Search Results for author:
Found 54 papers, 14 papers with code
MSECG: Incorporating Mamba for Robust and Efficient ECG Super-Resolution
Electrocardiogram (ECG) signals play a crucial role in diagnosing cardiovascular diseases.
Adversarial Detection with a Dynamically Stable System
Particularly, in our paper, the generation of adversarial examples is considered as the perturbation process of a Lyapunov dynamic system, and we propose an example stability mechanism, in which a novel control term is added in adversarial example generation to ensure that the normal examples can achieve dynamic stability while the adversarial examples cannot achieve the stability.
LPViT: Low-Power Semi-structured Pruning for Vision Transformers
Vision transformers have emerged as a promising alternative to convolutional neural networks for various image analysis tasks, offering comparable or superior performance.
From Algorithm to Hardware: A Survey on Efficient and Safe Deployment of Deep Neural Networks
To address these challenges, researchers have developed various model compression techniques such as model quantization and model pruning.
Improving Group Connectivity for Generalization of Federated Deep Learning
Bridging the gap between LMC and FL, in this paper, we leverage fixed anchor models to empirically and theoretically study the transitivity property of connectivity from two models (LMC) to a group of models (model fusion in FL).
Training-time Neuron Alignment through Permutation Subspace for Improving Linear Mode Connectivity and Model Fusion
In deep learning, stochastic gradient descent often yields functionally similar yet widely scattered solutions in the weight space even under the same initialization, causing barriers in the Linear Mode Connectivity (LMC) landscape.
A Framework for Inference Inspired by Human Memory Mechanisms
How humans and machines make sense of current inputs for relation reasoning and question-answering while putting the perceived information into context of our past memories, has been a challenging conundrum in cognitive science and artificial intelligence.
LCReg: Long-Tailed Image Classification with Latent Categories based Recognition
In this work, we tackle the challenging problem of long-tailed image recognition.
Efficient Joint Optimization of Layer-Adaptive Weight Pruning in Deep Neural Networks
On ImageNet, we achieve up to 4. 7% and 4. 6% higher top-1 accuracy compared to other methods for VGG-16 and ResNet-50, respectively.
Unlimited Knowledge Distillation for Action Recognition in the Dark
To address this issue, we propose an unlimited knowledge distillation (UKD) in this paper.
Improving the Transferability of Adversarial Examples via Direction Tuning
Although considerable efforts have been developed on improving the transferability of adversarial examples generated by transfer-based adversarial attacks, our investigation found that, the big deviation between the actual and steepest update directions of the current transfer-based adversarial attacks is caused by the large update step length, resulting in the generated adversarial examples can not converge well.
Fuzziness-tuned: Improving the Transferability of Adversarial Examples
In this paper, we first systematically investigated this issue and found that the enormous difference of attack success rates between the surrogate model and victim model is caused by the existence of a special area (known as fuzzy domain in our paper), in which the adversarial examples in the area are classified wrongly by the surrogate model while correctly by the victim model.
Deep Feature Selection for Anomaly Detection Based on Pretrained Network and Gaussian Discriminative Analysis
Deep learning neural network serves as a powerful tool for visual anomaly detection (AD) and fault diagnosis, attributed to its strong abstractive interpretation ability in the representation domain.
Ranked #73 on
Anomaly Detection
on MVTec AD
Hybrid Multimodal Feature Extraction, Mining and Fusion for Sentiment Analysis
In this paper, we present our solutions for the Multimodal Sentiment Analysis Challenge (MuSe) 2022, which includes MuSe-Humor, MuSe-Reaction and MuSe-Stress Sub-challenges.
FACM: Intermediate Layer Still Retain Effective Features against Adversarial Examples
To enhance the robustness of the classifier, in our paper, a \textbf{F}eature \textbf{A}nalysis and \textbf{C}onditional \textbf{M}atching prediction distribution (FACM) model is proposed to utilize the features of intermediate layers to correct the classification.
Improving the Robustness and Generalization of Deep Neural Network with Confidence Threshold Reduction
The empirical and theoretical analysis demonstrates that the MDL loss improves the robustness and generalization of the model simultaneously for natural training.
Long-tailed Recognition by Learning from Latent Categories
Previous long-tailed recognition methods commonly focus on the data augmentation or re-balancing strategy of the tail classes to give more attention to tail classes during the model training.
Ranked #9 on
Long-tail Learning
on CIFAR-10-LT (ρ=10)
OPQ: Compressing Deep Neural Networks with One-shot Pruning-Quantization
Numerous network compression methods such as pruning and quantization are proposed to reduce the model size significantly, of which the key is to find suitable compression allocation (e. g., pruning sparsity and quantization codebook) of each layer.
Gradient Aligned Attacks via a Few Queries
Specifically, we propose a gradient aligned mechanism to ensure that the derivatives of the loss function with respect to the logit vector have the same weight coefficients between the surrogate and victim models.
On Representation Knowledge Distillation for Graph Neural Networks
Past work on distillation for GNNs proposed the Local Structure Preserving loss (LSP), which matches local structural relationships defined over edges across the student and teacher's node embeddings.
Global Magnitude Pruning With Minimum Threshold Is All We Need
We showcase that magnitude based pruning, specifically, global magnitude pruning (GP) is sufficient to achieve SOTA performance on a range of neural network architectures.
Delving into Channels: Exploring Hyperparameter Space of Channel Bit Widths with Linear Complexity
We formulate the quantization of deep neural networks as a rate-distortion optimization problem, and present an ultra-fast algorithm to search the bit allocation of channels.
Few-Shot Segmentation with Global and Local Contrastive Learning
To this end, we first propose a prior extractor to learn the query information from the unlabeled images with our proposed global-local contrastive learning.
Point Discriminative Learning for Data-efficient 3D Point Cloud Analysis
In this work we propose PointDisc, a point discriminative learning method to leverage self-supervisions for data-efficient 3D point cloud classification and segmentation.
Learning Cross-Modal Retrieval With Noisy Labels
Recently, cross-modal retrieval is emerging with the help of deep multimodal learning.
PSRR-MaxpoolNMS: Pyramid Shifted MaxpoolNMS with Relationship Recovery
Unlike convolutions which are inherently parallel, the de-facto standard for NMS, namely GreedyNMS, cannot be easily parallelized and thus could be the performance bottleneck in convolutional object detection pipelines.
FFConv: Fast Factorized Convolutional Neural Network Inference on Encrypted Data
Despite the faster HECNN inference, the mainstream packing schemes Dense Packing (DensePack) and Convolution Packing (ConvPack) introduce expensive rotation overhead, which prolongs the inference latency of HECNN for deeper and wider CNN architectures.
Dimension Reduction in Quantum Key Distribution for Continuous- and Discrete-Variable Protocols
We develop a method to connect the infinite-dimensional description of optical continuous-variable quantum key distribution (QKD) protocols to a finite-dimensional formulation.
Dimensionality Reduction
Quantum Physics
A*HAR: A New Benchmark towards Semi-supervised learning for Class-imbalanced Human Activity Recognition
Despite the vast literature on Human Activity Recognition (HAR) with wearable inertial sensor data, it is perhaps surprising that there are few studies investigating semisupervised learning for HAR, particularly in a challenging scenario with class imbalance problem.
The Tsinghua University-Ma Huateng Telescopes for Survey: Overview and Performance of the System
The TMTS system can have a FoV of about 9 deg2 when monitoring the sky with two bands (i. e., SDSS g and r filters) at the same time, and a maximum FoV of ~18 deg2 when four telescopes monitor different sky areas in monochromatic filter mode.
Instrumentation and Methods for Astrophysics
Role-Wise Data Augmentation for Knowledge Distillation
To our knowledge, existing methods overlook the fact that although the student absorbs extra knowledge from the teacher, both models share the same input data -- and this data is the only medium by which the teacher's knowledge can be demonstrated.
Security proof of practical quantum key distribution with detection-efficiency mismatch
Our method also shows that in the absence of efficiency mismatch in our detector model, the key rate increases if the loss due to detection inefficiency is assumed to be outside of the adversary's control, as compared to the view where for a security proof this loss is attributed to the action of the adversary.
Quantum Physics
Deeply Activated Salient Region for Instance Search
Due to the lack of proper mechanism in locating instances and deriving feature representation, instance search is generally only effective for retrieving instances of known object categories.
MaskConvNet: Training Efficient ConvNets from Scratch via Budget-constrained Filter Pruning
(4) Fast, it is observed that the number of training epochs required by MaskConvNet is close to training a baseline without pruning.
Towards Effective 2-bit Quantization: Pareto-optimal Bit Allocation for Deep CNNs Compression
In this paper, we address an important problem of how to optimize the bit allocation of weights and activations for deep CNNs compression.
A*3D Dataset: Towards Autonomous Driving in Challenging Environments
With the increasing global popularity of self-driving cars, there is an immediate need for challenging real-world datasets for benchmarking and training various computer vision tasks such as 3D object detection.
Quantum-enhanced least-square support vector machine: simplified quantum algorithm and sparse solutions
We also incorporate kernel methods into the above quantum algorithms, which uses both exponential growth Hilbert space of qubits and infinite dimensionality of continuous variable for quantum feature maps.
Dataflow-based Joint Quantization of Weights and Activations for Deep Neural Networks
This paper addresses a challenging problem - how to reduce energy consumption without incurring performance drop when deploying deep neural networks (DNNs) at the inference stage.
TEA-DNN: the Quest for Time-Energy-Accuracy Co-optimized Deep Neural Networks
To this end, we introduce TEA-DNN, a NAS algorithm targeting multi-objective optimization of execution time, energy consumption, and classification accuracy of CNN workloads on embedded architectures.
Towards the AlexNet Moment for Homomorphic Encryption: HCNN, theFirst Homomorphic CNN on Encrypted Data with GPUs
In this paper, we show how to accelerate the performance of running CNNs on encrypted data with GPUs.
Simple security analysis of phase-matching measurement-device-independent quantum key distribution
Variations of phase-matching measurement-device-independent quantum key distribution (PM-MDI QKD) protocols have been investigated before, but it was recently discovered that this type of protocol (under the name of twin-field QKD) can beat the linear scaling of the repeaterless bound on secret key rate capacity.
Quantum Physics
End-to-End Video Classification with Knowledge Graphs
In particular, we unify traditional "knowledgeless" machine learning models and knowledge graphs in a novel end-to-end framework.
Pruning Convolutional Neural Networks for Image Instance Retrieval
In this work, we focus on the problem of image instance retrieval with deep descriptors extracted from pruned Convolutional Neural Networks (CNN).
Truly Multi-modal YouTube-8M Video Classification with Video, Audio, and Text
Beyond that, we extend the original competition by including text information in the classification, making this a truly multi-modal approach with vision, audio and text.
Deep Learning for Lung Cancer Detection: Tackling the Kaggle Data Science Bowl 2017 Challenge
We present a deep learning framework for computer-aided lung cancer diagnosis.
Compact Descriptors for Video Analysis: the Emerging MPEG Standard
This paper provides an overview of the on-going compact descriptors for video analysis standard (CDVA) from the ISO/IEC moving pictures experts group (MPEG).
Compression of Deep Neural Networks for Image Instance Retrieval
One major drawback of CNN-based {\it global descriptors} is that uncompressed deep neural network models require hundreds of megabytes of storage making them inconvenient to deploy in mobile applications or in custom hardware.
Nested Invariance Pooling and RBM Hashing for Image Instance Retrieval
The first one is Nested Invariance Pooling (NIP), a method inspired from i-theory, a mathematical theory for computing group invariant transformations with feed-forward neural networks.
Egocentric Activity Recognition with Multimodal Fisher Vector
With the increasing availability of wearable devices, research on egocentric activity recognition has received much attention recently.
Group Invariant Deep Representations for Image Instance Retrieval
Based on a thorough empirical evaluation using several publicly available datasets, we show that our method is able to significantly and consistently improve retrieval results every time a new type of invariance is incorporated.
Tiny Descriptors for Image Retrieval with Unsupervised Triplet Hashing
Then, triplet networks, a rank learning scheme based on weight sharing nets is used to fine-tune the binary embedding functions to retain as much as possible of the useful metric properties of the original space.
A Practical Guide to CNNs and Fisher Vectors for Image Instance Retrieval
The second part of the study focuses on the impact of geometrical transformations such as rotations and scale changes.
Co-Regularized Deep Representations for Video Summarization
A comprehensive user study is conducted comparing our proposed method to a variety of schemes, including the summarization currently in use by one of the most popular video sharing websites.
DeepHash: Getting Regularization, Depth and Fine-Tuning Right
This work focuses on representing very high-dimensional global image descriptors using very compact 64-1024 bit binary hashes for instance retrieval.
