Search Results for author:
Found 114 papers, 43 papers with code
Exploring Label Hierarchy in a Generative Way for Hierarchical Text Classification
Hierarchical Text Classification (HTC), which aims to predict text labels organized in hierarchical space, is a significant task lacking in investigation in natural language processing.
Dynamic Self-adaptive Multiscale Distillation from Pre-trained Multimodal Large Model for Efficient Cross-modal Representation Learning
Our methodology streamlines pre-trained multimodal large models using only their output features and original image-level information, requiring minimal computational resources.
Ensemble Adversarial Defense via Integration of Multiple Dispersed Low Curvature Models
In this work, we aim to enhance ensemble diversity by reducing attack transferability.
Privacy-Preserving End-to-End Spoken Language Understanding
Thus, the SLU system needs to ensure that a potential malicious attacker cannot deduce the sensitive attributes of the users, while it should avoid greatly compromising the SLU accuracy.
DiffSal: Joint Audio and Video Learning for Diffusion Saliency Prediction
Audio-visual saliency prediction can draw support from diverse modality complements, but further performance enhancement is still challenged by customized architectures as well as task-specific loss functions.
Global and Local Prompts Cooperation via Optimal Transport for Federated Learning
Specifically, for each client, we learn a global prompt to extract consensus knowledge among clients, and a local prompt to capture client-specific category characteristics.
A Unified Causal View of Instruction Tuning
The key idea is to learn task-required causal factors and only use those to make predictions for a given task.
BiLLM: Pushing the Limit of Post-Training Quantization for LLMs
Pretrained large language models (LLMs) exhibit exceptional general language processing capabilities but come with significant demands on memory and computational resources.
A Fast, Performant, Secure Distributed Training Framework For Large Language Model
In this paper, we propose a secure distributed LLM based on model slicing.
DaFoEs: Mixing Datasets towards the generalization of vision-state deep-learning Force Estimation in Minimally Invasive Robotic Surgery
In this paper, we present a new vision-haptic dataset (DaFoEs) with variable soft environments for the training of deep neural models.
Graph Relation Distillation for Efficient Biomedical Instance Segmentation
IGD constructs a graph representing instance features and relations, transferring these two types of knowledge by enforcing instance graph consistency.
Maximum Likelihood CFO Estimation for High-Mobility OFDM Systems: A Chinese Remainder Theorem Based Method
Orthogonal frequency division multiplexing (OFDM) is a widely adopted wireless communication technique but is sensitive to the carrier frequency offset (CFO).
Fed-CO2: Cooperation of Online and Offline Models for Severe Data Heterogeneity in Federated Learning
Specifically, the online model learns general knowledge that is shared among all clients, while the offline model is trained locally to learn the specialized knowledge of each individual client.
Earthfarseer: Versatile Spatio-Temporal Dynamical Systems Modeling in One Model
Efficiently modeling spatio-temporal (ST) physical processes and observations presents a challenging problem for the deep learning community.
A Simple Framework to Enhance the Adversarial Robustness of Deep Learning-based Intrusion Detection System
In this paper, we propose a novel IDS architecture that can enhance the robustness of IDS against adversarial attacks by combining conventional machine learning (ML) models and Deep Learning models.
Interpretable Modeling of Single-cell perturbation Responses to Novel Drugs Using Cycle Consistence Learning
Phenotype-based screening has attracted much attention for identifying cell-active compounds.
Generator Identification for Linear SDEs with Additive and Multiplicative Noise
In this paper, we present conditions for identifying the generator of a linear stochastic differential equation (SDE) from the distribution of its solution process with a given fixed initial state.
Experimental Results of Underwater Sound Speed Profile Inversion by Few-shot Multi-task Learning
Underwater Sound Speed Profile (SSP) distribution has great influence on the propagation mode of acoustic signal, thus the fast and accurate estimation of SSP is of great importance in building underwater observation systems.
Fast Ray-Tracing-Based Precise Underwater Acoustic Localization without Prior Acknowledgment of Target Depth
To tackle this issue, we propose an iterative ray tracing 3D underwater localization (IRTUL) method for stratification compensation.
Underwater Sound Speed Profile Construction: A Review
The proposal of SSP inversion method greatly improves the convenience and real--time performance, but the accuracy is not as good as the direct measurement method.
Rethinking Large-scale Pre-ranking System: Entire-chain Cross-domain Models
Industrial systems such as recommender systems and online advertising, have been widely equipped with multi-stage architectures, which are divided into several cascaded modules, including matching, pre-ranking, ranking and re-ranking.
Self-Supervised Neuron Segmentation with Multi-Agent Reinforcement Learning
By extracting semantic information from unlabeled data, self-supervised methods can improve the performance of downstream tasks, among which the mask image model (MIM) has been widely used due to its simplicity and effectiveness in recovering original information from masked images.
Multi-agent Reinforcement Learning
reinforcement-learning
+2
UniST: Towards Unifying Saliency Transformer for Video Saliency Prediction and Detection
While many approaches have crafted task-specific training paradigms for either video saliency prediction or video salient object detection tasks, few attention has been devoted to devising a generalized saliency modeling framework that seamlessly bridges both these distinct tasks.
DGSD: Dynamical Graph Self-Distillation for EEG-Based Auditory Spatial Attention Detection
Specifically, to effectively represent the non-Euclidean properties of EEG signals, dynamical graph convolutional networks are applied to represent the graph structure of EEG signals, which can also extract crucial features related to auditory spatial attention in EEG signals.
OHQ: On-chip Hardware-aware Quantization
Mixed-precision quantization leverages multiple bit-width architectures to unleash the accuracy and efficiency potential of quantized models.
Domain Adaptive Synapse Detection with Weak Point Annotations
In the second stage, we improve model generalizability on target data by regenerating square masks to get high-quality pseudo labels.
DARWIN Series: Domain Specific Large Language Models for Natural Science
To add new capabilities in natural science, enabling the acceleration and enrichment of automation of the discovery process, we present DARWIN, a series of tailored LLMs for natural science, mainly in physics, chemistry, and material science.
Inducing Causal Structure for Abstractive Text Summarization
The key idea is to reformulate the Variational Auto-encoder (VAE) to fit the joint distribution of the document and summary variables from the training corpus.
Minimalist Traffic Prediction: Linear Layer Is All You Need
Traffic prediction is essential for the progression of Intelligent Transportation Systems (ITS) and the vision of smart cities.
Learning Multiscale Consistency for Self-supervised Electron Microscopy Instance Segmentation
Instance segmentation in electron microscopy (EM) volumes is tough due to complex shapes and sparse annotations.
Induction Network: Audio-Visual Modality Gap-Bridging for Self-Supervised Sound Source Localization
By decoupling the gradients of visual and audio modalities, the discriminative visual representations of sound sources can be learned with the designed Induction Vector in a bootstrap manner, which also enables the audio modality to be aligned with the visual modality consistently.
Multi-scale Alternated Attention Transformer for Generalized Stereo Matching
Recent stereo matching networks achieves dramatic performance by introducing epipolar line constraint to limit the matching range of dual-view.
What, Indeed, is an Achievable Provable Guarantee for Learning-Enabled Safety Critical Systems
Machine learning has made remarkable advancements, but confidently utilising learning-enabled components in safety-critical domains still poses challenges.
Neural Causal Graph Collaborative Filtering
In this work, we propose to integrate causal modeling with the learning process of GCN-based GCF models, leveraging causality-aware graph embeddings to capture complex causal relations in recommendations.
FTFDNet: Learning to Detect Talking Face Video Manipulation with Tri-Modality Interaction
DeepFake based digital facial forgery is threatening public media security, especially when lip manipulation has been used in talking face generation, and the difficulty of fake video detection is further improved.
Graph Neural Networks Provably Benefit from Structural Information: A Feature Learning Perspective
Graph neural networks (GNNs) have pioneered advancements in graph representation learning, exhibiting superior feature learning and performance over multilayer perceptrons (MLPs) when handling graph inputs.
Generative Text-Guided 3D Vision-Language Pretraining for Unified Medical Image Segmentation
To address these challenges, we present Generative Text-Guided 3D Vision-Language Pretraining for Unified Medical Image Segmentation (GTGM), a framework that extends of VLP to 3D medical images without relying on paired textual descriptions.
Transforming Geospatial Ontologies by Homomorphisms
Geospatial ontology merging systems, natural partial orders on the systems, and geospatial ontology merging closures in the systems are then transformed under geospatial ontology system homomorphisms that are given by quotients and embeddings.
A Survey of Safety and Trustworthiness of Large Language Models through the Lens of Verification and Validation
Large Language Models (LLMs) have exploded a new heatwave of AI for their ability to engage end-users in human-level conversations with detailed and articulate answers across many knowledge domains.
Deep ReLU Networks Have Surprisingly Simple Polytopes
A ReLU network is a piecewise linear function over polytopes.
A data-driven rutting depth short-time prediction model with metaheuristic optimization for asphalt pavements based on RIOHTrack
Rutting of asphalt pavements is a crucial design criterion in various pavement design guides.
Understanding and Improving Feature Learning for Out-of-Distribution Generalization
Moreover, when fed the ERM learned features to the OOD objectives, the invariant feature learning quality significantly affects the final OOD performance, as OOD objectives rarely learn new features.
Large Language Models as Master Key: Unlocking the Secrets of Materials Science with GPT
The amount of data has growing significance in exploring cutting-edge materials and a number of datasets have been generated either by hand or automated approaches.
CASP-Net: Rethinking Video Saliency Prediction from an Audio-VisualConsistency Perceptual Perspective
Incorporating the audio stream enables Video Saliency Prediction (VSP) to imitate the selective attention mechanism of human brain.
Generic-to-Specific Distillation of Masked Autoencoders
Lightweight ViT models limited by the model capacity, however, benefit little from those pre-training mechanisms.
DMMG: Dual Min-Max Games for Self-Supervised Skeleton-Based Action Recognition
Our DMMG consists of a viewpoint variation min-max game and an edge perturbation min-max game.
Communication under Mixed Gaussian-Impulsive Channel: An End-to-End Framework
Under MGIN channel, classical communication signal schemes and corresponding detection methods usually can not achieve desirable performance as they are optimized with respect to WGN.
Style Projected Clustering for Domain Generalized Semantic Segmentation
In contrast to existing methods, we instead utilize the difference between images to build a better representation space, where the distinct style features are extracted and stored as the bases of representation.
Learning Cross-Representation Affinity Consistency for Sparsely Supervised Biomedical Instance Segmentation
Sparse instance-level supervision has recently been explored to address insufficient annotation in biomedical instance segmentation, which is easier to annotate crowded instances and better preserves instance completeness for 3D volumetric datasets compared to common semi-supervision. In this paper, we propose a sparsely supervised biomedical instance segmentation framework via cross-representation affinity consistency regularization.
Learning Steerable Function for Efficient Image Resampling
Image resampling is a basic technique that is widely employed in daily applications.
CASP-Net: Rethinking Video Saliency Prediction From an Audio-Visual Consistency Perceptual Perspective
Incorporating the audio stream enables Video Saliency Prediction (VSP) to imitate the selective attention mechanism of human brain.
A Soma Segmentation Benchmark in Full Adult Fly Brain
Finally, we provide quantitative and qualitative benchmark comparisons on the testset to validate the superiority of the proposed method, as well as preliminary statistics of the reconstructed somas in the full adult fly brain from the biological perspective.
TCFimt: Temporal Counterfactual Forecasting from Individual Multiple Treatment Perspective
TCFimt constructs adversarial tasks in a seq2seq framework to alleviate selection and time-varying bias and designs a contrastive learning-based block to decouple a mixed treatment effect into separated main treatment effects and causal interactions which further improves estimation accuracy.
Single-Pass Contrastive Learning Can Work for Both Homophilic and Heterophilic Graph
To answer this question, we theoretically study the concentration property of features obtained by neighborhood aggregation on homophilic and heterophilic graphs, introduce the single-pass augmentation-free graph contrastive learning loss based on the property, and provide performance guarantees for the minimizer of the loss on downstream tasks.
ViT-LSLA: Vision Transformer with Light Self-Limited-Attention
Consequently, this paper presents a light self-limited-attention (LSLA) consisting of a light self-attention mechanism (LSA) to save the computation cost and the number of parameters, and a self-limited-attention mechanism (SLA) to improve the performance.
Variance reduced Shapley value estimation for trustworthy data valuation
Data valuation, especially quantifying data value in algorithmic prediction and decision-making, is a fundamental problem in data trading scenarios.
Anisotropic multiresolution analyses for deepfake detection
We employ the fully separable wavelet transform and multiwavelets to obtain the anisotropic features to feed to standard CNN classifiers.
Joint Microstrip Selection and Beamforming Design for MmWave Systems with Dynamic Metasurface Antennas
Dynamic metasurface antennas (DMAs) provide a new paradigm to realize large-scale antenna arrays for future wireless systems.
Identifiability and Asymptotics in Learning Homogeneous Linear ODE Systems from Discrete Observations
This paper derives a sufficient condition for the identifiability of homogeneous linear ODE systems from a sequence of equally-spaced error-free observations sampled from a single trajectory.
Solving combinational optimization problems with evolutionary single-pixel imaging
Single-pixel imaging (SPI) is a novel optical imaging technique by replacing the pixelated sensor array in a conventional camera with a single-pixel detector.
VLSNR:Vision-Linguistics Coordination Time Sequence-aware News Recommendation
In our work, we propose a vision-linguistics coordinate time sequence news recommendation.
On the Sparse DAG Structure Learning Based on Adaptive Lasso
Learning the underlying Bayesian Networks (BNs), represented by directed acyclic graphs (DAGs), of the concerned events from purely-observational data is a crucial part of evidential reasoning.
Parameter Estimation of Mixed Gaussian-Impulsive Noise: An U-net++ Based Method
In many scenarios, the communication system suffers from both Gaussian white noise and non-Gaussian impulsive noise.
SAFARI: Versatile and Efficient Evaluations for Robustness of Interpretability
Finally, we demonstrate two applications of our methods: ranking robust XAI methods and selecting training schemes to improve both classification and interpretation robustness.
HiViT: Hierarchical Vision Transformer Meets Masked Image Modeling
A key idea of efficient implementation is to discard the masked image patches (or tokens) throughout the target network (encoder), which requires the encoder to be a plain vision transformer (e. g., ViT), albeit hierarchical vision transformers (e. g., Swin Transformer) have potentially better properties in formulating vision inputs.
MissDAG: Causal Discovery in the Presence of Missing Data with Continuous Additive Noise Models
In this paper, we develop a general method, which we call MissDAG, to perform causal discovery from data with incomplete observations.
Hierarchical Distribution-Aware Testing of Deep Learning
In this paper, we propose a new robustness testing approach for detecting AEs that considers both the feature level distribution and the pixel level distribution, capturing the perceptual quality of adversarial perturbations.
Deep Architecture Connectivity Matters for Its Convergence: A Fine-Grained Analysis
Advanced deep neural networks (DNNs), designed by either human or AutoML algorithms, are growing increasingly complex.
Playing Tic-Tac-Toe Games with Intelligent Single-pixel Imaging
Single-pixel imaging (SPI) is a novel optical imaging technique by replacing a two-dimensional pixelated sensor with a single-pixel detector and pattern illuminations.
Augmentation-Free Graph Contrastive Learning with Performance Guarantee
Graph contrastive learning (GCL) is the most representative and prevalent self-supervised learning approach for graph-structured data.
Enhancing Adversarial Training with Second-Order Statistics of Weights
In this paper, we show that treating model weights as random variables allows for enhancing adversarial training through \textbf{S}econd-Order \textbf{S}tatistics \textbf{O}ptimization (S$^2$O) with respect to the weights.
An Audio-Visual Attention Based Multimodal Network for Fake Talking Face Videos Detection
DeepFake based digital facial forgery is threatening the public media security, especially when lip manipulation has been used in talking face generation, the difficulty of fake video detection is further improved.
Attention-Based Lip Audio-Visual Synthesis for Talking Face Generation in the Wild
Rather than focusing on the unimportant regions of the face image, the proposed AttnWav2Lip model is able to pay more attention on the lip region reconstruction.
Audio-visual speech separation based on joint feature representation with cross-modal attention
Multi-modal based speech separation has exhibited a specific advantage on isolating the target character in multi-talker noisy environments.
Look\&Listen: Multi-Modal Correlation Learning for Active Speaker Detection and Speech Enhancement
Active speaker detection and speech enhancement have become two increasingly attractive topics in audio-visual scenario understanding.
Auto-scaling Vision Transformers without Training
The motivation comes from two pain spots: 1) the lack of efficient and principled methods for designing and scaling ViTs; 2) the tremendous computational cost of training ViT that is much heavier than its convolution counterpart.
Demystify Optimization and Generalization of Over-parameterized PAC-Bayesian Learning
In addition to being a pure generalization bound analysis tool, PAC-Bayesian bound can also be incorporated into an objective function to train a probabilistic neural network, making them a powerful and relevant framework that can numerically provide a tight generalization bound for supervised learning.
Achieving Efficient Distributed Machine Learning Using a Novel Non-Linear Class of Aggregation Functions
In this paper, we analyze properties of the WPM and rigorously prove convergence properties of our aggregation mechanism.
Knowledge Graph Based Waveform Recommendation: A New Communication Waveform Design Paradigm
In this paper, we investigate the waveform design from a novel perspective and propose a new waveform design paradigm with the knowledge graph (KG)-based intelligent recommendation system.
THE Benchmark: Transferable Representation Learning for Monocular Height Estimation
Therefore, we propose a new benchmark dataset to study the transferability of height estimation models in a cross-dataset setting.
Reliability Assessment and Safety Arguments for Machine Learning Components in System Assurance
The increasing use of Machine Learning (ML) components embedded in autonomous systems -- so-called Learning-Enabled Systems (LESs) -- has resulted in the pressing need to assure their functional safety.
Semantic-Aware Generation for Self-Supervised Visual Representation Learning
In this paper, we propose a self-supervised visual representation learning approach which involves both generative and discriminative proxies, where we focus on the former part by requiring the target network to recover the original image based on the mid-level features.
Ranked #63 on
Semantic Segmentation
on Cityscapes test
On the Equivalence between Neural Network and Support Vector Machine
Therefore, in this work, we propose to establish the equivalence between NN and SVM, and specifically, the infinitely wide NN trained by soft margin loss and the standard soft margin SVM with NTK trained by subgradient descent.
Deep Active Learning by Leveraging Training Dynamics
Active learning theories and methods have been extensively studied in classical statistical learning settings.
Long-tailed Distribution Adaptation
We propose to jointly optimize empirical risks of the unbalanced and balanced domains and approximate their domain divergence by intra-class and inter-class distances, with the aim to adapt models trained on the long-tailed distribution to general distributions in an interpretable way.
Hierarchy-Aware T5 with Path-Adaptive Mask Mechanism for Hierarchical Text Classification
Hierarchical Text Classification (HTC), which aims to predict text labels organized in hierarchical space, is a significant task lacking in investigation in natural language processing.
Unsupervised Cross-Modal Distillation for Thermal Infrared Tracking
To solve this problem, we propose to distill representations of the TIR modality from the RGB modality with Cross-Modal Distillation (CMD) on a large amount of unlabeled paired RGB-TIR data.
Heterogeneous network-based drug repurposing for COVID-19
The Corona Virus Disease 2019 (COVID-19) belongs to human coronaviruses (HCoVs), which spreads rapidly around the world.
Connection Sensitivity Matters for Training-free DARTS: From Architecture-Level Scoring to Operation-Level Sensitivity Analysis
We investigate this question through the lens of edge connectivity, and provide an affirmative answer by defining a connectivity concept, ZERo-cost Operation Sensitivity (ZEROS), to score the importance of candidate operations in DARTS at initialization.
Assessing the Reliability of Deep Learning Classifiers Through Robustness Evaluation and Operational Profiles
The utilisation of Deep Learning (DL) is advancing into increasingly more sophisticated applications.
Conformer: Local Features Coupling Global Representations for Visual Recognition
Within Convolutional Neural Network (CNN), the convolution operations are good at extracting local features but experience difficulty to capture global representations.
Ranked #322 on
Image Classification
on ImageNet
PD-GAN: Probabilistic Diverse GAN for Image Inpainting
To this end, we propose spatially probabilistic diversity normalization (SPDNorm) inside the modulation to model the probability of generating a pixel conditioned on the context information.
Advanced Deep Networks for 3D Mitochondria Instance Segmentation
Mitochondria instance segmentation from electron microscopy (EM) images has seen notable progress since the introduction of deep learning methods.
Ranked #1 on
3D Instance Segmentation
on MitoEM
Detecting Operational Adversarial Examples for Reliable Deep Learning
The utilisation of Deep Learning (DL) raises new challenges regarding its dependability in critical applications.
Towards Optimal Algorithms for Multi-Player Bandits without Collision Sensing Information
We propose a novel algorithm for multi-player multi-armed bandits without collision sensing information.
DeFLOCNet: Deep Image Editing via Flexible Low-level Controls
While existing methods combine an input image and these low-level controls for CNN inputs, the corresponding feature representations are not sufficient to convey user intentions, leading to unfaithfully generated content.
Sequential Random Network for Fine-grained Image Classification
To address this issue, we use the proposed SRN which composed of BiLSTM and several Tanh-Dropout blocks (called BiLSTM-TDN), to further process DCNN one-dimensional features for highlighting the detail information of image.
Towards Deepening Graph Neural Networks: A GNTK-based Optimization Perspective
Inspired by our theoretical insights on trainability, we propose Critical DropEdge, a connectivity-aware and graph-adaptive sampling method, to alleviate the exponential decay problem more fundamentally.
A Unified Framework for Specification Tests of Continuous Treatment Effect Models
We propose a general framework for the specification testing of continuous treatment effect models.
Fairness and Accuracy in Federated Learning
An appropriate weight selection algorithm that combines the information quantity of training accuracy and training frequency to measure the weights is proposed.
BayLIME: Bayesian Local Interpretable Model-Agnostic Explanations
Given the pressing need for assuring algorithmic transparency, Explainable AI (XAI) has emerged as one of the key areas of AI research.
Implicit bias of deep linear networks in the large learning rate phase
We claim that depending on the separation conditions of data, the gradient descent iterates will converge to a flatter minimum in the catapult phase.
Embedding and Extraction of Knowledge in Tree Ensemble Classifiers
Whilst, as the increasing use of machine learning models in security-critical applications, the embedding and extraction of malicious knowledge are equivalent to the notorious backdoor attack and its defence, respectively.
Rethinking Image Inpainting via a Mutual Encoder-Decoder with Feature Equalizations
We use CNN features from the deep and shallow layers of the encoder to represent structures and textures of an input image, respectively.
Achievable Rate Region of MISO Interference Channel Aided by Intelligent Reflecting Surface
This paper investigates the achievable rate region of the multiple-input single-output (MISO) interference channel aided by intelligent reflecting surfaces (IRSs).
On the Neural Tangent Kernel of Deep Networks with Orthogonal Initialization
The prevailing thinking is that orthogonal weights are crucial to enforcing dynamical isometry and speeding up training.
Gaussian Process Latent Variable Model Factorization for Context-aware Recommender Systems
Our work is primarily inspired by the Gaussian Process Latent Variable Model (GPLVM), which was a non-linear dimensionality reduction method.
Mean field theory for deep dropout networks: digging up gradient backpropagation deeply
In recent years, the mean field theory has been applied to the study of neural networks and has achieved a great deal of success.
One-Stage Inpainting with Bilateral Attention and Pyramid Filling Block
However, the two-stage architecture is time-consuming, the contextual information lack high-level semantics and ignores both the semantic relevance and distance information of hole's feature patches, these limitations result in blurry textures and distorted structures of final result.
Coverage Guided Testing for Recurrent Neural Networks
The test metrics and test case generation algorithm are implemented into a tool TestRNN, which is then evaluated on a set of LSTM benchmarks.
Transferability of Spectral Graph Convolutional Neural Networks
Transferability, which is a certain type of generalization capability, can be loosely defined as follows: if two graphs describe the same phenomenon, then a single filter or ConvNet should have similar repercussions on both graphs.
testRNN: Coverage-guided Testing on Recurrent Neural Networks
Recurrent neural networks (RNNs) have been widely applied to various sequential tasks such as text processing, video recognition, and molecular property prediction.
Attributes-aided Part Detection and Refinement for Person Re-identification
Person attributes are often exploited as mid-level human semantic information to help promote the performance of person re-identification task.
Multiobjective Optimization Differential Evolution Enhanced with Principle Component Analysis for Constrained Optimization
PMODE and HECO-PDE are compared with the algorithms from the IEEE CEC 2018 competition and another recent MOEA for constrained optimisation.
