Search Results for author:
Found 144 papers, 43 papers with code
LatticeNet: Towards Lightweight Image Super-resolution with Lattice Block
Drawing lessons from lattice filter bank, we design the lattice block (LB) in which two butterfly structures are applied to combine two RBs.
Boosting Deep Neural Network Efficiency with Dual-Module Inference
Using Deep Neural Networks (DNNs) in machine learning tasks is promising in delivering high-quality results but challenging to meet stringent latency requirements and energy constraints because of the memory-bound and the compute-bound execution pattern of DNNs.
PromptAD: Learning Prompts with only Normal Samples for Few-Shot Anomaly Detection
The vision-language model has brought great improvement to few-shot industrial anomaly detection, which usually needs to design of hundreds of prompts through prompt engineering.
DEMOS: Dynamic Environment Motion Synthesis in 3D Scenes via Local Spherical-BEV Perception
To handle this problem, we propose the first Dynamic Environment MOtion Synthesis framework (DEMOS) to predict future motion instantly according to the current scene, and use it to dynamically update the latent motion for final motion synthesis.
Progressive Contrastive Learning with Multi-Prototype for Unsupervised Visible-Infrared Person Re-identification
To address the problem, we propose a Progressive Contrastive Learning with Multi-Prototype (PCLMP) method for USVI-ReID.
Multi-Memory Matching for Unsupervised Visible-Infrared Person Re-Identification
To associate cross-modality clustered pseudo-labels, we design a Multi-Memory Learning and Matching (MMLM) module, ensuring that optimization explicitly focuses on the nuances of individual perspectives and establishes reliable cross-modality correspondences.
CLIP-guided Federated Learning on Heterogeneous and Long-Tailed Data
For server-side learning, in order to mitigate the heterogeneity and class-distribution imbalance, we generate federated features to retrain the server model.
Beyond the Label Itself: Latent Labels Enhance Semi-supervised Point Cloud Panoptic Segmentation
Second, in the Image Branch, we propose the Instance Position-scale Learning (IPSL) Module to learn and fuse the information of instance position and scale, which is from a 2D pre-trained detector and a type of latent label obtained from 3D to 2D projection.
COTR: Compact Occupancy TRansformer for Vision-based 3D Occupancy Prediction
The autonomous driving community has shown significant interest in 3D occupancy prediction, driven by its exceptional geometric perception and general object recognition capabilities.
Multi-modal In-Context Learning Makes an Ego-evolving Scene Text Recognizer
A straightforward solution is performing model fine-tuning tailored to a specific scenario, but it is computationally intensive and requires multiple model copies for various scenarios.
Generalized Category Discovery in Semantic Segmentation
This paper explores a novel setting called Generalized Category Discovery in Semantic Segmentation (GCDSS), aiming to segment unlabeled images given prior knowledge from a labeled set of base classes.
LiDAR-Camera Panoptic Segmentation via Geometry-Consistent and Semantic-Aware Alignment
3D panoptic segmentation is a challenging perception task that requires both semantic segmentation and instance segmentation.
Underwater Acoustic Target Recognition based on Smoothness-inducing Regularization and Spectrogram-based Data Augmentation
Underwater acoustic target recognition is a challenging task owing to the intricate underwater environments and limited data availability.
Underwater-Art: Expanding Information Perspectives With Text Templates For Underwater Acoustic Target Recognition
In our work, we propose to implement Underwater Acoustic Recognition based on Templates made up of rich relevant information (hereinafter called "UART").
Learning Music Sequence Representation from Text Supervision
Music representation learning is notoriously difficult for its complex human-related concepts contained in the sequence of numerical signals.
Adaptive ship-radiated noise recognition with learnable fine-grained wavelet transform
Background noise and variable channel transmission environment make it complicated to implement accurate ship-radiated noise recognition.
Advancing underwater acoustic target recognition via adaptive data pruning and smoothness-inducing regularization
Underwater acoustic recognition for ship-radiated signals has high practical application value due to the ability to recognize non-line-of-sight targets.
NPS: A Framework for Accurate Program Sampling Using Graph Neural Network
Furthermore, NPS shows higher accuracy and generality than the state-of-the-art GNN approach in code behavior learning, enabling the generation of high-quality execution embeddings.
SpatialFormer: Semantic and Target Aware Attentions for Few-Shot Learning
Then we derive two specific attention modules, named SpatialFormer Semantic Attention (SFSA) and SpatialFormer Target Attention (SFTA), to enhance the target object regions while reduce the background distraction.
High-Resolution GAN Inversion for Degraded Images in Large Diverse Datasets
A generic method for generating a high-quality image from the degraded one is in demand.
Instance and Category Supervision are Alternate Learners for Continual Learning
Continual Learning (CL) is the constant development of complex behaviors by building upon previously acquired skills.
Rethinking Gradient Projection Continual Learning: Stability / Plasticity Feature Space Decoupling
In this paper, we propose a space decoupling (SD) algorithm to decouple the feature space into a pair of complementary subspaces, i. e., the stability space I, and the plasticity space R. I is established by conducting space intersection between the historic and current feature space, and thus I contains more task-shared bases.
Memory-Friendly Scalable Super-Resolution via Rewinding Lottery Ticket Hypothesis
In the forward stage, we take advantage of LTH with rewinding weights to progressively shrink the SR model and the pruning-out masks that form nested sets.
Multi-Centroid Task Descriptor for Dynamic Class Incremental Inference
As a result, our dynamic inference network is trained independently of baseline and provides a flexible, efficient solution to distinguish between tasks.
Dual Pseudo-Labels Interactive Self-Training for Semi-Supervised Visible-Infrared Person Re-Identification
Visible-infrared person re-identification (VI-ReID) aims to match a specific person from a gallery of images captured from non-overlapping visible and infrared cameras.
Weakly Supervised Semantic Segmentation for Large-Scale Point Cloud
Firstly, we construct a pretext task, \textit{i. e.,} point cloud colorization, with a self-supervised learning to transfer the learned prior knowledge from a large amount of unlabeled point cloud to a weakly supervised network.
Global Meets Local: Effective Multi-Label Image Classification via Category-Aware Weak Supervision
This paper builds a unified framework to perform effective noisy-proposal suppression and to interact between global and local features for robust feature learning.
AdaTriplet-RA: Domain Matching via Adaptive Triplet and Reinforced Attention for Unsupervised Domain Adaptation
Unsupervised domain adaption (UDA) is a transfer learning task where the data and annotations of the source domain are available but only have access to the unlabeled target data during training.
Transforming RIS-Assisted Passive Beamforming from Tedious to Simple: A Relaxation Algorithm for Rician Channel
This paper investigates the problem of maximizing the signal-to-noise ratio (SNR) in reconfigurable intelligent surface (RIS)-assisted MISO communication systems.
A Comprehensive Survey on Distributed Training of Graph Neural Networks
This situation poses a considerable challenge for newcomers, hindering their ability to grasp a comprehensive understanding of the workflows, computational patterns, communication strategies, and optimization techniques employed in distributed GNN training.
Rethinking the Metric in Few-shot Learning: From an Adaptive Multi-Distance Perspective
In this paper, for the first time, we investigate the contributions of different distance metrics, and propose an adaptive fusion scheme, bringing significant improvements in few-shot classification.
Faith: An Efficient Framework for Transformer Verification on GPUs
In this paper, we propose Faith, an efficient framework for transformer verification on GPUs.
Image Understands Point Cloud: Weakly Supervised 3D Semantic Segmentation via Association Learning
In this paper, we propose a novel cross-modality weakly supervised method for 3D segmentation, incorporating complementary information from unlabeled images.
Prototype-Aware Heterogeneous Task for Point Cloud Completion
Moreover, for effective training, we consider difficulty-based sampling strategy to encourage the network to pay more attention to some partial point clouds with fewer geometric information.
Attentive pooling for Group Activity Recognition
However, the existing methods simply employed max/average pooling in this framework, which ignored the distinct contributions of different individuals to the group activity recognition.
Boosting Night-time Scene Parsing with Learnable Frequency
Based on this, we propose to exploit the image frequency distributions for night-time scene parsing.
MILAN: Masked Image Pretraining on Language Assisted Representation
When the masked autoencoder is pretrained and finetuned on ImageNet-1K dataset with an input resolution of 224x224, MILAN achieves a top-1 accuracy of 85. 4% on ViT-Base, surpassing previous state-of-the-arts by 1%.
Predicting the Output Structure of Sparse Matrix Multiplication with Sampled Compression Ratio
We also propose a reference design of the existing sampling-based method with optimized computing overheads to demonstrate the better accuracy of the proposed method.
MoEC: Mixture of Expert Clusters
Sparsely Mixture of Experts (MoE) has received great interest due to its promising scaling capability with affordable computational overhead.
Variational Distillation for Multi-View Learning
Information Bottleneck (IB) based multi-view learning provides an information theoretic principle for seeking shared information contained in heterogeneous data descriptions.
The Spike Gating Flow: A Hierarchical Structure Based Spiking Neural Network for Online Gesture Recognition
At last, we conclude the few-shot learning paradigm of the developed network: 1) a hierarchical structure-based network design involves human prior knowledge; 2) SNNs for content based global dynamic feature detection.
Task-Specific Expert Pruning for Sparse Mixture-of-Experts
The sparse Mixture-of-Experts (MoE) model is powerful for large-scale pre-training and has achieved promising results due to its model capacity.
NTIRE 2022 Challenge on Efficient Super-Resolution: Methods and Results
The aim was to design a network for single image super-resolution that achieved improvement of efficiency measured according to several metrics including runtime, parameters, FLOPs, activations, and memory consumption while at least maintaining the PSNR of 29. 00dB on DIV2K validation set.
Toward Robust Spiking Neural Network Against Adversarial Perturbation
To the best of our knowledge, this is the first analysis on robust training of SNNs.
LAKe-Net: Topology-Aware Point Cloud Completion by Localizing Aligned Keypoints
An asymmetric keypoint locator, including an unsupervised multi-scale keypoint detector and a complete keypoint generator, is proposed for localizing aligned keypoints from complete and partial point clouds.
CHEX: CHannel EXploration for CNN Model Compression
However, conventional pruning methods have limitations in that: they are restricted to pruning process only, and they require a fully pre-trained large model.
Dynamic N:M Fine-grained Structured Sparse Attention Mechanism
We evaluate the 1:2 and 2:4 sparsity under different configurations and achieve 1. 27~ 1. 89x speedups over the full-attention mechanism.
Survey on Graph Neural Network Acceleration: An Algorithmic Perspective
Next, we provide comparisons from aspects of the efficiency and characteristics of these methods.
LOSTIN: Logic Optimization via Spatio-Temporal Information with Hybrid Graph Models
Despite the stride made by machine learning (ML) based performance modeling, two major concerns that may impede production-ready ML applications in EDA are stringent accuracy requirements and generalization capability.
High-Level Synthesis Performance Prediction using GNNs: Benchmarking, Modeling, and Advancing
The contribution of this work is three-fold.
HybridCR: Weakly-Supervised 3D Point Cloud Semantic Segmentation via Hybrid Contrastive Regularization
To address the huge labeling cost in large-scale point cloud semantic segmentation, we propose a novel hybrid contrastive regularization (HybridCR) framework in weakly-supervised setting, which obtains competitive performance compared to its fully-supervised counterpart.
En-Compactness: Self-Distillation Embedding & Contrastive Generation for Generalized Zero-Shot Learning
Our ICCE promotes intra-class compactness with inter-class separability on both seen and unseen classes in the embedding space and visual feature space.
Compact Multi-level Sparse Neural Networks with Input Independent Dynamic Rerouting
Deep neural networks (DNNs) have shown to provide superb performance in many real life applications, but their large computation cost and storage requirement have prevented them from being deployed to many edge and internet-of-things (IoT) devices.
Structured Semantic Transfer for Multi-Label Recognition with Partial Labels
To reduce the annotation cost, we propose a structured semantic transfer (SST) framework that enables training multi-label recognition models with partial labels, i. e., merely some labels are known while other labels are missing (also called unknown labels) per image.
Load-balanced Gather-scatter Patterns for Sparse Deep Neural Networks
Our experiments show that GS patterns consistently make better trade-offs between accuracy and computation efficiency compared to conventional structured sparse patterns.
Towards Efficient Ansatz Architecture for Variational Quantum Algorithms
In this paper, we propose a novel training scheme to mitigate such noise-induced gradient vanishing.
Exploring Versatile Prior for Human Motion via Motion Frequency Guidance
Prior plays an important role in providing the plausible constraint on human motion.
Mitigating Noise-Induced Gradient Vanishing in Variational Quantum Algorithm Training
In this paper, we propose a novel training scheme to mitigate such noise-induced gradient vanishing.
Transformer Acceleration with Dynamic Sparse Attention
We demonstrate that the sparse patterns are dynamic, depending on input sequences.
Understanding GNN Computational Graph: A Coordinated Computation, IO, and Memory Perspective
The same data are propagated through the graph structure to perform the same neural operation multiple times in GNNs, leading to redundant computation which accounts for 92. 4% of total operators.
DFSSATTEN: Dynamic Fine-grained Structured Sparse Attention Mechanism
Transformers are becoming mainstream solutions for various tasks like NLP and Computer vision.
Self-supervised Models are Good Teaching Assistants for Vision Transformers
These findings motivate us to introduce an self-supervised teaching assistant (SSTA) besides the commonly used supervised teacher to improve the performance of transformers.
Program-to-Circuit: Exploiting GNNs for Program Representation and Circuit Translation
Pioneering in this direction, we expect more GNN endeavors to revolutionize this high-demand Program-to-Circuit problem and to enrich the expressiveness of GNNs on programs.
H2Learn: High-Efficiency Learning Accelerator for High-Accuracy Spiking Neural Networks
Although spiking neural networks (SNNs) take benefits from the bio-plausible neural modeling, the low accuracy under the common local synaptic plasticity learning rules limits their application in many practical tasks.
Dual Reweighting Domain Generalization for Face Presentation Attack Detection
Face anti-spoofing approaches based on domain generalization (DG) have drawn growing attention due to their robustness for unseen scenarios.
Novelty Detection via Contrastive Learning with Negative Data Augmentation
Moreover, our model is more stable for training in a non-adversarial manner, compared to other adversarial based novelty detection methods.
Effective Model Sparsification by Scheduled Grow-and-Prune Methods
It addresses the shortcomings of the previous works by repeatedly growing a subset of layers to dense and then pruning them back to sparse after some training.
Towards Compact Single Image Super-Resolution via Contrastive Self-distillation
Convolutional neural networks (CNNs) are highly successful for super-resolution (SR) but often require sophisticated architectures with heavy memory cost and computational overhead, significantly restricts their practical deployments on resource-limited devices.
Omni-supervised Point Cloud Segmentation via Gradual Receptive Field Component Reasoning
Our method can significantly improve the backbones in all three datasets.
Ranked #2 on
Semantic Segmentation
on Semantic3D
Discrete-continuous Action Space Policy Gradient-based Attention for Image-Text Matching
We propose a novel attention scheme which projects the image and text embedding into a common space and optimises the attention weights directly towards the evaluation metrics.
Contrastive Learning for Compact Single Image Dehazing
In this paper, we propose a novel contrastive regularization (CR) built upon contrastive learning to exploit both the information of hazy images and clear images as negative and positive samples, respectively.
Ranked #5 on
Image Dehazing
on RS-Haze
Farewell to Mutual Information: Variational Distillation for Cross-Modal Person Re-Identification
The Information Bottleneck (IB) provides an information theoretic principle for representation learning, by retaining all information relevant for predicting label while minimizing the redundancy.
Cross-Modality Person Re-identification
Cross-Modal Person Re-Identification
+3
Roles of the Narrow Electronic Band near the Fermi Level in 1$T$-TaS$_2$-Related Layered Materials
4$H_{\rm b}$-TaS$_2$ is a superconducting compound with alternating 1$T$-TaS$_2$ and 1$H$-TaS$_2$ layers, where the 1$H$-TaS$_2$ layer has weak charge density wave (CDW) pattern and reduces the CDW coupling between the adjacent 1$T$-TaS$_2$ layers.
Mesoscale and Nanoscale Physics Materials Science
MPU: Towards Bandwidth-abundant SIMT Processor via Near-bank Computing
For general purpose scenarios, lightweight hardware designs for diverse data paths, architectural supports for the SIMT programming model, and end-to-end software optimizations remain challenging.
Hardware Architecture
A Case for 3D Integrated System Design for Neuromorphic Computing & AI Applications
Over the last decade, artificial intelligence has found many applications areas in the society.
A Survey of Machine Learning for Computer Architecture and Systems
Then, we summarize the common problems in computer architecture/system design that can be solved by ML techniques, and the typical ML techniques employed to resolve each of them.
IronMan: GNN-assisted Design Space Exploration in High-Level Synthesis via Reinforcement Learning
Despite the great success of High-Level Synthesis (HLS) tools, we observe several unresolved challenges: 1) the high-level abstraction of programming styles in HLS sometimes conceals optimization opportunities; 2) existing HLS tools do not provide flexible trade-off (Pareto) solutions among different objectives and constraints; 3) the actual quality of the resulting RTL designs is hard to predict.
Learn from Concepts: Towards the Purified Memory for Few-shot Learning
In this paper, we present a novel purified memory mechanism that simulates the recognition process of human beings.
Boundary-Aware Geometric Encoding for Semantic Segmentation of Point Clouds
Boundary information plays a significant role in 2D image segmentation, while usually being ignored in 3D point cloud segmentation where ambiguous features might be generated in feature extraction, leading to misclassification in the transition area between two objects.
Perturbed Self-Distillation: Weakly Supervised Large-Scale Point Cloud Semantic Segmentation
In this way, the graph topology of the whole point cloud can be effectively established by the introduced auxiliary supervision, such that the information propagation between the labeled and unlabeled points will be realized.
Redefining Self-Normalization Property
Moreover, analysis on the activation's mean in the forward pass reveals that the self-normalization property gets weaker with larger fan-in of each layer, which explains the performance degradation on large benchmarks like ImageNet.
AU-Expression Knowledge Constrained Representation Learning for Facial Expression Recognition
In this work, we explore the correlations among the action units and facial expressions, and devise an AU-Expression Knowledge Constrained Representation Learning (AUE-CRL) framework to learn the AU representations without AU annotations and adaptively use representations to facilitate facial expression recognition.
Facial Expression Recognition
Facial Expression Recognition (FER)
+1
Training and Inference for Integer-Based Semantic Segmentation Network
However, neural network quantization can be used to reduce computation load while maintaining comparable accuracy and original network structure.
Rubik: A Hierarchical Architecture for Efficient Graph Learning
Graph convolutional network (GCN) emerges as a promising direction to learn the inductive representation in graph data commonly used in widespread applications, such as E-commerce, social networks, and knowledge graphs.
Hardware Architecture
Cross-Domain Facial Expression Recognition: A Unified Evaluation Benchmark and Adversarial Graph Learning
Although each declares to achieve superior performance, fair comparisons are lacking due to the inconsistent choices of the source/target datasets and feature extractors.
Ranked #1 on
Cross-Domain Facial Expression Recognition
on Source: AFE, Target: CK+, JAFFE, SFEW2.0, FER2013, ExpW
Cross-Domain Facial Expression Recognition
Domain Adaptation
+3
Adversarial Graph Representation Adaptation for Cross-Domain Facial Expression Recognition
However, most of these works focus on holistic feature adaptation, and they ignore local features that are more transferable across different datasets.
Cross-Domain Facial Expression Recognition
Facial Expression Recognition (FER)
Brain Tumor Anomaly Detection via Latent Regularized Adversarial Network
The brain structure in the collected data is complicated, thence, doctors are required to spend plentiful energy when diagnosing brain abnormalities.
Semi-supervised Anomaly Detection
Supervised Anomaly Detection
GNNAdvisor: An Adaptive and Efficient Runtime System for GNN Acceleration on GPUs
As the emerging trend of graph-based deep learning, Graph Neural Networks (GNNs) excel for their capability to generate high-quality node feature vectors (embeddings).
Distributed, Parallel, and Cluster Computing
SmartExchange: Trading Higher-cost Memory Storage/Access for Lower-cost Computation
We present SmartExchange, an algorithm-hardware co-design framework to trade higher-cost memory storage/access for lower-cost computation, for energy-efficient inference of deep neural networks (DNNs).
NTIRE 2020 Challenge on NonHomogeneous Dehazing
We focus on the proposed solutions and their results evaluated on NH-Haze, a novel dataset consisting of 55 pairs of real haze free and nonhomogeneous hazy images recorded outdoor.
NTIRE 2020 Challenge on Image Demoireing: Methods and Results
Track 1 targeted the single image demoireing problem, which seeks to remove moire patterns from a single image.
TIMELY: Pushing Data Movements and Interfaces in PIM Accelerators Towards Local and in Time Domain
Resistive-random-access-memory (ReRAM) based processing-in-memory (R$^2$PIM) accelerators show promise in bridging the gap between Internet of Thing devices' constrained resources and Convolutional/Deep Neural Networks' (CNNs/DNNs') prohibitive energy cost.
Comparing SNNs and RNNs on Neuromorphic Vision Datasets: Similarities and Differences
Neuromorphic data, recording frameless spike events, have attracted considerable attention for the spatiotemporal information components and the event-driven processing fashion.
Ranked #11 on
Gesture Recognition
on DVS128 Gesture
Computation on Sparse Neural Networks: an Inspiration for Future Hardware
We show that for practically complicated problems, it is more beneficial to search large and sparse models in the weight dominated region.
Meta Segmentation Network for Ultra-Resolution Medical Images
MSN can fast generate the weights of fusion layers through a simple meta-learner, requiring only a few training samples and epochs to converge.
Anomaly Detection by One Class Latent Regularized Networks
Anomaly detection is a fundamental problem in computer vision area with many real-world applications.
Acoustic anomaly detection via latent regularized gaussian mixture generative adversarial networks
Acoustic anomaly detection aims at distinguishing abnormal acoustic signals from the normal ones.
Novelty Detection via Non-Adversarial Generative Network
One-class novelty detection is the process of determining if a query example differs from the training examples (the target class).
SceneEncoder: Scene-Aware Semantic Segmentation of Point Clouds with A Learnable Scene Descriptor
Besides local features, global information plays an essential role in semantic segmentation, while recent works usually fail to explicitly extract the meaningful global information and make full use of it.
Memristor Hardware-Friendly Reinforcement Learning
Namely, neuromorphic architectures that leverage memristors, the programmable and nonvolatile two-terminal devices, as synaptic weights in hardware neural networks, are candidates of choice to realize such highly energy-efficient and complex nervous systems.
HyGCN: A GCN Accelerator with Hybrid Architecture
In this work, we first characterize the hybrid execution patterns of GCNs on Intel Xeon CPU.
Distributed, Parallel, and Cluster Computing
Exploring Adversarial Attack in Spiking Neural Networks with Spike-Compatible Gradient
Recently, backpropagation through time inspired learning algorithms are widely introduced into SNNs to improve the performance, which brings the possibility to attack the models accurately given Spatio-temporal gradient maps.
A Comprehensive and Modularized Statistical Framework for Gradient Norm Equality in Deep Neural Networks
Powered by our metric and framework, we analyze extensive initialization, normalization, and network structures.
Proq: Projection-based Runtime Assertions for Debugging on a Quantum Computer
In this paper, we propose Proq, a runtime assertion scheme for testing and debugging quantum programs on a quantum computer.
DARB: A Density-Aware Regular-Block Pruning for Deep Neural Networks
As a further optimization, we propose a density-adaptive regular-block (DARB) pruning that outperforms prior structured pruning work with high pruning ratio and decoding efficiency.
Comprehensive SNN Compression Using ADMM Optimization and Activity Regularization
As well known, the huge memory and compute costs of both artificial neural networks (ANNs) and spiking neural networks (SNNs) greatly hinder their deployment on edge devices with high efficiency.
QGAN: Quantize Generative Adversarial Networks to Extreme low-bits
Despite the success in model reduction of convolutional neural networks (CNNs), neural network quantization methods have not yet been studied on GANs, which are mainly faced with the issues of both the effectiveness of quantization algorithms and the instability of training GAN models.
Dual-module Inference for Efficient Recurrent Neural Networks
Using Recurrent Neural Networks (RNNs) in sequence modeling tasks is promising in delivering high-quality results but challenging to meet stringent latency requirements because of the memory-bound execution pattern of RNNs.
Training High-Performance and Large-Scale Deep Neural Networks with Full 8-bit Integers
In this way, all the operations in the training and inference can be bit-wise operations, pushing towards faster processing speed, decreased memory cost, and higher energy efficiency.
AccD: A Compiler-based Framework for Accelerating Distance-related Algorithms on CPU-FPGA Platforms
As a promising solution to boost the performance of distance-related algorithms (e. g., K-means and KNN), FPGA-based acceleration attracts lots of attention, but also comes with numerous challenges.
Distributed, Parallel, and Cluster Computing Programming Languages
Semi-Supervised Video Salient Object Detection Using Pseudo-Labels
Specifically, we present an effective video saliency detector that consists of a spatial refinement network and a spatiotemporal module.
Ranked #1 on
Video Salient Object Detection
on VOS-T
(using extra training data)
Effective and Efficient Batch Normalization Using Few Uncorrelated Data for Statistics' Estimation
We identify that the effectiveness expects less data correlation while the efficiency expects regular execution pattern.
Tackling the Qubit Mapping Problem for NISQ-Era Quantum Devices
Due to little consideration in the hardware constraints, e. g., limited connections between physical qubits to enable two-qubit gates, most quantum algorithms cannot be directly executed on the Noisy Intermediate-Scale Quantum (NISQ) devices.
Neural Network Model Extraction Attacks in Edge Devices by Hearing Architectural Hints
As neural networks continue their reach into nearly every aspect of software operations, the details of those networks become an increasingly sensitive subject.
Cryptography and Security Hardware Architecture
FPSA: A Full System Stack Solution for Reconfigurable ReRAM-based NN Accelerator Architecture
In this paper, we propose a full system stack solution, composed of a reconfigurable architecture design, Field Programmable Synapse Array (FPSA) and its software system including neural synthesizer, temporal-to-spatial mapper, and placement & routing.
QGAN: Quantized Generative Adversarial Networks
The intensive computation and memory requirements of generative adversarial neural networks (GANs) hinder its real-world deployment on edge devices such as smartphones.
A Secure and Persistent Memory System for Non-volatile Memory
Specifically, SecPM leverages the CWT scheme to guarantee the crash consistency via ensuring both the data and its counter are durable before the data flush completes, and leverages the CWR scheme to improve the system performance via exploiting the spatial locality of counter storage, log and data writes.
Distributed, Parallel, and Cluster Computing Hardware Architecture Cryptography and Security
Facial Landmark Machines: A Backbone-Branches Architecture with Progressive Representation Learning
In this paper, we propose a novel cascaded backbone-branches fully convolutional neural network~(BB-FCN) for rapidly and accurately localizing facial landmarks in unconstrained and cluttered settings.
TETRIS: TilE-matching the TRemendous Irregular Sparsity
Increasing the sparsity granularity can lead to better hardware utilization, but it will compromise the sparsity for maintaining accuracy.
HitNet: Hybrid Ternary Recurrent Neural Network
For example, we improve the perplexity per word (PPW) of a ternary LSTM on Penn Tree Bank (PTB) corpus from 126 (the state-of-the-art result to the best of our knowledge) to 110. 3 with a full precision model in 97. 2, and a ternary GRU from 142 to 113. 5 with a full precision model in 102. 7.
Designing by Training: Acceleration Neural Network for Fast High-Dimensional Convolution
Over the decades, people took a handmade approach to design fast algorithms for the Gaussian convolution.
Image Captioning Based on a Hierarchical Attention Mechanism and Policy Gradient Optimization
Automatically generating the descriptions of an image, i. e., image captioning, is an important and fundamental topic in artificial intelligence, which bridges the gap between computer vision and natural language processing.
Bi-GANs-ST for Perceptual Image Super-resolution
In this paper, motivated by [1], we aim to generate a high-quality SR result which balances between the two indices, i. e., the perception index and root-mean-square error (RMSE).
Batch Normalization Sampling
In this paper, we propose alleviating this problem through sampling only a small fraction of data for normalization at each iteration.
Dynamic Sparse Graph for Efficient Deep Learning
We propose to execute deep neural networks (DNNs) with dynamic and sparse graph (DSG) structure for compressive memory and accelerative execution during both training and inference.
Jointly Deep Multi-View Learning for Clustering Analysis
To our best knowledge, this is the first work to model the multi-view clustering in a deep joint framework, which will provide a meaningful thinking in unsupervised multi-view learning.
Off-Policy Evaluation and Learning from Logged Bandit Feedback: Error Reduction via Surrogate Policy
Such an error reduction phenomenon is somewhat surprising as the estimated surrogate policy is less accurate than the given historical policy.
Crossbar-aware neural network pruning
Crossbar architecture based devices have been widely adopted in neural network accelerators by taking advantage of the high efficiency on vector-matrix multiplication (VMM) operations.
Structurally Sparsified Backward Propagation for Faster Long Short-Term Memory Training
Further, we can enforce structured sparsity in the gate gradients to make the LSTM backward pass up to 45% faster than the state-of-the-art dense approach and 168% faster than the state-of-the-art sparsifying method on modern GPUs.
Flow Guided Recurrent Neural Encoder for Video Salient Object Detection
Image saliency detection has recently witnessed significant progress due to deep convolutional neural networks.
Ranked #2 on
Video Salient Object Detection
on DAVSOD-Difficult20
(using extra training data)
Weakly Supervised Salient Object Detection Using Image Labels
Our algorithm is based on alternately exploiting a graphical model and training a fully convolutional network for model updating.
L1-Norm Batch Normalization for Efficient Training of Deep Neural Networks
Batch Normalization (BN) has been proven to be quite effective at accelerating and improving the training of deep neural networks (DNNs).
Bridging the Gap Between Neural Networks and Neuromorphic Hardware with A Neural Network Compiler
Different from developing neural networks (NNs) for general-purpose processors, the development for NN chips usually faces with some hardware-specific restrictions, such as limited precision of network signals and parameters, constrained computation scale, and limited types of non-linear functions.
Effective Image Retrieval via Multilinear Multi-index Fusion
In this paper, we propose a new multi-index fusion scheme for image retrieval.
Robust Kernelized Multi-View Self-Representations for Clustering by Tensor Multi-Rank Minimization
In particular, the original tensor-based multi-view self-representation clustering problem is a special case of our approach and can be solved by our algorithm.
Joint Hierarchical Category Structure Learning and Large-Scale Image Classification
We propose a novel image classification method based on learning hierarchical inter-class structures.
Instance-Level Salient Object Segmentation
Image saliency detection has recently witnessed rapid progress due to deep convolutional neural networks.
Ranked #15 on
RGB Salient Object Detection
on DUTS-TE
(max F-measure metric)
On Unifying Multi-View Self-Representations for Clustering by Tensor Multi-Rank Minimization
Different from traditional unfolding based tensor norm, this low-rank tensor constraint has optimality properties similar to that of matrix rank derived from SVD, so the complementary information among views can be explored more efficiently and thoroughly.
CNNLab: a Novel Parallel Framework for Neural Networks using GPU and FPGA-a Practical Study with Trade-off Analysis
To improve the performance and maintain the scalability, we present CNNLab, a novel deep learning framework using GPU and FPGA-based accelerators.
DLAU: A Scalable Deep Learning Accelerator Unit on FPGA
As the emerging field of machine learning, deep learning shows excellent ability in solving complex learning problems.
Weighted Schatten $p$-Norm Minimization for Image Denoising and Background Subtraction
However, NNM tends to over-shrink the rank components and treats the different rank components equally, limiting its flexibility in practical applications.
A New Low-Rank Tensor Model for Video Completion
On the other, t-TNN is equal to the nuclear norm of block circulant matricization of the twist tensor in the original domain, which extends the traditional matrix nuclear norm in a block circulant way.
Weighted Schatten $p$-Norm Minimization for Image Denoising with Local and Nonlocal Regularization
An efficient algorithm is also proposed to solve the WSNM problem.
Distortion-driven Turbulence Effect Removal using Variational Model
To solve, or at least reduce these effects, we propose a new scheme to recover a latent image from observed frames by integrating a new variational model and distortion-driven spatial-temporal kernel regression.
