Search Results for author:
Found 31 papers, 13 papers with code
FaultSeg Swin-UNETR: Transformer-Based Self-Supervised Pretraining Model for Fault Recognition
This paper introduces an approach to enhance seismic fault recognition through self-supervised pretraining.
Towards a Unified Theoretical Understanding of Non-contrastive Learning via Rank Differential Mechanism
In this work, we propose a unified theoretical understanding for existing variants of non-contrastive learning.
PDO-s3DCNNs: Partial Differential Operator Based Steerable 3D CNNs
Steerable models can provide very general and flexible equivariance by formulating equivariance requirements in the language of representation theory and feature fields, which has been recognized to be effective for many vision tasks.
Automatic Text Extractive Summarization Based on Graph and Pre-trained Language Model Attention
Representing a text as a graph for obtaining automatic text summarization has been investigated for over ten years.
ARGO: Modeling Heterogeneity in E-commerce Recommendation
Nowadays, E-commerce is increasingly integrated into our daily lives.
Criterion-based Heterogeneous Collaborative Filtering for Multi-behavior Implicit Recommendation
Besides, CHCF integrates criterion learning and user preference learning into a unified framework, which can be trained jointly for the interaction prediction of the target behavior.
Deep Unsupervised Hashing by Distilled Smooth Guidance
Hashing has been widely used in approximate nearest neighbor search for its storage and computational efficiency.
PDO-eS2CNNs: Partial Differential Operator Based Equivariant Spherical CNNs
Spherical signals exist in many applications, e. g., planetary data, LiDAR scans and digitalization of 3D objects, calling for models that can process spherical data effectively.
HRN: A Holistic Approach to One Class Learning
Existing neural network based one-class learning methods mainly use various forms of auto-encoders or GAN style adversarial training to learn a latent representation of the given one class of data.
Translation vs. Dialogue: A Comparative Analysis of Sequence-to-Sequence Modeling
Understanding neural models is a major topic of interest in the deep learning community.
CIMON: Towards High-quality Hash Codes
However, due to the inefficient representation ability of the pre-trained model, many false positives and negatives in local semantic similarity will be introduced and lead to error propagation during the hash code learning.
PDO-eConvs: Partial Differential Operator Based Equivariant Convolutions
In implementation, we discretize the system using the numerical schemes of PDOs, deriving approximately equivariant convolutions (PDO-eConvs).
Ranked #1 on
Image Classification
on MNIST-rot-12
Real-time Universal Style Transfer on High-resolution Images via Zero-channel Pruning
Extracting effective deep features to represent content and style information is the key to universal style transfer.
DefenseVGAE: Defending against Adversarial Attacks on Graph Data via a Variational Graph Autoencoder
Graph neural networks (GNNs) achieve remarkable performance for tasks on graph data.
Multi-Label Classification with Label Graph Superimposing
In this paper, we propose a label graph superimposing framework to improve the conventional GCN+CNN framework developed for multi-label recognition in the following two aspects.
Ranked #28 on
Multi-Label Classification
on MS-COCO
Transformation of Dense and Sparse Text Representations
The key idea of the proposed approach is to use a Forward Transformation to transform dense representations to sparse representations.
Learning from Positive and Unlabeled Data with Adversarial Training
Positive-unlabeled (PU) learning learns a binary classifier using only positive and unlabeled examples without labeled negative examples.
Fast Universal Style Transfer for Artistic and Photorealistic Rendering
Given a pair of images as the source of content and the reference of style, existing solutions usually first train an auto-encoder (AE) to reconstruct the image using deep features and then embeds pre-defined style transfer modules into the AE reconstruction procedure to transfer the style of the reconstructed image through modifying the deep features.
StyleNAS: An Empirical Study of Neural Architecture Search to Uncover Surprisingly Fast End-to-End Universal Style Transfer Networks
Finally compared to existing universal style transfer networks for photorealistic rendering such as PhotoWCT that stacks multiple well-trained auto-encoders and WCT transforms in a non-end-to-end manner, the architectures designed by StyleNAS produce better style-transferred images with details preserving, using a tiny number of operators/parameters, and enjoying around 500x inference time speed-up.
GSN: A Graph-Structured Network for Multi-Party Dialogues
Existing neural models for dialogue response generation assume that utterances are sequentially organized.
Overcoming Catastrophic Forgetting via Model Adaptation
Several continual learning methods have been proposed to address the problem.
The Anisotropic Noise in Stochastic Gradient Descent: Its Behavior of Escaping from Minima and Regularization Effects
Along this line, we theoretically study a general form of gradient based optimization dynamics with unbiased noise, which unifies SGD and standard Langevin dynamics.
A Guider Network for Multi-Dual Learning
A large amount of parallel data is needed to train a strong neural machine translation (NMT) system.
T-SVD Based Non-convex Tensor Completion and Robust Principal Component Analysis
Tensor completion and robust principal component analysis have been widely used in machine learning while the key problem relies on the minimization of a tensor rank that is very challenging.
Spatial-Aware Non-Local Attention for Fashion Landmark Detection
Fashion landmark detection is a challenging task even using the current deep learning techniques, due to the large variation and non-rigid deformation of clothes.
Tangent-Normal Adversarial Regularization for Semi-supervised Learning
The proposed TNAR is composed by two complementary parts, the tangent adversarial regularization (TAR) and the normal adversarial regularization (NAR).
ELEGANT: Exchanging Latent Encodings with GAN for Transferring Multiple Face Attributes
Recent studies on face attribute transfer have achieved great success.
The Anisotropic Noise in Stochastic Gradient Descent: Its Behavior of Escaping from Sharp Minima and Regularization Effects
Along this line, we study a general form of gradient based optimization dynamics with unbiased noise, which unifies SGD and standard Langevin dynamics.
Topic-Based Question Generation
In the paper, we propose a new question generation problem, which also requires the input of a target topic in addition to a piece of descriptive text.
DNA-GAN: Learning Disentangled Representations from Multi-Attribute Images
Disentangling factors of variation has become a very challenging problem on representation learning.
Combination Features and Models for Human Detection
This paper presents effective combination models with certain combination features for human detection.
