Search Results for author:
Found 133 papers, 33 papers with code
RTLMarker: Protecting LLM-Generated RTL Copyright via a Hardware Watermarking Framework
Recent advances of large language models in the field of Verilog generation have raised several ethical and security concerns, such as code copyright protection and dissemination of malicious code.
Deep Reinforcement Learning for Job Scheduling and Resource Management in Cloud Computing: An Algorithm-Level Review
Cloud computing has revolutionized the provisioning of computing resources, offering scalable, flexible, and on-demand services to meet the diverse requirements of modern applications.
Adaptive Self-supervised Learning for Social Recommendations
More specifically, an adaptive weighting mechanism is proposed to learn adaptive weights for various self-supervised auxiliary tasks, so as to balance the contribution of such self-supervised auxiliary tasks for enhancing representation learning in social recommendations.
Efficient Scaling of Diffusion Transformers for Text-to-Image Generation
We empirically study the scaling properties of various Diffusion Transformers (DiTs) for text-to-image generation by performing extensive and rigorous ablations, including training scaled DiTs ranging from 0. 3B upto 8B parameters on datasets up to 600M images.
Distributed Estimation with Quantized Measurements and Communication over Markovian Switching Topologies
This paper addresses distributed parameter estimation in stochastic dynamic systems with quantized measurements, constrained by quantized communication and Markovian switching directed topologies.
Recursive Projection-Free Identification with Binary-Valued Observations
This paper is concerned with parameter identification problem for finite impulse response (FIR) systems with binary-valued observations under low computational complexity.
BodyMetric: Evaluating the Realism of Human Bodies in Text-to-Image Generation
In particular, we use BodyMetric to benchmark the generation ability of text-to-image models to produce realistic human bodies.
Online Physics-Informed Dynamic Mode Decomposition: Theory and Applications
Leveraging the Bayesian DMD framework, we propose a probabilistic interpretation of Physics-informed DMD (piDMD), examining the impact of physical constraints on the DMD linear operator.
Dependency-Aware CAV Task Scheduling via Diffusion-Based Reinforcement Learning
To solve the problem, we further propose a diffusion-based reinforcement learning algorithm, named Synthetic DDQN based Subtasks Scheduling, which can make adaptive task scheduling decision in real time.
Fast High-Quality Enhanced Imaging Algorithm for Layered Dielectric Targets Based on MMW MIMO-SAR System
Millimeter-wave (MMW) multiple-input multiple-output synthetic aperture radar (MIMO-SAR) system is a technology that can achieve high resolution, high frame rate, and all-weather imaging and has received extensive attention in the non-destructive testing and internal imaging applications of layered dielectric targets.
High-Order Associative Learning Based on Memristive Circuits for Efficient Learning
Memristive associative learning has gained significant attention for its ability to mimic fundamental biological learning mechanisms while maintaining system simplicity.
COMET: Towards Partical W4A4KV4 LLMs Serving
We integrate the optimized W4Ax kernel into our inference framework, COMET, and provide efficient management to support popular LLMs such as LLaMA-3-70B.
A Survey of Low-shot Vision-Language Model Adaptation via Representer Theorem
As such, this survey paper first proposes a unified computational framework from the perspective of Representer Theorem and then derives many of the existing methods by specializing this framework.
Wavenumber-Domain Near-Field Channel Estimation: Beyond the Fresnel Bound
The lower bound of the Fresnel approximation imposes a constraint that becomes more pronounced as the array size grows.
SuperEncoder: Towards Universal Neural Approximate Quantum State Preparation
Numerous quantum algorithms operate under the assumption that classical data has already been converted into quantum states, a process termed Quantum State Preparation (QSP).
Natural language is not enough: Benchmarking multi-modal generative AI for Verilog generation
Natural language interfaces have exhibited considerable potential in the automation of Verilog generation derived from high-level specifications through the utilization of large language models, garnering significant attention.
Unifying Unsupervised Graph-Level Anomaly Detection and Out-of-Distribution Detection: A Benchmark
To bridge the gap, in this work, we present a Unified Benchmark for unsupervised Graph-level OOD and anomaly Detection (our method), a comprehensive evaluation framework that unifies GLAD and GLOD under the concept of generalized graph-level OOD detection.
Efficient Sharpness-Aware Minimization for Molecular Graph Transformer Models
Sharpness-aware minimization (SAM) has received increasing attention in computer vision since it can effectively eliminate the sharp local minima from the training trajectory and mitigate generalization degradation.
The Surprising Benefits of Base Rate Neglect in Robust Aggregation
We find that a certain degree of base rate neglect helps with robust forecast aggregation.
Understanding Auditory Evoked Brain Signal via Physics-informed Embedding Network with Multi-Task Transformer
Experiments on a specific dataset demonstrate PEMT-Net's significant performance in multi-task auditory signal decoding, surpassing existing methods and offering new insights into the brain's mechanisms for processing complex auditory information.
Genshin: General Shield for Natural Language Processing with Large Language Models
Large language models (LLMs) like ChatGPT, Gemini, or LLaMA have been trending recently, demonstrating considerable advancement and generalizability power in countless domains.
Balancing User Preferences by Social Networks: A Condition-Guided Social Recommendation Model for Mitigating Popularity Bias
More specifically, CGSoRec first includes a Condition-Guided Social Denoising Model (CSD) to remove redundant social relations in the social network for capturing users' social preferences with items more precisely.
Qsco: A Quantum Scoring Module for Open-set Supervised Anomaly Detection
Open set anomaly detection (OSAD) is a crucial task that aims to identify abnormal patterns or behaviors in data sets, especially when the anomalies observed during training do not represent all possible classes of anomalies.
Rethinking Independent Cross-Entropy Loss For Graph-Structured Data
We learn the joint distribution of node and cluster labels conditioned on their representations, and train GNNs with the obtained joint loss.
Progressive enhancement and restoration for mural images under low-light and defected conditions based on multi-receptive field strategy
To address the escalating damage to ancient murals and facilitate batch restoration at archaeological sites, we propose a two-stage restoration model with automatic defect area detection strategy which called MER(Mural Enhancement and Restoration net) for ancient murals that are damaged and have been captured in low light.
Channel Estimation for Holographic MIMO: Wavenumber-Domain Sparsity Inspired Approaches
This paper investigates the sparse channel estimation for holographic multiple-input multiple-output (HMIMO) systems.
Merging Parameter Estimation and Classification Using LASSO
Soft sensing is a way to indirectly obtain information of signals for which direct sensing is difficult or prohibitively expensive.
Grounded Compositional and Diverse Text-to-3D with Pretrained Multi-View Diffusion Model
In this paper, we propose an effective two-stage approach named Grounded-Dreamer to generate 3D assets that can accurately follow complex, compositional text prompts while achieving high fidelity by using a pre-trained multi-view diffusion model.
Adaptive tracking control for non-periodic reference signals under quantized observations
This paper considers an adaptive tracking control problem for stochastic regression systems with multi-threshold quantized observations.
Weak Distribution Detectors Lead to Stronger Generalizability of Vision-Language Prompt Tuning
The idea is realized by exploiting out-of-distribution (OOD) detection to predict whether a sample belongs to a base distribution or a novel distribution and then using the score generated by a dedicated competition based scoring function to fuse the zero-shot and few-shot classifier.
Compositional Kronecker Context Optimization for Vision-Language Models
Context Optimization (CoOp) has emerged as a simple yet effective technique for adapting CLIP-like vision-language models to downstream image recognition tasks.
Data is all you need: Finetuning LLMs for Chip Design via an Automated design-data augmentation framework
Our 13B model (ChipGPT-FT) has a pass rate improvement compared with GPT-3. 5 in Verilog generation and outperforms in EDA script (i. e., SiliconCompiler) generation with only 200 EDA script data.
Wavenumber Domain Sparse Channel Estimation in Holographic MIMO
In this paper, we investigate the sparse channel estimation in holographic multiple-input multiple-output (HMIMO) systems.
Multi-step Temporal Modeling for UAV Tracking
This module leverages temporal information to refresh the template feature, yielding a more precise correlation map.
Intensive Vision-guided Network for Radiology Report Generation
Given the above limitation in feature extraction, we propose a Globally-intensive Attention (GIA) module in the medical image encoder to simulate and integrate multi-view vision perception.
Quantum-Assisted Adaptive Beamforming in UASs Network: Enhancing Airborne Communication via Collaborative UASs for NextG IoT
Hovering creates significant beam path distortions, impacting the reliability and quality of distributed beamforming in airborne networks.
CIM-MLC: A Multi-level Compilation Stack for Computing-In-Memory Accelerators
Based on the proposed abstraction, CIM-MLC can compile tasks onto a wide range of CIM accelerators having different devices, architectures, and programming interfaces.
MetaSeg: Content-Aware Meta-Net for Omni-Supervised Semantic Segmentation
Noisy labels, inevitably existing in pseudo segmentation labels generated from weak object-level annotations, severely hampers model optimization for semantic segmentation.
Towards Auto-Modeling of Formal Verification for NextG Protocols: A Multimodal cross- and self-attention Large Language Model Approach
This paper introduces Auto-modeling of Formal Verification with Real-world Prompting for 5G and NextG protocols (AVRE), a novel system designed for the formal verification of Next Generation (NextG) communication protocols, addressing the increasing complexity and scalability challenges in network protocol design and verification.
Visual Explanations of Image-Text Representations via Multi-Modal Information Bottleneck Attribution
Vision-language pretrained models have seen remarkable success, but their application to safety-critical settings is limited by their lack of interpretability.
Cross-Layer Optimization for Fault-Tolerant Deep Learning
Fault-tolerant deep learning accelerator is the basis for highly reliable deep learning processing and critical to deploy deep learning in safety-critical applications such as avionics and robotics.
BACTrack: Building Appearance Collection for Aerial Tracking
At the same time, the appearance discriminator employs an online adaptive template-update strategy to ensure that the collected multiple templates remain reliable and diverse, allowing them to closely follow rapid changes in the target's appearance and suppress background interference during tracking.
LifelongMemory: Leveraging LLMs for Answering Queries in Long-form Egocentric Videos
In this paper we introduce LifelongMemory, a new framework for accessing long-form egocentric videographic memory through natural language question answering and retrieval.
Anonymous Jamming Detection in 5G with Bayesian Network Model Based Inference Analysis
To address this, an unsupervised auto-encoder-based anomaly detection is presented with an AUC of 0. 987.
Identification of morphological fingerprint in perinatal brains using quasi-conformal mapping and contrastive learning
The morphological fingerprint in the brain is capable of identifying the uniqueness of an individual.
Vital Signs Estimation Using a 26 GHz Multi-Beam Communication Testbed
The results show that the estimated breath rate and heart rate reach below 2 beats per minute (bpm) error compared to the reference captured by on-body sensor for the single-person monostatic sensing scenario with body-transceiver distance up to 2 m, and the two-person bistatic sensing scenario with BS-UE distance up to 4 m. The presented work does not optimize the OFDM waveform parameters for sensing; it demonstrates a promising JCAS proof-of-concept in contact-free vital sign monitoring using mmWave multi-beam communication systems.
Near-Field Sparse Channel Estimation for Extremely Large-Scale RIS-Aided Wireless Communications
To tackle this challenge, we exploit the sparsity inherent in the cascaded channel.
Improved Motor Imagery Classification Using Adaptive Spatial Filters Based on Particle Swarm Optimization Algorithm
The classification accuracy of the proposed method has reached 74. 61% and 81. 19% on datasets 2a and 2b, respectively.
CodeGen4Libs: A Two-Stage Approach for Library-Oriented Code Generation
To evaluate the effectiveness of our approach, we conduct extensive experiments on a dataset of 403, 780 data items.
Asymptotically Efficient Quasi-Newton Type Identification with Quantized Observations Under Bounded Persistent Excitations
This paper is concerned with the optimal identification problem of dynamical systems in which only quantized output observations are available under the assumption of fixed thresholds and bounded persistent excitations.
Federated Learning in Big Model Era: Domain-Specific Multimodal Large Models
Preliminary experiments show that enterprises can enhance and accumulate intelligent capabilities through multimodal model federated learning, thereby jointly creating an smart city model that provides high-quality intelligent services covering energy infrastructure safety, residential community security, and urban operation management.
A Survey on Fairness in Large Language Models
Large Language Models (LLMs) have shown powerful performance and development prospects and are widely deployed in the real world.
Exploring Winograd Convolution for Cost-effective Neural Network Fault Tolerance
When it is applied on fault-tolerant neural networks enhanced with fault-aware retraining and constrained activation functions, the resulting model accuracy generally shows significant improvement in presence of various faults.
From Ambiguity to Explicitness: NLP-Assisted 5G Specification Abstraction for Formal Analysis
Our work is proof of concept for an efficient procedure in performing formal analysis for largescale complicate specification and protocol analysis, especially for 5G and nextG communications.
Distributed 3D-Beam Reforming for Hovering-Tolerant UAVs Communication over Coexistence: A Deep-Q Learning for Intelligent Space-Air-Ground Integrated Networks
By augmenting the system with the impairments due to hovering and rotational motion, we show that the proposed DQN algorithm can reform the beam in real-time with negligible error.
Prompt Tuning Pushes Farther, Contrastive Learning Pulls Closer: A Two-Stage Approach to Mitigate Social Biases
Meanwhile, experimental results on the GLUE benchmark show that CCPA retains the language modeling capability of PLMs.
Interaction-Aware Planning With Deep Inverse Reinforcement Learning for Human-Like Autonomous Driving in Merge Scenarios
To consider the interaction factor, the reward function for planning is utilized to evaluate the joint trajectories of the autonomous driving vehicle (ADV) and traffic vehicles.
ChipGPT: How far are we from natural language hardware design
As large language models (LLMs) like ChatGPT exhibited unprecedented machine intelligence, it also shows great performance in assisting hardware engineers to realize higher-efficiency logic design via natural language interaction.
NLP-based Cross-Layer 5G Vulnerabilities Detection via Fuzzing Generated Run-Time Profiling
The effectiveness and efficiency of 5G software stack vulnerability and unintended behavior detection are essential for 5G assurance, especially for its applications in critical infrastructures.
Radar Altimeter Redesign for Multi-Stage Interference Risk Mitigation in 5G and Beyond
The radar altimeter is installed on most 14 CFR Pt 25 category aircraft, which are applicable to passenger travel and represent most airline traffic.
Location Tracking for Reconfigurable Intelligent Surfaces Aided Vehicle Platoons: Diverse Sparsities Inspired Approaches
In this paper, we investigate the employment of reconfigurable intelligent surfaces (RISs) into vehicle platoons, functioning in tandem with a base station (BS) in support of the high-precision location tracking.
Bayesian Inference-assisted Machine Learning for Near Real-Time Jamming Detection and Classification in 5G New Radio (NR)
The increased flexibility and density of spectrum access in 5G New Radio (NR) has made jamming detection and classification a critical research area.
AdPE: Adversarial Positional Embeddings for Pretraining Vision Transformers via MAE+
A criterion in unsupervised pretraining is the pretext task needs to be sufficiently hard to prevent the transformer encoder from learning trivial low-level features not generalizable well to downstream tasks.
Variation Enhanced Attacks Against RRAM-based Neuromorphic Computing System
The RRAM-based neuromorphic computing system has amassed explosive interests for its superior data processing capability and energy efficiency than traditional architectures, and thus being widely used in many data-centric applications.
Recursive Identification of Set-Valued Systems under Uniform Persistent Excitations
This paper studies the control-oriented identification problem of set-valued moving average systems with uniform persistent excitations and observation noises.
A Node-collaboration-informed Graph Convolutional Network for Precise Representation to Undirected Weighted Graphs
Based on this idea, a Node-collaboration-informed Graph Convolutional Network (NGCN) is proposed with three-fold ideas: a) Learning latent collaborative information from the interaction of node pairs via a node-collaboration module; b) Building the residual connection and weighted representation propagation to obtain high representation capacity; and c) Implementing the model optimization in an end-to-end fashion to achieve precise representation to the target UWG.
Representation Learning for Continuous Action Spaces is Beneficial for Efficient Policy Learning
Meanwhile, we divide the whole learning task into learning with the large-scale representation models in an unsupervised manner and learning with the small-scale policy model in the RL manner. The small policy model facilitates policy learning, while not sacrificing generalization and expressiveness via the large representation model.
Dynamic Loss For Robust Learning
Label noise and class imbalance commonly coexist in real-world data.
Ranked #6 on
Learning with noisy labels
on ANIMAL
Sybil-Proof Diffusion Auction in Social Networks
A diffusion auction is a market to sell commodities over a social network, where the challenge is to incentivize existing buyers to invite their neighbors in the network to join the market.
Balancing Utility and Fairness in Submodular Maximization (Technical Report)
Submodular function maximization is a fundamental combinatorial optimization problem with plenty of applications -- including data summarization, influence maximization, and recommendation.
Statistical Modeling of Soft Error Influence on Neural Networks
Prior work mainly rely on fault simulation to analyze the influence of soft errors on NN processing.
Prompt Tuning with Soft Context Sharing for Vision-Language Models
Inspired by the fact that modeling task relationship by multi-task learning can usually boost performance, we propose a novel method SoftCPT (Soft Context Sharing for Prompt Tuning) to tune pre-trained vision-language models on multiple target few-shot tasks jointly.
Real-Time Robust Video Object Detection System Against Physical-World Adversarial Attacks
This work proposes Themis, a software/hardware system to defend against adversarial patches for real-time robust video object detection.
Traffic Analytics Development Kits (TADK): Enable Real-Time AI Inference in Networking Apps
Sophisticated traffic analytics, such as the encrypted traffic analytics and unknown malware detection, emphasizes the need for advanced methods to analyze the network traffic.
GPPT: Graph Pre-training and Prompt Tuning to Generalize Graph Neural Networks
Based on the pre-trained model, we propose the graph prompting function to modify the standalone node into a token pair, and reformulate the downstream node classification looking the same as edge prediction.
DS-MVSNet: Unsupervised Multi-view Stereo via Depth Synthesis
To mine the information in probability volume, we creatively synthesize the source depths by splattering the probability volume and depth hypotheses to source views.
Inverted Semantic-Index for Image Retrieval
We then propose a merging and splitting method to solve the problem that the number of partitions is unchangeable in the inverted semantic-index.
HoVer-Trans: Anatomy-aware HoVer-Transformer for ROI-free Breast Cancer Diagnosis in Ultrasound Images
In this study, we propose a novel ROI-free model for breast cancer diagnosis in ultrasound images with interpretable feature representations.
FKreg: A MATLAB toolbox for fast Multivariate Kernel Regression
Kernel smooth is the most fundamental technique for data density and regression estimation.
Reconfigurable Intelligent Surface (RIS)-aided Vehicular Networks: Their Protocols, Resource Allocation, and Performance
Reconfigurable intelligent surfaces (RISs) assist in paving the way for the evolution of conventional vehicular networks to autonomous driving.
Resilience-Motivated Distribution System Restoration Considering Electricity-Water-Gas Interdependency
In this paper, a distribution system service restoration method considering the electricity-water-gas interdependency is proposed.
Winograd Convolution: A Perspective from Fault Tolerance
Winograd convolution is originally proposed to reduce the computing overhead by converting multiplication in neural network (NN) with addition via linear transformation.
Dual-Flattening Transformers through Decomposed Row and Column Queries for Semantic Segmentation
We propose a Dual-Flattening Transformer (DFlatFormer) to enable high-resolution output by reducing complexity to $\mathcal{O}(hw(H+W))$ that is multiple orders of magnitude smaller than the naive dense transformer.
DDU-Net: Dual-Decoder-U-Net for Road Extraction Using High-Resolution Remote Sensing Images
Extracting roads from high-resolution remote sensing images (HRSIs) is vital in a wide variety of applications, such as autonomous driving, path planning, and road navigation.
Delving into Sample Loss Curve to Embrace Noisy and Imbalanced Data
In practice, however, biased samples with corrupted labels and of tailed classes commonly co-exist in training data.
ACDNet: Adaptively Combined Dilated Convolution for Monocular Panorama Depth Estimation
Depth estimation is a crucial step for 3D reconstruction with panorama images in recent years.
Ranked #5 on
Depth Estimation
on Stanford2D3D Panoramic
Hard Sample Aware Noise Robust Learning for Histopathology Image Classification
In this work, we introduce a novel hard sample aware noise robust learning method for histopathology image classification.
Ranked #1 on
Learning with noisy labels
on Chaoyang
Predicting Axillary Lymph Node Metastasis in Early Breast Cancer Using Deep Learning on Primary Tumor Biopsy Slides
Conclusion: Our study provides a novel DL-based biomarker on primary tumor CNB slides to predict the metastatic status of ALN preoperatively for patients with EBC.
Total-Body Low-Dose CT Image Denoising using Prior Knowledge Transfer Technique with Contrastive Regularization Mechanism
The derived architecture is referred to as the Teacher-Student Consistency Network (TSC-Net), which consists of the teacher network and the student network with identical architecture.
PAPooling: Graph-based Position Adaptive Aggregation of Local Geometry in Point Clouds
Fine-grained geometry, captured by aggregation of point features in local regions, is crucial for object recognition and scene understanding in point clouds.
Perceptual Consistency in Video Segmentation
More specifically, by measuring the perceptual consistency between the predicted segmentation and the available ground truth on a nearby frame and combining it with the segmentation confidence, we can accurately assess the classification correctness on each pixel.
Pyramid Correlation based Deep Hough Voting for Visual Object Tracking
Through experiments we find that, without regression, the performance could be equally promising as long as we delicately design the network to suit the training objective.
On the Scheduling Policy for Multi-process WNCS under Edge Computing
The monotonicity of the value function in MDP is characterized and then used to show the threshold structure properties of the optimal scheduling policy.
A Semantic Indexing Structure for Image Retrieval
In large-scale image retrieval, many indexing methods have been proposed to narrow down the searching scope of retrieval.
R2F: A Remote Retraining Framework for AIoT Processors with Computing Errors
It takes the remote AIoT processor with soft errors in the training loop such that the on-site computing errors can be learned with the application data on the server and the retrained models can be resilient to the soft errors.
HAN: An Efficient Hierarchical Self-Attention Network for Skeleton-Based Gesture Recognition
Previous methods for skeleton-based gesture recognition mostly arrange the skeleton sequence into a pseudo picture or spatial-temporal graph and apply deep Convolutional Neural Network (CNN) or Graph Convolutional Network (GCN) for feature extraction.
InverseForm: A Loss Function for Structured Boundary-Aware Segmentation
We present a novel boundary-aware loss term for semantic segmentation using an inverse-transformation network, which efficiently learns the degree of parametric transformations between estimated and target boundaries.
Ranked #5 on
Semantic Segmentation
on Cityscapes test
Damage accumulation during high temperature fatigue of Ti/SiC$_f$ metal matrix composites under different stress amplitudes
The three-dimensional morphology of the crack and fibre fractures has been mapped by CT. During stable growth, matrix cracking dominates with the crack deflecting (by 50-100 $\mu$m in height) when bypassing bridging fibres.
Computed Tomography (CT)
X-Ray Diffraction (XRD)
Materials Science
Applied Physics
Hero: On the Chaos When PATH Meets Modules
The results showed that \textsc{Hero} achieved a high detection rate of 98. 5\% on a DM issue benchmark and found 2, 422 new DM issues in 2, 356 popular Golang projects.
Software Engineering
Electroabsorption in gated GaAs nanophotonic waveguides
We report on the analysis of electroabsorption in thin GaAs/Al$_{0. 3}$Ga$_{0. 7}$As nanophotonic waveguides with an embedded $p$-$i$-$n$ junction.
Optics Materials Science Quantum Physics
Knowledge Mining and Transferring for Domain Adaptive Object Detection
Specifically, KTNet is constructed on a base detector with intrinsic knowledge mining and relational knowledge constraints.
Can Scale-Consistent Monocular Depth Be Learned in a Self-Supervised Scale-Invariant Manner?
The integration of SAG loss and two-stream network enables more consistent scale inference and more accurate relative depth estimation.
SWA Object Detection
In this technique report, we systematically investigate the effects of applying SWA to object detection as well as instance segmentation.
Characterizing and Detecting Freezing of Gait using Multi-modal Physiological Signals
Features significantly associated with freezing episodes were ranked and used for the freezing detection.
VC-Net: Deep Volume-Composition Networks for Segmentation and Visualization of Highly Sparse and Noisy Image Data
A multi-stream convolutional neural network is proposed to learn the 3D volume and 2D MIP features respectively and then explore their inter-dependencies in a joint volume-composition embedding space by unprojecting the MIP features into 3D volume embedding space.
VarifocalNet: An IoU-aware Dense Object Detector
In this paper, we propose to learn an Iou-aware Classification Score (IACS) as a joint representation of object presence confidence and localization accuracy.
Ranked #24 on
Object Detection
on COCO-O
Automatic Speech Summarisation: A Scoping Review
We also discuss the strengths and weaknesses of these different methods and speech features.
Differentiable Joint Pruning and Quantization for Hardware Efficiency
We present a differentiable joint pruning and quantization (DJPQ) scheme.
Multi-level colonoscopy malignant tissue detection with adversarial CAC-UNet
The automatic and objective medical diagnostic model can be valuable to achieve early cancer detection, and thus reducing the mortality rate.
Ranked #1 on
Tumor Segmentation
on DigestPath
You Only Search Once: A Fast Automation Framework for Single-Stage DNN/Accelerator Co-design
DNN/Accelerator co-design has shown great potential in improving QoR and performance.
Bayesian Bits: Unifying Quantization and Pruning
We introduce Bayesian Bits, a practical method for joint mixed precision quantization and pruning through gradient based optimization.
Linear Symmetric Quantization of Neural Networks for Low-precision Integer Hardware
With the proliferation of specialized neural network processors that operate on low-precision integers, the performance of Deep Neural Network inference becomes increasingly dependent on the result of quantization.
Combining GHOST and Casper
We present "Gasper," a proof-of-stake-based consensus protocol, which is an idealized version of the proposed Ethereum 2. 0 beacon chain.
Cryptography and Security 68W15
An Iterative Heuristic Method to Determine Radial Topology for Distribution System Restoration
The case studies indicate that the proposed method can determine radial topology in a few seconds and ensure the restoration capacity.
LiDAR Iris for Loop-Closure Detection
In this paper, a global descriptor for a LiDAR point cloud, called LiDAR Iris, is proposed for fast and accurate loop-closure detection.
Breast Anatomy Enriched Tumor Saliency Estimation
Then we refine the layers by integrating a non-semantic breast anatomy model to solve the problems of incomplete mammary layers.
Accelerating Generative Neural Networks on Unmodified Deep Learning Processors -- A Software Approach
Generative neural network is a new category of neural networks and it has been widely utilized in applications such as content generation, unsupervised learning, segmentation and pose estimation.
Refined-Segmentation R-CNN: A Two-stage Convolutional Neural Network for Punctate White Matter Lesion Segmentation in Preterm Infants
In this paper, we construct an efficient two-stage PWML semantic segmentation network based on the characteristics of the lesion, called refined segmentation R-CNN (RS RCNN).
Tumor Saliency Estimation for Breast Ultrasound Images via Breast Anatomy Modeling
First, we model breast anatomy and decompose breast ultrasound image into layers using Neutro-Connectedness; then utilize the layers to generate the foreground and background maps; and finally propose a novel objective function to estimate the tumor saliency by integrating the foreground map, background map, adaptive center bias, and region-based correlation cues.
Neural Response Generation with Meta-Words
We present open domain response generation with meta-words.
Inpatient2Vec: Medical Representation Learning for Inpatients
In addition, for unordered medical activity set, existing medical RL methods utilize a simple pooling strategy, which would result in indistinguishable contributions among the activities for learning.
A Hybrid Framework for Tumor Saliency Estimation
Automatic tumor segmentation of breast ultrasound (BUS) image is quite challenging due to the complicated anatomic structure of breast and poor image quality.
BUSIS: A Benchmark for Breast Ultrasound Image Segmentation
Breast ultrasound (BUS) image segmentation is challenging and critical for BUS Comput-er-Aided Diagnosis (CAD) systems.
Review. Machine learning techniques for traffic sign detection
An automatic road sign detection system localizes road signs from within images captured by an on-board camera of a vehicle, and support the driver to properly ride the vehicle.
Restricting Greed in Training of Generative Adversarial Network
Generative adversarial network (GAN) has gotten wide re-search interest in the field of deep learning.
10,000+ Times Accelerated Robust Subset Selection (ARSS)
Subset selection from massive data with noised information is increasingly popular for various applications.
Effective Spectral Unmixing via Robust Representation and Learning-based Sparsity
Based on this observation, we exploit a learning-based sparsity method to simultaneously learn the HU results and a sparse guidance map.
Active Flattening of Curved Document Images via Two Structured Beams
Document images captured by a digital camera often suffer from serious geometric distortions.
Structured Sparse Method for Hyperspectral Unmixing
With this constraint, our method can learn a compact space, where highly similar pixels are grouped to share correlated sparse representations.
Spectral Unmixing via Data-guided Sparsity
Hyperspectral unmixing, the process of estimating a common set of spectral bases and their corresponding composite percentages at each pixel, is an important task for hyperspectral analysis, visualization and understanding.
Robust Hyperspectral Unmixing with Correntropy based Metric
In addition, with sparsity constraints, our model can naturally generate sparse abundances.
