancement, which is user-friendly to meet various requirements by selecting different images as brightness reference.
Video Matting via Consistency-Regularized Graph Neural Networks
In this paper, we propose to enhance the temporal coherence by Consistency-Regularized Graph Neural Networks (CRGNN) with the aid of a synthesized video matting dataset.
Temperature Regret Matching for Imperfect-Information Games
Regret matching (RM) plays a crucial role in CFR and its variants to approach Nash equilibrium.
Neighbor Class Consistency on Unsupervised Domain Adaptation
Unsupervised domain adaptation (UDA) is to make predictions for unlabeled data in a target domain with labeled data from source domain available.
OpenHoldem: A Benchmark for Large-Scale Imperfect-Information Game Research
Owning to the unremitting efforts by a few institutes, significant progress has recently been made in designing superhuman AIs in No-limit Texas Hold'em (NLTH), the primary testbed for large-scale imperfect-information game research.
DSAM: A Distance Shrinking with Angular Marginalizing Loss for High Performance Vehicle Re-identificatio
To obtain a high-performance vehicle ReID model, we present a novel Distance Shrinking with Angular Marginalizing (DSAM) loss function to perform hybrid learning in both the Original Feature Space (OFS) and the Feature Angular Space (FAS) using the local verification and the global identification information.
AIM 2020 Challenge on Learned Image Signal Processing Pipeline
This paper reviews the second AIM learned ISP challenge and provides the description of the proposed solutions and results.
Beyond the Deep Metric Learning: Enhance the Cross-Modal Matching with Adversarial Discriminative Domain Regularization
In this paper, we address this limitation with an efficient learning objective that considers the discriminative feature distributions between the visual objects and sentence words.
Pushing The Limit of Type I Codebook For FDD Massive MIMO Beamforming: A Channel Covariance Reconstruction Approach
There is a fundamental trade-off between the channel representation resolution of codebooks and the overheads of feedback communications in the fifth generation new radio (5G NR) frequency division duplex (FDD) massive multiple-input and multiple-output (MIMO) systems.
MixCon: Adjusting the Separability of Data Representations for Harder Data Recovery
To address the issue that deep neural networks (DNNs) are vulnerable to model inversion attacks, we design an objective function, which adjusts the separability of the hidden data representations, as a way to control the trade-off between data utility and vulnerability to inversion attacks.
TextHide: Tackling Data Privacy in Language Understanding Tasks
In addition, TextHide fits well with the popular framework of fine-tuning pre-trained language models (e. g., BERT) for any sentence or sentence-pair task.
InstaHide: Instance-hiding Schemes for Private Distributed Learning
This paper introduces InstaHide, a simple encryption of training images, which can be plugged into existing distributed deep learning pipelines.
Light Field View Synthesis via Aperture Disparity and Warping Confidence Map
This paper presents a learning-based approach to synthesize the view from an arbitrary camera position given a sparse set of images.
Cross-Domain Document Object Detection: Benchmark Suite and Method
We establish a benchmark suite consisting of different types of PDF document datasets that can be utilized for cross-domain DOD model training and evaluation.
Adversarial Feature Hallucination Networks for Few-Shot Learning
The recent flourish of deep learning in various tasks is largely accredited to the rich and accessible labeled data.
Privacy-preserving Learning via Deep Net Pruning
This paper attempts to answer the question whether neural network pruning can be used as a tool to achieve differential privacy without losing much data utility.
Learning Relaxed Belady for Content Distribution Network Caching
This paper presents a new approach for caching in CDNs that uses machine learning to approximate the Belady MIN algorithm.
Rethinking Zero-Shot Learning: A Conditional Visual Classification Perspective
We instead reformulate ZSL as a conditioned visual classification problem, i. e., classifying visual features based on the classifiers learned from the semantic descriptions.
Visual Semantic Reasoning for Image-Text Matching
It outperforms the current best method by 6. 8% relatively for image retrieval and 4. 8% relatively for caption retrieval on MS-COCO (Recall@1 using 1K test set).
Ranked #8 on
Image Retrieval
on Flickr30K 1K test
On-board Deep Q-Network for UAV-assisted Online Power Transfer and Data Collection
A key challenge is online MPT and data collection in the presence of on-board control of a UAV (e. g., patrolling velocity) for preventing battery drainage and data queue overflow of the sensing devices, while up-to-date knowledge on battery level and data queue of the devices is not available at the UAV.
Patient-Specific Effects of Medication Using Latent Force Models with Gaussian Processes
However, capturing the short-term effects of drugs and therapeutic interventions on patient physiological state remains challenging.
Authenticated Key-Value Stores with Hardware Enclaves
To circumvent the limited enclave memory (128 MB with the latest Intel CPUs), we propose to place the memory buffer of the eLSM store outside the enclave and protect the buffer using a new authenticated data structure by digesting individual LSM-tree levels.
Cryptography and Security Databases Distributed, Parallel, and Cluster Computing Data Structures and Algorithms
FeatherNets: Convolutional Neural Networks as Light as Feather for Face Anti-spoofing
Face Anti-spoofing gains increased attentions recently in both academic and industrial fields.
Ranked #3 on
Face Anti-Spoofing
on SiW-Enroll5
Residual Non-local Attention Networks for Image Restoration
To address this issue, we design local and non-local attention blocks to extract features that capture the long-range dependencies between pixels and pay more attention to the challenging parts.
PZnet: Efficient 3D ConvNet Inference on Manycore CPUs
Convolutional nets have been shown to achieve state-of-the-art accuracy in many biomedical image analysis tasks.
Fast 3D Line Segment Detection From Unorganized Point Cloud
This paper presents a very simple but efficient algorithm for 3D line segment detection from large scale unorganized point cloud.
Dynamic Spatio-temporal Graph-based CNNs for Traffic Prediction
To capture the graph dynamics, we use the graph prediction stream to predict the dynamic graph structures, and the predicted structures are fed into the flow prediction stream.
Support Neighbor Loss for Person Re-Identification
To ensure scalability and separability, a softmax-like function is formulated to push apart the positive and negative support sets.
Payoff Control in the Iterated Prisoner's Dilemma
Repeated game has long been the touchstone model for agents' long-run relationships.
Image Super-Resolution Using Very Deep Residual Channel Attention Networks
To solve these problems, we propose the very deep residual channel attention networks (RCAN).
Ranked #21 on
Image Super-Resolution
on BSD100 - 4x upscaling
Deep Cost-Sensitive and Order-Preserving Feature Learning for Cross-Population Age Estimation
First, a novel cost-sensitive multi-task loss function is designed to learn transferable aging features by training on the source population.
Deep Ordinal Hashing with Spatial Attention
However, most existing deep hashing methods directly learn the hash functions by encoding the global semantic information, while ignoring the local spatial information of images.
Large Linear Multi-output Gaussian Process Learning
Gaussian processes (GPs), or distributions over arbitrary functions in a continuous domain, can be generalized to the multi-output case: a linear model of coregionalization (LMC) is one approach.
Sparse Multi-Output Gaussian Processes for Medical Time Series Prediction
In the scenario of real-time monitoring of hospital patients, high-quality inference of patients' health status using all information available from clinical covariates and lab tests is essential to enable successful medical interventions and improve patient outcomes.
Quantum cluster approach to the topological invariants in correlated Chern insulators
We detect the topological properties of Chern insulators with strong Coulomb interactions by use of cluster perturbation theory and variational cluster approach.
Strongly Correlated Electrons
From rules to runs: A dynamic epistemic take on imperfect information games
We argue that the problem lies in the mix-up of two interpretations of the extensive form game structures: game rules or game runs which do not always coincide.
First-Take-All: Temporal Order-Preserving Hashing for 3D Action Videos
With the prevalence of the commodity depth cameras, the new paradigm of user interfaces based on 3D motion capturing and recognition have dramatically changed the way of interactions between human and computers.
Line-Based Multi-Label Energy Optimization for Fisheye Image Rectification and Calibration
Fisheye image rectification and estimation of intrinsic parameters for real scenes have been addressed in the literature by using line information on the distorted images.
Rank Subspace Learning for Compact Hash Codes
In this work, we propose a novel hash learning framework that encodes feature's rank orders instead of numeric values in a number of optimal low-dimensional ranking subspaces.
