Search Results for author:
Found 37 papers, 13 papers with code
Towards well-specified semi-supervised model-based classifiers via structural adaptation
This issue is known as model misspecification.
DADA: Deep Adversarial Data Augmentation for Extremely Low Data Regime Classification
Given insufficient data, while many techniques have been developed to help combat overfitting, the challenge remains if one tries to train deep networks, especially in the ill-posed extremely low data regimes: only a small set of labeled data are available, and nothing -- including unlabeled data -- else.
Structure-Preserving Transformation: Generating Diverse and Transferable Adversarial Examples
A common requirement in all these works is that the malicious perturbations should be small enough (measured by an L_p norm for some p) so that they are imperceptible to humans.
Wasserstein Autoencoders for Collaborative Filtering
Two different cost functions are designed for measuring the distance between the implicit feedback data and its re-generated version of data.
Heterogeneous-Temporal Graph Convolutional Networks: Make the Community Detection Much Better
Community detection has long been an important yet challenging task to analyze complex networks with a focus on detecting topological structures of graph data.
Structure Matters: Towards Generating Transferable Adversarial Images
In this paper, we propose the novel concepts of structure patterns and structure-aware perturbations that relax the small perturbation constraint while still keeping images natural.
Computer-Aided Clinical Skin Disease Diagnosis Using CNN and Object Detection Models
Our results show that object detection can help improve the accuracy of some skin disease classes.
Automatically Generating Macro Research Reports from a Piece of News
As we all know, it requires the macro analysts to write such reports within a short period of time after the important economic news are released.
SiENet: Siamese Expansion Network for Image Extrapolation
In this paper, a novel two-stage siamese adversarial model for image extrapolation, named Siamese Expansion Network (SiENet) is proposed.
Generating Long Financial Report using Conditional Variational Autoencoders with Knowledge Distillation
Particularly, we choose Bi-GRU as the encoder and decoder component of CVAE, and learn the latent variable distribution from input news.
Developing Univariate Neurodegeneration Biomarkers with Low-Rank and Sparse Subspace Decomposition
With hippocampal UMIs, the estimated minimum sample sizes needed to detect a 25$\%$ reduction in the mean annual change with 80$\%$ power and two-tailed $P=0. 05$ are 116, 279 and 387 for the longitudinal $A\beta+$ AD, $A\beta+$ mild cognitive impairment (MCI) and $A\beta+$ CU groups, respectively.
RRCN: A Reinforced Random Convolutional Network based Reciprocal Recommendation Approach for Online Dating
In particular, we technically propose a novel random CNN component that can randomly convolute non-adjacent features to capture their interaction information and learn feature embeddings of key attributes to make the final recommendation.
Probing Negative Sampling Strategies to Learn GraphRepresentations via Unsupervised Contrastive Learning
Graph representation learning has long been an important yet challenging task for various real-world applications.
DAGNN: Demand-aware Graph Neural Networks for Session-based Recommendation
Then, the demand-aware graph neural network is designed to extract session demand graph to learn the demand-aware item embedddings for the later recommendations.
Detecting Communities from Heterogeneous Graphs: A Context Path-based Graph Neural Network Model
With the surge of graph embedding mechanism, it has also been adopted to community detection.
VDPC: Variational Density Peak Clustering Algorithm
Furthermore, we divide all data points into different levels according to their local density and propose a unified clustering framework by combining the advantages of both DPC and DBSCAN.
NTIRE 2022 Challenge on Super-Resolution and Quality Enhancement of Compressed Video: Dataset, Methods and Results
This challenge includes three tracks.
GSim: A Graph Neural Network based Relevance Measure for Heterogeneous Graphs
Most of existing relevance measures focus on homogeneous networks where objects are of the same type, and a few measures are developed for heterogeneous graphs, but they often need the pre-defined meta-path.
Mixture of Attention Heads: Selecting Attention Heads Per Token
This paper proposes the Mixture of Attention Heads (MoA), a new architecture that combines multi-head attention with the MoE mechanism.
Power Efficient Video Super-Resolution on Mobile NPUs with Deep Learning, Mobile AI & AIM 2022 challenge: Report
While numerous solutions have been proposed for this problem, they are usually quite computationally demanding, demonstrating low FPS rates and power efficiency on mobile devices.
Transformer-Patcher: One Mistake worth One Neuron
Our method outperforms previous fine-tuning and HyperNetwork-based methods and achieves state-of-the-art performance for Sequential Model Editing (SME).
SAM-helps-Shadow:When Segment Anything Model meet shadow removal
The challenges surrounding the application of image shadow removal to real-world images and not just constrained datasets like ISTD/SRD have highlighted an urgent need for zero-shot learning in this field.
Recyclable Semi-supervised Method Based on Multi-model Ensemble for Video Scene Parsing
Pixel-level Scene Understanding is one of the fundamental problems in computer vision, which aims at recognizing object classes, masks and semantics of each pixel in the given image.
Enlighten Anything: When Segment Anything Model Meets Low-Light Image Enhancement
Image restoration is a low-level visual task, and most CNN methods are designed as black boxes, lacking transparency and intrinsic aesthetics.
BrickPal: Augmented Reality-based Assembly Instructions for Brick Models
The assembly instruction is a mandatory component of Lego-like brick sets. The conventional production of assembly instructions requires a considerable amount of manual fine-tuning, which is intractable for casual users and customized brick sets. Moreover, the traditional paper-based instructions lack expressiveness and interactivity. To tackle the two problems above, we present BrickPal, an augmented reality-based system, which visualizes assembly instructions in an augmented reality head-mounted display.
Weakly supervised learning for pattern classification in serial femtosecond crystallography
Th is heavy dependence on labeled datasets will seriously restrict the application of networks, because it is very costly to annotate a large number of diffraction patterns.
An Effective Data Creation Pipeline to Generate High-quality Financial Instruction Data for Large Language Model
At the beginning era of large language model, it is quite critical to generate a high-quality financial dataset to fine-tune a large language model for financial related tasks.
FinVis-GPT: A Multimodal Large Language Model for Financial Chart Analysis
In this paper, we propose FinVis-GPT, a novel multimodal large language model (LLM) specifically designed for financial chart analysis.
Improving Depth Gradient Continuity in Transformers: A Comparative Study on Monocular Depth Estimation with CNN
To explore the differences between Transformers and CNNs, we employ a sparse pixel approach to contrastively analyze the distinctions between the two.
Causal-Story: Local Causal Attention Utilizing Parameter-Efficient Tuning For Visual Story Synthesis
The current state-of-the-art method combines the features of historical captions, historical frames, and the current captions as conditions for generating the current frame.
Efficient Remote Sensing Segmentation With Generative Adversarial Transformer
Most deep learning methods that achieve high segmentation accuracy require deep network architectures that are too heavy and complex to run on embedded devices with limited storage and memory space.
A Dual Attentive Generative Adversarial Network for Remote Sensing Image Change Detection
Remote sensing change detection between bi-temporal images receives growing concentration from researchers.
How to Determine the Most Powerful Pre-trained Language Model without Brute Force Fine-tuning? An Empirical Survey
However, there is a lack of a comprehensive comparison between these estimation methods yet.
Enlighten-Your-Voice: When Multimodal Meets Zero-shot Low-light Image Enhancement
Low-light image enhancement is a crucial visual task, and many unsupervised methods tend to overlook the degradation of visible information in low-light scenes, which adversely affects the fusion of complementary information and hinders the generation of satisfactory results.
Building Lane-Level Maps from Aerial Images
In this paper, we introduce for the first time a large-scale aerial image dataset built for lane detection, with high-quality polyline lane annotations on high-resolution images of around 80 kilometers of road.
Wavelet-Decoupling Contrastive Enhancement Network for Fine-Grained Skeleton-Based Action Recognition
Skeleton-based action recognition has attracted much attention, benefiting from its succinctness and robustness.
Building the Directed Semantic Graph for Coherent Long Text Generation
These directed subgraphs are considered to well preserve extra but relevant content to the short input text, and then they are decoded by the employed pre-trained model to generate coherent long text.
