Search Results for author:
Found 237 papers, 107 papers with code
Learning Attentive and Hierarchical Representations for 3D Shape Recognition
This paper proposes a novel method for 3D shape representation learning, namely Hyperbolic Embedded Attentive Representation (HEAR).
Region Graph Embedding Network for Zero-Shot Learning
To exploit the progressive interactions among these regions, we represent them as a region graph, on which the parts relation reasoning is performed with graph convolutions, thus leading to our PRR branch.
MambaTrack: Exploiting Dual-Enhancement for Night UAV Tracking
Night unmanned aerial vehicle (UAV) tracking is impeded by the challenges of poor illumination, with previous daylight-optimized methods demonstrating suboptimal performance in low-light conditions, limiting the utility of UAV applications.
GaussianPretrain: A Simple Unified 3D Gaussian Representation for Visual Pre-training in Autonomous Driving
In this context, we are excited to introduce GaussianPretrain, a novel pre-training paradigm that achieves a holistic understanding of the scene by uniformly integrating geometric and texture representations.
Step-wise Distribution Alignment Guided Style Prompt Tuning for Source-free Cross-domain Few-shot Learning
This paper addresses the source-free CDFSL (SF-CDFSL) problem, tackling few-shot learning (FSL) in the target domain using only pre-trained models and a few target samples without source data or strategies.
Cross Space and Time: A Spatio-Temporal Unitized Model for Traffic Flow Forecasting
In this paper, we introduce the Spatio-Temporal Unitized Model (STUM), a unified framework designed to capture both spatial and temporal dependencies while addressing spatio-temporal heterogeneity through techniques such as distribution alignment and feature fusion.
MaDiNet: Mamba Diffusion Network for SAR Target Detection
The fundamental challenge in SAR target detection lies in developing discriminative, efficient, and robust representations of target characteristics within intricate non-cooperative environments.
UEVAVD: A Dataset for Developing UAV's Eye View Active Object Detection
Active Object Detection (AOD) offers an effective way to achieve this purpose.
Advances in Photoacoustic Imaging Reconstruction and Quantitative Analysis for Biomedical Applications
Photoacoustic imaging (PAI) represents an innovative biomedical imaging modality that harnesses the advantages of optical resolution and acoustic penetration depth while ensuring enhanced safety.
Right this way: Can VLMs Guide Us to See More to Answer Questions?
To investigate this gap, we identify a critical and challenging task in the Visual Question Answering (VQA) scenario: can VLMs indicate how to adjust an image when the visual information is insufficient to answer a question?
Artificial Intelligence of Things: A Survey
We hope this survey will serve as a valuable resource for those engaged in AIoT research and act as a catalyst for future explorations to bridge gaps and drive advancements in this exciting field.
New Paradigm of Adversarial Training: Breaking Inherent Trade-Off between Accuracy and Robustness via Dummy Classes
Accordingly, to relax the tension between clean and robust learning derived from this overstrict assumption, we propose a new AT paradigm by introducing an additional dummy class for each original class, aiming to accommodate the hard adversarial samples with shifted distribution after perturbation.
S$^4$ST: A Strong, Self-transferable, faSt, and Simple Scale Transformation for Transferable Targeted Attack
Transferable targeted adversarial attacks (TTAs) against deep neural networks have been proven significantly more challenging than untargeted ones, yet they remain relatively underexplored.
Numerical Approximation Capacity of Neural Networks with Bounded Parameters: Do Limits Exist, and How Can They Be Measured?
This leads us to question: \textbf{Does the approximation capacity of a neural network remain universal, or does it have a limit when the parameters are practically bounded?
Towards Underwater Camouflaged Object Tracking: An Experimental Evaluation of SAM and SAM 2
Over the past decade, significant progress has been made in visual object tracking, largely due to the availability of large-scale training datasets.
Infrared Small Target Detection in Satellite Videos: A New Dataset and A Novel Recurrent Feature Refinement Framework
To address the aforementioned challenges, in this paper, we first build a large-scale dataset for MIRST detection in satellite videos (namely IRSatVideo-LEO), and then develop a recurrent feature refinement (RFR) framework as the baseline method.
Plane2Depth: Hierarchical Adaptive Plane Guidance for Monocular Depth Estimation
Specifically, in the proposed plane guided depth generator (PGDG), we design a set of plane queries as prototypes to softly model planes in the scene and predict per-pixel plane coefficients.
Seeing Your Speech Style: A Novel Zero-Shot Identity-Disentanglement Face-based Voice Conversion
Face-based Voice Conversion (FVC) is a novel task that leverages facial images to generate the target speaker's voice style.
Fusing Pruned and Backdoored Models: Optimal Transport-based Data-free Backdoor Mitigation
This method, based on our findings on neuron weight changes (NWCs) of random unlearning, uses optimal transport (OT)-based model fusion to combine the advantages of both pruned and backdoored models.
Prior-free Balanced Replay: Uncertainty-guided Reservoir Sampling for Long-Tailed Continual Learning
Even in the era of large models, one of the well-known issues in continual learning (CL) is catastrophic forgetting, which is significantly challenging when the continual data stream exhibits a long-tailed distribution, termed as Long-Tailed Continual Learning (LTCL).
Segment Anything for Videos: A Systematic Survey
To address this gap, this work conducts a systematic review on SAM for videos in the era of foundation models.
BackdoorBench: A Comprehensive Benchmark and Analysis of Backdoor Learning
1) We provide an integrated implementation of state-of-the-art (SOTA) backdoor learning algorithms (currently including 20 attack and 32 defense algorithms), based on an extensible modular-based codebase.
Enhancing Transferability of Targeted Adversarial Examples: A Self-Universal Perspective
We also contribute a surprising empirical insight that one of the most fundamental transformations, simple image scaling, is highly effective, scalable, sufficient, and necessary in enhancing targeted transferability.
A Comprehensive Survey on Human Video Generation: Challenges, Methods, and Insights
The goal of this survey is to offer the research community a clear and holistic view of the advancements in human video generation, highlighting the milestones achieved and the challenges that lie ahead.
ScaleDepth: Decomposing Metric Depth Estimation into Scale Prediction and Relative Depth Estimation
Our method decomposes metric depth into scene scale and relative depth, and predicts them through a semantic-aware scale prediction (SASP) module and an adaptive relative depth estimation (ARDE) module, respectively.
Ranked #1 on
Monocular Depth Estimation
on DIODE Outdoor
Cross Domain Object Detection via Multi-Granularity Confidence Alignment based Mean Teacher
Cross domain object detection learns an object detector for an unlabeled target domain by transferring knowledge from an annotated source domain.
Visible-Thermal Tiny Object Detection: A Benchmark Dataset and Baselines
Based on the proposed RGBT-Tiny dataset and SAFit measure, extensive evaluations have been conducted, including 23 recent state-of-the-art algorithms that cover four different types (i. e., visible generic detection, visible SOD, thermal SOD and RGBT object detection).
TwinS: Revisiting Non-Stationarity in Multivariate Time Series Forecasting
In this paper, we begin by validating this theory through wavelet analysis and propose the Transformer-based TwinS model, which consists of three modules to address the non-stationary periodic distributions: Wavelet Convolution, Period-Aware Attention, and Channel-Temporal Mixed MLP.
WebUOT-1M: Advancing Deep Underwater Object Tracking with A Million-Scale Benchmark
Most existing trackers are tailored for open-air environments, leading to performance degradation when applied to UOT due to domain gaps.
Unveiling and Mitigating Backdoor Vulnerabilities based on Unlearning Weight Changes and Backdoor Activeness
Recently, without poisoned data, unlearning models with clean data and then learning a pruning mask have contributed to backdoor defense.
TIMA: Text-Image Mutual Awareness for Balancing Zero-Shot Adversarial Robustness and Generalization Ability
Simultaneously, fixed pre-trained image embeddings are used as cross-modal auxiliary supervision to maintain the similarity between the MHE-tuned and original text embeddings by the knowledge distillation, preserving semantic information between different classes.
Awesome Multi-modal Object Tracking
To leverage more modalities, some recent efforts have been made to learn a unified visual object tracking model for any modality.
SARatrX: Towards Building A Foundation Model for SAR Target Recognition
Despite the remarkable progress in synthetic aperture radar automatic target recognition (SAR ATR), recent efforts have concentrated on the detection or classification of a specific and coarse category, e. g., vehicles, ships, airplanes, or buildings.
Bridge to Non-Barrier Communication: Gloss-Prompted Fine-grained Cued Speech Gesture Generation with Diffusion Model
Therefore, we propose a novel Gloss-prompted Diffusion-based CS Gesture generation framework (called GlossDiff).
Explainable Survival Analysis with Uncertainty using Convolution-Involved Vision Transformer
Highlights•Without patching WSIs, a novel ViT-based model is proposed for survival predictions.•We first introduce aleatoric uncertainty into the survival loss function.•We explain survival prediction using a post-hoc explainable method.•Our method outperforms baselines in accuracy, explainability, and reliability.
From Narratives to Numbers: Valid Inference Using Language Model Predictions from Verbal Autopsy Narratives
In this paper, we develop a method for valid inference using outcomes (in our case COD) predicted from free-form text using state-of-the-art NLP techniques.
SceneTracker: Long-term Scene Flow Estimation Network
Considering the complementarity of scene flow estimation in the spatial domain's focusing capability and 3D object tracking in the temporal domain's coherence, this study aims to address a comprehensive new task that can simultaneously capture fine-grained and long-term 3D motion in an online manner: long-term scene flow estimation (LSFE).
Bioinformatics and Biomedical Informatics with ChatGPT: Year One Review
The year 2023 marked a significant surge in the exploration of applying large language model (LLM) chatbots, notably ChatGPT, across various disciplines.
SurroundSDF: Implicit 3D Scene Understanding Based on Signed Distance Field
Vision-centric 3D environment understanding is both vital and challenging for autonomous driving systems.
LSKNet: A Foundation Lightweight Backbone for Remote Sensing
While a considerable amount of research has been dedicated to remote sensing classification, object detection and semantic segmentation, most of these studies have overlooked the valuable prior knowledge embedded within remote sensing scenarios.
Ranked #2 on
Change Detection
on S2Looking
SARDet-100K: Towards Open-Source Benchmark and ToolKit for Large-Scale SAR Object Detection
To the best of our knowledge, SARDet-100K is the first COCO-level large-scale multi-class SAR object detection dataset ever created.
Ranked #2 on
2D Object Detection
on SARDet-100K
(using extra training data)
Hide in Thicket: Generating Imperceptible and Rational Adversarial Perturbations on 3D Point Clouds
We find that concealing deformation perturbations in areas insensitive to human eyes can achieve a better trade-off between imperceptibility and adversarial strength, specifically in parts of the object surface that are complex and exhibit drastic curvature changes.
A Survey on Human-AI Teaming with Large Pre-Trained Models
In the rapidly evolving landscape of artificial intelligence (AI), the collaboration between human intelligence and AI systems, known as Human-AI (HAI) Teaming, has emerged as a cornerstone for advancing problem-solving and decision-making processes.
Enhancing Information Maximization with Distance-Aware Contrastive Learning for Source-Free Cross-Domain Few-Shot Learning
For this reason, this paper explores a Source-Free CDFSL (SF-CDFSL) problem, in which CDFSL is addressed through the use of existing pretrained models instead of training a model with source data, avoiding accessing source data.
Lightweight Pixel Difference Networks for Efficient Visual Representation Learning
With PDC and Bi-PDC, we further present two lightweight deep networks named \emph{Pixel Difference Networks (PiDiNet)} and \emph{Binary PiDiNet (Bi-PiDiNet)} respectively to learn highly efficient yet more accurate representations for visual tasks including edge detection and object recognition.
Computation and Parameter Efficient Multi-Modal Fusion Transformer for Cued Speech Recognition
Cued Speech (CS) is a pure visual coding method used by hearing-impaired people that combines lip reading with several specific hand shapes to make the spoken language visible.
Towards Assessing the Synthetic-to-Measured Adversarial Vulnerability of SAR ATR
Recently, there has been increasing concern about the vulnerability of deep neural network (DNN)-based synthetic aperture radar (SAR) automatic target recognition (ATR) to adversarial attacks, where a DNN could be easily deceived by clean input with imperceptible but aggressive perturbations.
BackdoorBench: A Comprehensive Benchmark and Analysis of Backdoor Learning
We hope that our efforts could build a solid foundation of backdoor learning to facilitate researchers to investigate existing algorithms, develop more innovative algorithms, and explore the intrinsic mechanism of backdoor learning.
Bilateral Reference for High-Resolution Dichotomous Image Segmentation
It comprises two essential components: the localization module (LM) and the reconstruction module (RM) with our proposed bilateral reference (BiRef).
Ranked #1 on
Camouflaged Object Segmentation
on COD
Camouflaged Object Segmentation
Dichotomous Image Segmentation
+3
ARBiBench: Benchmarking Adversarial Robustness of Binarized Neural Networks
2) BNNs consistently exhibit better adversarial robustness under black-box attacks.
OccNeRF: Advancing 3D Occupancy Prediction in LiDAR-Free Environments
Occupancy prediction reconstructs 3D structures of surrounding environments.
Defenses in Adversarial Machine Learning: A Survey
Adversarial phenomenon has been widely observed in machine learning (ML) systems, especially in those using deep neural networks, describing that ML systems may produce inconsistent and incomprehensible predictions with humans at some particular cases.
Predicting Gradient is Better: Exploring Self-Supervised Learning for SAR ATR with a Joint-Embedding Predictive Architecture
The growing Synthetic Aperture Radar (SAR) data has the potential to build a foundation model through Self-Supervised Learning (SSL) methods, which can achieve various SAR Automatic Target Recognition (ATR) tasks with pre-training in large-scale unlabeled data and fine-tuning in small labeled samples.
A Causal Disentangled Multi-Granularity Graph Classification Method
Graph data widely exists in real life, with large amounts of data and complex structures.
Enhancing Representations through Heterogeneous Self-Supervised Learning
Thus, we propose Heterogeneous Self-Supervised Learning (HSSL), which enforces a base model to learn from an auxiliary head whose architecture is heterogeneous from the base model.
Realistic Speech-to-Face Generation with Speech-Conditioned Latent Diffusion Model with Face Prior
To overcome this challenge, we introduce the concept of residuals by integrating a statistical face prior to the diffusion process.
RenderOcc: Vision-Centric 3D Occupancy Prediction with 2D Rendering Supervision
3D occupancy prediction holds significant promise in the fields of robot perception and autonomous driving, which quantifies 3D scenes into grid cells with semantic labels.
DFormer: Rethinking RGBD Representation Learning for Semantic Segmentation
We present DFormer, a novel RGB-D pretraining framework to learn transferable representations for RGB-D segmentation tasks.
Ranked #1 on
RGB-D Salient Object Detection
on DES
Fast Sparse PCA via Positive Semidefinite Projection for Unsupervised Feature Selection
A standard convex SPCA-based model with PSD constraint for unsupervised feature selection is proposed.
Grouping Boundary Proposals for Fast Interactive Image Segmentation
These boundary proposals are then incorporated into the proposed image segmentation model, such that the target segmentation contours are made up of a set of selected boundary proposals and the corresponding geodesic paths linking them.
A Survey on Deep Multi-modal Learning for Body Language Recognition and Generation
In summary, this survey paper provides a comprehensive understanding of deep multi-modal learning for various BL generations and recognitions for the first time.
Few-shot Class-incremental Learning: A Survey
In our in-depth examination, we delve into various facets of FSCIL, encompassing the problem definition, the discussion of the primary challenges of unreliable empirical risk minimization and the stability-plasticity dilemma, general schemes, and relevant problems of IL and Few-shot Learning (FSL).
class-incremental learning
Class-Incremental Object Detection
+6
Pareto Invariant Representation Learning for Multimedia Recommendation
Multimedia recommendation involves personalized ranking tasks, where multimedia content is usually represented using a generic encoder.
The RoboDepth Challenge: Methods and Advancements Towards Robust Depth Estimation
In this paper, we summarize the winning solutions from the RoboDepth Challenge -- an academic competition designed to facilitate and advance robust OoD depth estimation.
SwinMM: Masked Multi-view with Swin Transformers for 3D Medical Image Segmentation
To address this limitation, we present Masked Multi-view with Swin Transformers (SwinMM), a novel multi-view pipeline for enabling accurate and data-efficient self-supervised medical image analysis.
ROFusion: Efficient Object Detection using Hybrid Point-wise Radar-Optical Fusion
In this paper, we propose a hybrid point-wise Radar-Optical fusion approach for object detection in autonomous driving scenarios.
Unbiased Scene Graph Generation via Two-stage Causal Modeling
To remedy this, we propose Two-stage Causal Modeling (TsCM) for the SGG task, which takes the long-tailed distribution and semantic confusion as confounders to the Structural Causal Model (SCM) and then decouples the causal intervention into two stages.
All in One: Exploring Unified Vision-Language Tracking with Multi-Modal Alignment
This approach achieves feature integration in a unified backbone, removing the need for carefully-designed fusion modules and resulting in a more effective and efficient VL tracking framework.
Revisiting Computer-Aided Tuberculosis Diagnosis
This dataset enables the training of sophisticated detectors for high-quality CTD.
UniOcc: Unifying Vision-Centric 3D Occupancy Prediction with Geometric and Semantic Rendering
In this technical report, we present our solution, named UniOCC, for the Vision-Centric 3D occupancy prediction track in the nuScenes Open Dataset Challenge at CVPR 2023.
Ranked #4 on
Prediction Of Occupancy Grid Maps
on Occ3D-nuScenes
SplatFlow: Learning Multi-frame Optical Flow via Splatting
The occlusion problem remains a crucial challenge in optical flow estimation (OFE).
Emotional Talking Head Generation based on Memory-Sharing and Attention-Augmented Networks
Given an audio clip and a reference face image, the goal of the talking head generation is to generate a high-fidelity talking head video.
A Novel Interpretable and Generalizable Re-synchronization Model for Cued Speech based on a Multi-Cuer Corpus
Cued Speech (CS) is a multi-modal visual coding system combining lip reading with several hand cues at the phonetic level to make the spoken language visible to the hearing impaired.
MAVD: The First Open Large-Scale Mandarin Audio-Visual Dataset with Depth Information
Audio-visual speech recognition (AVSR) gains increasing attention from researchers as an important part of human-computer interaction.
Versatile Backdoor Attack with Visible, Semantic, Sample-Specific, and Compatible Triggers
Deep neural networks (DNNs) can be manipulated to exhibit specific behaviors when exposed to specific trigger patterns, without affecting their performance on benign samples, dubbed \textit{backdoor attack}.
X-IQE: eXplainable Image Quality Evaluation for Text-to-Image Generation with Visual Large Language Models
This paper introduces a novel explainable image quality evaluation approach called X-IQE, which leverages visual large language models (LLMs) to evaluate text-to-image generation methods by generating textual explanations.
FedAds: A Benchmark for Privacy-Preserving CVR Estimation with Vertical Federated Learning
We introduce FedAds, the first benchmark for CVR estimation with vFL, to facilitate standardized and systematical evaluations for vFL algorithms.
A Comprehensive Survey on Segment Anything Model for Vision and Beyond
As the first to comprehensively review the progress of segmenting anything task for vision and beyond based on the foundation model of SAM, this work focuses on its applications to various tasks and data types by discussing its historical development, recent progress, and profound impact on broad applications.
Deep Intellectual Property Protection: A Survey
Deep Neural Networks (DNNs), from AlexNet to ResNet to ChatGPT, have made revolutionary progress in recent years, and are widely used in various fields.
A Forward and Backward Compatible Framework for Few-shot Class-incremental Pill Recognition
In forward-compatible learning, we propose an innovative virtual class synthesis strategy and a Center-Triplet (CT) loss to enhance discriminative feature learning.
class-incremental learning
Few-Shot Class-Incremental Learning
+6
Boosting Convolutional Neural Networks with Middle Spectrum Grouped Convolution
This paper proposes a novel module called middle spectrum grouped convolution (MSGC) for efficient deep convolutional neural networks (DCNNs) with the mechanism of grouped convolution.
Hierarchical Disentanglement-Alignment Network for Robust SAR Vehicle Recognition
However, robustly recognizing vehicle targets is a challenging task in SAR due to the large intraclass variations and small interclass variations.
Mapping Degeneration Meets Label Evolution: Learning Infrared Small Target Detection with Single Point Supervision
Interestingly, during the training phase supervised by point labels, we discover that CNNs first learn to segment a cluster of pixels near the targets, and then gradually converge to predict groundtruth point labels.
Learning Invariant Representation via Contrastive Feature Alignment for Clutter Robust SAR Target Recognition
The proposed method contributes a mixed clutter variants generation strategy and a new inference branch equipped with channel-weighted mean square error (CWMSE) loss for invariant representation learning.
Discovering and Explaining the Non-Causality of Deep Learning in SAR ATR
Therefore, the degree of overfitting for clutter reflects the non-causality of deep learning in SAR ATR.
FER-former: Multi-modal Transformer for Facial Expression Recognition
The ever-increasing demands for intuitive interactions in Virtual Reality has triggered a boom in the realm of Facial Expression Recognition (FER).
Facial Expression Recognition
Facial Expression Recognition (FER)
SRFormerV2: Taking a Closer Look at Permuted Self-Attention for Image Super-Resolution
Without any bells and whistles, we show that our SRFormer achieves a 33. 86dB PSNR score on the Urban100 dataset, which is 0. 46dB higher than that of SwinIR but uses fewer parameters and computations.
From Local Binary Patterns to Pixel Difference Networks for Efficient Visual Representation Learning
LBP is a successful hand-crafted feature descriptor in computer vision.
Deep Learning for Cross-Domain Few-Shot Visual Recognition: A Survey
To address this, Few-shot learning (FSL) enables models to perform the target tasks with very few labeled examples by leveraging prior knowledge from related tasks.
Spatio-Temporal Structure Consistency for Semi-supervised Medical Image Classification
Experiments on two medical image datasets (i. e., ISIC 2018 challenge and ChestX-ray14) show that our method outperforms state-of-the-art SSL methods.
Attacks in Adversarial Machine Learning: A Systematic Survey from the Life-cycle Perspective
Adversarial machine learning (AML) studies the adversarial phenomenon of machine learning, which may make inconsistent or unexpected predictions with humans.
Generalized Few-Shot Continual Learning with Contrastive Mixture of Adapters
The goal of Few-Shot Continual Learning (FSCL) is to incrementally learn novel tasks with limited labeled samples and preserve previous capabilities simultaneously, while current FSCL methods are all for the class-incremental purpose.
Learning Symbolic Models for Graph-structured Physical Mechanism
The essence of our method is to model the formula skeleton with a message-passing flow, which helps transform the discovery of the skeleton into the search for the message-passing flow.
Uncertainty-Aware Distillation for Semi-Supervised Few-Shot Class-Incremental Learning
Given a model well-trained with a large-scale base dataset, Few-Shot Class-Incremental Learning (FSCIL) aims at incrementally learning novel classes from a few labeled samples by avoiding overfitting, without catastrophically forgetting all encountered classes previously.
class-incremental learning
Few-Shot Class-Incremental Learning
+2
Enabling Augmented Segmentation and Registration in Ultrasound-Guided Spinal Surgery via Realistic Ultrasound Synthesis from Diagnostic CT Volume
While the US is not a standard paradigm for spinal surgery, the scarcity of intra-operative clinical US data is an insurmountable bottleneck in training a neural network.
BS3D: Building-scale 3D Reconstruction from RGB-D Images
Various datasets have been proposed for simultaneous localization and mapping (SLAM) and related problems.
Global Balanced Experts for Federated Long-Tailed Learning
In particular, a proxy is derived from the accumulated gradients uploaded by the clients after local training, and is shared by all clients as the class prior for re-balance training.
WL-Align: Weisfeiler-Lehman Relabeling for Aligning Users across Networks via Regularized Representation Learning
Aligning users across networks using graph representation learning has been found effective where the alignment is accomplished in a low-dimensional embedding space.
TiG-BEV: Multi-view BEV 3D Object Detection via Target Inner-Geometry Learning
In this paper, we propose the learning scheme of Target Inner-Geometry from the LiDAR modality into camera-based BEV detectors for both dense depth and BEV features, termed as TiG-BEV.
AMDET: Attention based Multiple Dimensions EEG Transformer for Emotion Recognition
In this paper, we propose a deep model called Attention-based Multiple Dimensions EEG Transformer (AMDET), which can exploit the complementarity among the spectral-spatial-temporal features of EEG data by employing the multi-dimensional global attention mechanism.
Generating and Weighting Semantically Consistent Sample Pairs for Ultrasound Contrastive Learning
In this work, we pre-train DNNs on ultrasound (US) domains instead of ImageNet to reduce the domain gap in medical US applications.
Cross-Modal Mutual Learning for Cued Speech Recognition
To our knowledge, this is the first work on ACSR for Mandarin Chinese.
Rethinking Two Consensuses of the Transferability in Deep Learning
Deep transfer learning (DTL) has formed a long-term quest toward enabling deep neural networks (DNNs) to reuse historical experiences as efficiently as humans.
TAOTF: A Two-stage Approximately Orthogonal Training Framework in Deep Neural Networks
In the first stage, we propose a novel algorithm called polar decomposition-based orthogonal initialization (PDOI) to find a good initialization for the orthogonal optimization.
Power Efficient Video Super-Resolution on Mobile NPUs with Deep Learning, Mobile AI & AIM 2022 challenge: Report
While numerous solutions have been proposed for this problem, they are usually quite computationally demanding, demonstrating low FPS rates and power efficiency on mobile devices.
Boosting Binary Neural Networks via Dynamic Thresholds Learning
For ViTs, DyBinaryCCT presents the superiority of the convolutional embedding layer in fully binarized ViTs and achieves 56. 1% on the ImageNet dataset, which is nearly 9% higher than the baseline.
Dynamic Event-Triggered Discrete-Time Linear Time-Varying System with Privacy-Preservation
Moreover, the privacy of the system is analyzed to ensure the security of the real data.
HiCo: Hierarchical Contrastive Learning for Ultrasound Video Model Pretraining
This work proposes a hierarchical contrastive learning (HiCo) method to improve the transferability for the US video model pretraining.
On Clustering Trend in Language Evolution Based on Dynamical Behaviors of Multi-Agent Model
Computer model has been extensively adopted to overcome the time limitation of language evolution by transforming language theory into physical modeling mechanism, which helps to explore the general laws of the evolution.
SVNet: Where SO(3) Equivariance Meets Binarization on Point Cloud Representation
Precisely, the presence of scalar features makes the major part of the network binarizable, while vector features serve to retain rich structural information and ensure SO(3) equivariance.
Scattering Model Guided Adversarial Examples for SAR Target Recognition: Attack and Defense
Toward building more robust DNN-based SAR ATR models, this article explores the domain knowledge of SAR imaging process and proposes a novel Scattering Model Guided Adversarial Attack (SMGAA) algorithm which can generate adversarial perturbations in the form of electromagnetic scattering response (called adversarial scatterers).
Sim2Word: Explaining Similarity with Representative Attribute Words via Counterfactual Explanations
Different from existing models, in this paper, we propose a new interpretation method that explains the image similarity models by salience maps and attribute words.
Bag of Tricks for FGSM Adversarial Training
Adversarial training (AT) with samples generated by Fast Gradient Sign Method (FGSM), also known as FGSM-AT, is a computationally simple method to train robust networks.
Cross-Domain Few-Shot Classification via Inter-Source Stylization
The goal of Cross-Domain Few-Shot Classification (CDFSC) is to accurately classify a target dataset with limited labelled data by exploiting the knowledge of a richly labelled auxiliary dataset, despite the differences between the domains of the two datasets.
KL-divergence Based Deep Learning for Discrete Time Model
Neural Network (Deep Learning) is a modern model in Artificial Intelligence and it has been exploited in Survival Analysis.
Data-free Backdoor Removal based on Channel Lipschitzness
Pruning these channels was then shown to be effective in mitigating the backdoor behaviors.
Graph Signal Processing for Heterogeneous Change Detection Part II: Spectral Domain Analysis
Then, we propose a regression model for the HCD, which decomposes the source signal into the regressed signal and changed signal, and requires the regressed signal have the same spectral property as the target signal on the same graph.
Graph Signal Processing for Heterogeneous Change Detection Part I: Vertex Domain Filtering
In this first part, we analyze the HCD with GSP from the vertex domain.
Advanced Conditional Variational Autoencoders (A-CVAE): Towards interpreting open-domain conversation generation via disentangling latent feature representation
Particularly, the model integrates the macro-level guided-category knowledge and micro-level open-domain dialogue data for the training, leveraging the priori knowledge into the latent space, which enables the model to disentangle the latent variables within the mesoscopic scale.
Rethinking Few-Shot Class-Incremental Learning with Open-Set Hypothesis in Hyperbolic Geometry
Few-Shot Class-Incremental Learning (FSCIL) aims at incrementally learning novel classes from a few labeled samples by avoiding the overfitting and catastrophic forgetting simultaneously.
class-incremental learning
Few-Shot Class-Incremental Learning
+3
HQANN: Efficient and Robust Similarity Search for Hybrid Queries with Structured and Unstructured Constraints
The in-memory approximate nearest neighbor search (ANNS) algorithms have achieved great success for fast high-recall query processing, but are extremely inefficient when handling hybrid queries with unstructured (i. e., feature vectors) and structured (i. e., related attributes) constraints.
MetaLR: Meta-tuning of Learning Rates for Transfer Learning in Medical Imaging
In this work, we propose a meta-learning-based LR tuner, named MetaLR, to make different layers automatically co-adapt to downstream tasks based on their transferabilities across domains.
Median Pixel Difference Convolutional Network for Robust Face Recognition
Face recognition is one of the most active tasks in computer vision and has been widely used in the real world.
Deep Learning for Visual Speech Analysis: A Survey
Visual speech, referring to the visual domain of speech, has attracted increasing attention due to its wide applications, such as public security, medical treatment, military defense, and film entertainment.
Acoustic-to-articulatory Inversion based on Speech Decomposition and Auxiliary Feature
Acoustic-to-articulatory inversion (AAI) is to obtain the movement of articulators from speech signals.
Residual-guided Personalized Speech Synthesis based on Face Image
Experimental results show that the speech synthesized by our model is comparable to the personalized speech synthesized by training a large amount of audio data in previous works.
Exploring Inter-Channel Correlation for Diversity-preserved KnowledgeDistillation
Extensive experiments on two vision tasks, includ-ing ImageNet classification and Pascal VOC segmentation, demonstrate the superiority of our ICKD, which consis-tently outperforms many existing methods, advancing thestate-of-the-art in the fields of Knowledge Distillation.
WebUAV-3M: A Benchmark for Unveiling the Power of Million-Scale Deep UAV Tracking
In this work, we propose WebUAV-3M, the largest public UAV tracking benchmark to date, to facilitate both the development and evaluation of deep UAV trackers.
Attentional Feature Refinement and Alignment Network for Aircraft Detection in SAR Imagery
Aircraft detection in Synthetic Aperture Radar (SAR) imagery is a challenging task in SAR Automatic Target Recognition (SAR ATR) areas due to aircraft's extremely discrete appearance, obvious intraclass variation, small size and serious background's interference.
Improved (Related-key) Differential-based Neural Distinguishers for SIMON and SIMECK Block Ciphers
In CRYPTO 2019, Gohr made a pioneering attempt and successfully applied deep learning to the differential cryptanalysis against NSA block cipher SPECK32/64, achieving higher accuracy than the pure differential distinguishers.
Decoupling Makes Weakly Supervised Local Feature Better
Weakly supervised learning can help local feature methods to overcome the obstacle of acquiring a large-scale dataset with densely labeled correspondences.
Ranked #1 on
Camera Localization
on Aachen Day-Night benchmark
Local Motion and Contrast Priors Driven Deep Network for Infrared Small Target Super-Resolution
Specifically, motivated by the local motion prior in the spatio-temporal dimension, we propose a local spatio-temporal attention module to perform implicit frame alignment and incorporate the local spatio-temporal information to enhance the local features (especially for small targets).
Learnable Lookup Table for Neural Network Quantization
Since a linear quantizer (i. e., round(*) function) cannot well fit the bell-shaped distributions of weights and activations, many existing methods use pre-defined functions (e. g., exponential function) with learnable parameters to build the quantizer for joint optimization.
Highly-Efficient Incomplete Large-Scale Multi-View Clustering With Consensus Bipartite Graph
Multi-view clustering has received increasing attention due to its effectiveness in fusing complementary information without manual annotations.
Efficient Video Transformers with Spatial-Temporal Token Selection
Video transformers have achieved impressive results on major video recognition benchmarks, which however suffer from high computational cost.
Towards Improving Embedding Based Models of Social Network Alignment via Pseudo Anchors
Social network alignment aims at aligning person identities across social networks.
Image-Guided Navigation of a Robotic Ultrasound Probe for Autonomous Spinal Sonography Using a Shadow-aware Dual-Agent Framework
Ultrasound (US) imaging is commonly used to assist in the diagnosis and interventions of spine diseases, while the standardized US acquisitions performed by manually operating the probe require substantial experience and training of sonographers.
Transient Synchronization Stability Analysis of Wind Farms with MMC-HVDC Integration Under Offshore AC Grid Fault
The MMC-HVDC connected offshore wind farms (OWFs) could suffer short circuit fault (SCF), whereas their transient stability is not well analysed.
Unsupervised cross-user adaptation in taste sensation recognition based on surface electromyography with conformal prediction and domain regularized component analysis
The results show that DRCA improved the classification accuracy on six subjects (p < 0. 05), compared with the baseline models trained only with the source domain data;, while CPSC did not guarantee the accuracy improvement.
Dynamic Binary Neural Network by learning channel-wise thresholds
The experimental results prove that our method is an effective and straightforward way to reduce information loss and enhance performance of BNNs.
Decoupling Long- and Short-Term Patterns in Spatiotemporal Inference
Specifically, we introduce a joint spatiotemporal graph attention network to learn the relations across space and time for short-term patterns.