Search Results for author:
Found 57 papers, 27 papers with code
WHC: Weighted Hybrid Criterion for Filter Pruning on Convolutional Neural Networks
Filter pruning has attracted increasing attention in recent years for its capacity in compressing and accelerating convolutional neural networks.
Scale-Semantic Joint Decoupling Network for Image-text Retrieval in Remote Sensing
To address these issues, we propose a novel Scale-Semantic Joint Decoupling Network (SSJDN) for remote sensing image-text retrieval.
FIXED: Frustratingly Easy Domain Generalization with Mixup
Firstly, Mixup cannot effectively identify the domain and class information that can be used for learning invariant representations.
Sub-network Multi-objective Evolutionary Algorithm for Filter Pruning
Filter pruning is a common method to achieve model compression and acceleration in deep neural networks (DNNs). Some research regarded filter pruning as a combinatorial optimization problem and thus used evolutionary algorithms (EA) to prune filters of DNNs.
Understanding the Failure of Batch Normalization for Transformers in NLP
Batch Normalization (BN) is a core and prevalent technique in accelerating the training of deep neural networks and improving the generalization on Computer Vision (CV) tasks.
An Investigation into Whitening Loss for Self-supervised Learning
A desirable objective in self-supervised learning (SSL) is to avoid feature collapse.
MDM: Molecular Diffusion Model for 3D Molecule Generation
At the same time, the generated molecules lack enough diversity.
Towards Better Understanding with Uniformity and Explicit Regularization of Embeddings in Embedding-based Neural Topic Models
In this paper, we propose an embedding regularized neural topic model, which applies the specially designed training constraints on word embedding and topic embedding to reduce the optimization space of parameters.
Bi-level Doubly Variational Learning for Energy-based Latent Variable Models
In this paper, we propose Bi-level doubly variational learning (BiDVL), which is based on a new bi-level optimization framework and two tractable variational distributions to facilitate learning EBLVMs.
Revisiting Domain Generalized Stereo Matching Networks from a Feature Consistency Perspective
The stereo contrastive feature loss function explicitly constrains the consistency between learned features of matching pixel pairs which are observations of the same 3D points.
Delving into the Estimation Shift of Batch Normalization in a Network
We define the estimation shift magnitude of BN to quantitatively measure the difference between its estimated population statistics and expected ones.
Rot-Pro: Modeling Transitivity by Projection in Knowledge Graph Embedding
In this paper, we first theoretically show that the transitive relations can be modeled with projections.
Ranked #11 on
Link Prediction
on YAGO3-10
Towards Defending Multiple $\ell_p$-Norm Bounded Adversarial Perturbations via Gated Batch Normalization
We observe that different $\ell_p$ bounded adversarial perturbations induce different statistical properties that can be separated and characterized by the statistics of Batch Normalization (BN).
Joint Matrix Decomposition for Deep Convolutional Neural Networks Compression
To overcome this problem, we propose to compress CNNs and alleviate performance degradation via joint matrix decomposition, which is different from existing works that compressed layers separately.
Efficient Neural Network
Matrix Factorization / Decomposition
+1
KAISA: An Adaptive Second-Order Optimizer Framework for Deep Neural Networks
Kronecker-factored Approximate Curvature (K-FAC) has recently been shown to converge faster in deep neural network (DNN) training than stochastic gradient descent (SGD); however, K-FAC's larger memory footprint hinders its applicability to large models.
Many-to-One Distribution Learning and K-Nearest Neighbor Smoothing for Thoracic Disease Identification
For chest X-ray imaging, annotating large-scale data requires professional domain knowledge and is time-consuming.
S2-BNN: Bridging the Gap Between Self-Supervised Real and 1-bit Neural Networks via Guided Distribution Calibration
In this paper, we focus on this more difficult scenario: learning networks where both weights and activations are binary, meanwhile, without any human annotated labels.
EGFI: Drug-Drug Interaction Extraction and Generation with Fusion of Enriched Entity and Sentence Information
To address such a problem, we propose EGFI for extracting and consolidating drug interactions from large-scale medical literature text data.
Visual-Textual Attentive Semantic Consistency for Medical Report Generation
Second, the progressive report decoder consists of a sentence decoder and a word decoder, where we propose image-sentence matching and description accuracy losses to constrain the visual-textual semantic consistency.
CCT-Net: Category-Invariant Cross-Domain Transfer for Medical Single-to-Multiple Disease Diagnosis
A category-invariant cross-domain transfer (CCT) method is proposed to address this single-to-multiple extension.
One-Bit Target Detection in Collocated MIMO Radar and Performance Degradation Analysis
Target detection is an important problem in multiple-input multiple-output (MIMO) radar.
Slimmable Generative Adversarial Networks
In particular, for real-time generation tasks, different devices require generators of different sizes due to varying computing power.
Towards Defending Multiple Adversarial Perturbations via Gated Batch Normalization
To better understand this phenomenon, we propose the \emph{multi-domain} hypothesis, stating that different types of adversarial perturbations are drawn from different domains.
Effects of the Nonlinearity in Activation Functions on the Performance of Deep Learning Models
The nonlinearity of activation functions used in deep learning models are crucial for the success of predictive models.
Group Whitening: Balancing Learning Efficiency and Representational Capacity
Results show that GW consistently improves the performance of different architectures, with absolute gains of $1. 02\%$ $\sim$ $1. 49\%$ in top-1 accuracy on ImageNet and $1. 82\%$ $\sim$ $3. 21\%$ in bounding box AP on COCO.
Normalization Techniques in Training DNNs: Methodology, Analysis and Application
Normalization techniques are essential for accelerating the training and improving the generalization of deep neural networks (DNNs), and have successfully been used in various applications.
A Benchmark for Studying Diabetic Retinopathy: Segmentation, Grading, and Transferability
This dataset has 1, 842 images with pixel-level DR-related lesion annotations, and 1, 000 images with image-level labels graded by six board-certified ophthalmologists with intra-rater consistency.
Invertible Zero-Shot Recognition Flows
Deep generative models have been successfully applied to Zero-Shot Learning (ZSL) recently.
Convolutional Neural Network Training with Distributed K-FAC
Training neural networks with many processors can reduce time-to-solution; however, it is challenging to maintain convergence and efficiency at large scales.
Topic Detection and Summarization of User Reviews
As the sentiments are typically short, we combine sentiments talking about the same aspect into a single document and apply topic modeling method to identify hidden topics among customer reviews and summaries.
Controllable Orthogonalization in Training DNNs
Orthogonality is widely used for training deep neural networks (DNNs) due to its ability to maintain all singular values of the Jacobian close to 1 and reduce redundancy in representation.
An Efficient Agreement Mechanism in CapsNets By Pairwise Product
Capsule networks (CapsNets) are capable of modeling visual hierarchical relationships, which is achieved by the "routing-by-agreement" mechanism.
An Investigation into the Stochasticity of Batch Whitening
Our work originates from the observation that while various whitening transformations equivalently improve the conditioning, they show significantly different behaviors in discriminative scenarios and training Generative Adversarial Networks (GANs).
The Medical Scribe: Corpus Development and Model Performance Analyses
We used this annotation scheme to label a corpus of about 6k clinical encounters.
Layer-wise Conditioning Analysis in Exploring the Learning Dynamics of DNNs
To this end, we propose layer-wise conditioning analysis, which explores the optimization landscape with respect to each layer independently.
Unbiased Scene Graph Generation via Rich and Fair Semantic Extraction
Extracting graph representation of visual scenes in image is a challenging task in computer vision.
Deformable Tube Network for Action Detection in Videos
To perform action detection, we design a 3D convolution network with skip connections for tube classification and regression.
Query-Adaptive Hash Code Ranking for Large-Scale Multi-View Visual Search
For each hash table, a query-adaptive bitwise weighting is introduced to alleviate the quantization loss by simultaneously exploiting the quality of hash functions and their complement for nearest neighbor search.
Iterative Normalization: Beyond Standardization towards Efficient Whitening
With the support of SND, we provide natural explanations to several phenomena from the perspective of optimization, e. g., why group-wise whitening of DBN generally outperforms full-whitening and why the accuracy of BN degenerates with reduced batch sizes.
Analyzing Periodicity and Saliency for Adult Video Detection
Content-based adult video detection plays an important role in preventing pornography.
Utilizing Complex-valued Network for Learning to Compare Image Patches
At present, the great achievements of convolutional neural network(CNN) in feature and metric learning have attracted many researchers.
FanStore: Enabling Efficient and Scalable I/O for Distributed Deep Learning
Our experiments with benchmarks and real applications show that FanStore can scale DL training to 512 compute nodes with over 90\% scaling efficiency.
Distributed, Parallel, and Cluster Computing
Data-driven Analytics for Business Architectures: Proposed Use of Graph Theory
Business Architecture (BA) plays a significant role in helping organizations understand enterprise structures and processes, and align them with strategic objectives.
Decorrelated Batch Normalization
Batch Normalization (BN) is capable of accelerating the training of deep models by centering and scaling activations within mini-batches.
Orthogonal Weight Normalization: Solution to Optimization overMultiple Dependent Stiefel Manifolds in Deep Neural Networks
In this paper, we generalize such square orthogonal matrix to orthogonal rectangular matrix and formulating this problem in feed-forward Neural Networks (FNNs) as Optimization over Multiple Dependent Stiefel Manifolds (OMDSM).
DGCNN: Disordered Graph Convolutional Neural Network Based on the Gaussian Mixture Model
Convolutional neural networks (CNNs) can be applied to graph similarity matching, in which case they are called graph CNNs.
Ranked #1 on
Graph Classification
on AIDS
Projection Based Weight Normalization for Deep Neural Networks
We conduct comprehensive experiments on several widely-used image datasets including CIFAR-10, CIFAR-100, SVHN and ImageNet for supervised learning over the state-of-the-art convolutional neural networks, such as Inception, VGG and residual networks.
Centered Weight Normalization in Accelerating Training of Deep Neural Networks
Training deep neural networks is difficult for the pathological curvature problem.
Orthogonal Weight Normalization: Solution to Optimization over Multiple Dependent Stiefel Manifolds in Deep Neural Networks
In this paper, we generalize such square orthogonal matrix to orthogonal rectangular matrix and formulating this problem in feed-forward Neural Networks (FNNs) as Optimization over Multiple Dependent Stiefel Manifolds (OMDSM).
Block-Normalized Gradient Method: An Empirical Study for Training Deep Neural Network
In this paper, we propose a generic and simple strategy for utilizing stochastic gradient information in optimization.
Micro Fourier Transform Profilometry ($μ$FTP): 3D shape measurement at 10,000 frames per second
Recent advances in imaging sensors and digital light projection technology have facilitated a rapid progress in 3D optical sensing, enabling 3D surfaces of complex-shaped objects to be captured with improved resolution and accuracy.
Multi-View Complementary Hash Tables for Nearest Neighbor Search
have enjoyed the benefits of complementary hash tables and information fusion over multiple views.
Varying-smoother models for functional responses
We discuss three approaches to estimating varying-smoother models: (a) methods that employ a tensor product penalty; (b) an approach based on smoothed functional principal component scores; and (c) two-step methods consisting of an initial smooth with respect to $t$ at each $s$, followed by a postprocessing step.
Methodology
