Search Results for author:
Found 51 papers, 22 papers with code
Low-Light Image Enhancement with Illumination-Aware Gamma Correction and Complete Image Modelling Network
We propose to integrate the effectiveness of gamma correction with the strong modelling capacities of deep networks, which enables the correction factor gamma to be learned in a coarse to elaborate manner via adaptively perceiving the deviated illumination.
Self-supervised Learning and Graph Classification under Heterophily
Self-supervised learning has shown its promising capability in graph representation learning in recent work.
Controlling Text-to-Image Diffusion by Orthogonal Finetuning
To tackle this challenge, we introduce a principled finetuning method -- Orthogonal Finetuning (OFT), for adapting text-to-image diffusion models to downstream tasks.
A Survey on Time-Series Pre-Trained Models
Time-Series Mining (TSM) is an important research area since it shows great potential in practical applications.
Boosting Convolutional Neural Networks with Middle Spectrum Grouped Convolution
This paper proposes a novel module called middle spectrum grouped convolution (MSGC) for efficient deep convolutional neural networks (DCNNs) with the mechanism of grouped convolution.
Locate Then Generate: Bridging Vision and Language with Bounding Box for Scene-Text VQA
Different to conventional STVQA models which take the linguistic semantics and visual semantics in scene text as two separate features, in this paper, we propose a paradigm of "Locate Then Generate" (LTG), which explicitly unifies this two semantics with the spatial bounding box as a bridge connecting them.
Disorder-invariant Implicit Neural Representation
However, the expressive power of INR is limited by the spectral bias in the network training.
MeshDiffusion: Score-based Generative 3D Mesh Modeling
We consider the task of generating realistic 3D shapes, which is useful for a variety of applications such as automatic scene generation and physical simulation.
Minimum Latency Deep Online Video Stabilization
In this work, we adopt recent off-the-shelf high-quality deep motion models for motion estimation to recover the camera trajectory and focus on the latter two steps.
Remote estimation of geologic composition using interferometric synthetic-aperture radar in California's Central Valley
We also achieved significant accuracy with 1/4 sparse sampling to reduce any spatial correlations among data, suggesting that the model has the potential to be generalized to other regions for indirect estimation of geologic composition.
DINER: Disorder-Invariant Implicit Neural Representation
Implicit neural representation (INR) characterizes the attributes of a signal as a function of corresponding coordinates which emerges as a sharp weapon for solving inverse problems.
Iterative Teaching by Data Hallucination
We consider the problem of iterative machine teaching, where a teacher sequentially provides examples based on the status of a learner under a discrete input space (i. e., a pool of finite samples), which greatly limits the teacher's capability.
Continual Learning by Modeling Intra-Class Variation
It has been observed that neural networks perform poorly when the data or tasks are presented sequentially.
SML:Enhance the Network Smoothness with Skip Meta Logit for CTR Prediction
In light of the smoothness property brought by skip connections in ResNet, this paper proposed the Skip Logit to introduce the skip connection mechanism that fits arbitrary DNN dimensions and embraces similar properties to ResNet.
BRIEF but Powerful: Byzantine-Robust and Privacy-Preserving Federated Learning via Model Segmentation and Secure clustering
To thwart attacks of malicious majority, we develop an algorithm called Model Segmentation, where local updates in the same cluster are aggregated together, and the aggregations are sent back to corresponding clients correctly.
Ghost-free High Dynamic Range Imaging with Context-aware Transformer
High dynamic range (HDR) deghosting algorithms aim to generate ghost-free HDR images with realistic details.
Structural Causal 3D Reconstruction
This paper considers the problem of unsupervised 3D object reconstruction from in-the-wild single-view images.
Expressiveness and Learnability: A Unifying View for Evaluating Self-Supervised Learning
We propose to use the Intrinsic Dimension (ID) to assess expressiveness and introduce Cluster Learnability (CL) to assess learnability.
NTIRE 2022 Challenge on High Dynamic Range Imaging: Methods and Results
The challenge is composed of two tracks with an emphasis on fidelity and complexity constraints: In Track 1, participants are asked to optimize objective fidelity scores while imposing a low-complexity constraint (i. e. solutions can not exceed a given number of operations).
Generative Flow Networks for Discrete Probabilistic Modeling
We present energy-based generative flow networks (EB-GFN), a novel probabilistic modeling algorithm for high-dimensional discrete data.
VirtualCube: An Immersive 3D Video Communication System
The VirtualCube system is a 3D video conference system that attempts to overcome some limitations of conventional technologies.
Hierarchical clustering by aggregating representatives in sub-minimum-spanning-trees
One of the main challenges for hierarchical clustering is how to appropriately identify the representative points in the lower level of the cluster tree, which are going to be utilized as the roots in the higher level of the cluster tree for further aggregation.
Iterative Teaching by Label Synthesis
In this paper, we consider the problem of iterative machine teaching, where a teacher provides examples sequentially based on the current iterative learner.
A Generic Knowledge Based Medical Diagnosis Expert System
The proposed disease diagnosis system also uses a graphical user interface (GUI) to facilitate users to interact with the expert system.
Learnability and Expressiveness in Self-Supervised Learning
In this work, we argue that representations induced by self-supervised learning (SSL) methods should both be expressive and learnable.
Cognitive Visual Commonsense Reasoning Using Dynamic Working Memory
Moreover, the proposed model provides intuitive interpretation into visual commonsense reasoning.
A Consciousness-Inspired Planning Agent for Model-Based Reinforcement Learning
We present an end-to-end, model-based deep reinforcement learning agent which dynamically attends to relevant parts of its state during planning.
Model-based Reinforcement Learning
Out-of-Distribution Generalization
+2
ADNet: Attention-guided Deformable Convolutional Network for High Dynamic Range Imaging
In this paper, we present an attention-guided deformable convolutional network for hand-held multi-frame high dynamic range (HDR) imaging, namely ADNet.
Ranked #5 on
Face Alignment
on WFW (Extra Data)
LSTM Based Sentiment Analysis for Cryptocurrency Prediction
Recent studies in big data analytics and natural language processing develop automatic techniques in analyzing sentiment in the social media information.
Learning with Hyperspherical Uniformity
Due to the over-parameterization nature, neural networks are a powerful tool for nonlinear function approximation.
A Bayesian Spatial Modeling Approach to Mortality Forecasting
This paper extends Bayesian mortality projection models for multiple populations considering the stochastic structure and the effect of spatial autocorrelation among the observations.
Methodology
A Data-driven Human Responsibility Management System
An ideal safe workplace is described as a place where staffs fulfill responsibilities in a well-organized order, potential hazardous events are being monitored in real-time, as well as the number of accidents and relevant damages are minimized.
Using Machine Learning to Automate Mammogram Images Analysis
Early detection of breast cancer in X-ray mammography is believed to have effectively reduced the mortality rate.
Orthogonal Over-Parameterized Training
The inductive bias of a neural network is largely determined by the architecture and the training algorithm.
Reinterpretation of LHC Results for New Physics: Status and Recommendations after Run 2
We report on the status of efforts to improve the reinterpretation of searches and measurements at the LHC in terms of models for new physics, in the context of the LHC Reinterpretation Forum.
High Energy Physics - Phenomenology High Energy Physics - Experiment
NEW: A Generic Learning Model for Tie Strength Prediction in Networks
Tie strength prediction, sometimes named weight prediction, is vital in exploring the diversity of connectivity pattern emerged in networks.
A Compared Study Between Some Subspace Based Algorithms
The technology of face recognition has made some progress in recent years.
Visual-Textual Association with Hardest and Semi-Hard Negative Pairs Mining for Person Search
In order to evaluate the effectiveness and feasibility of the proposed approach, we conduct extensive experiments on typical person search datasdet: CUHK-PEDES, in which our approach achieves the top1 score of 55. 32% as a new state-of-the-art.
Neural Similarity Learning
By generalizing inner product with a bilinear matrix, we propose the neural similarity which serves as a learnable parametric similarity measure for CNNs.
Context-endcoding for neural network based skull stripping in magnetic resonance imaging
Skull stripping is usually the first step for most brain analysisprocess in magnetic resonance images.
Regularizing Neural Networks via Minimizing Hyperspherical Energy
Inspired by the Thomson problem in physics where the distribution of multiple propelling electrons on a unit sphere can be modeled via minimizing some potential energy, hyperspherical energy minimization has demonstrated its potential in regularizing neural networks and improving their generalization power.
Exponential Family Estimation via Adversarial Dynamics Embedding
We present an efficient algorithm for maximum likelihood estimation (MLE) of exponential family models, with a general parametrization of the energy function that includes neural networks.
Coupled Variational Bayes via Optimization Embedding
This flexible function class couples the variational distribution with the original parameters in the graphical models, allowing end-to-end learning of the graphical models by back-propagation through the variational distribution.
Learning towards Minimum Hyperspherical Energy
In light of this intuition, we reduce the redundancy regularization problem to generic energy minimization, and propose a minimum hyperspherical energy (MHE) objective as generic regularization for neural networks.
Decoupled Networks
Inner product-based convolution has been a central component of convolutional neural networks (CNNs) and the key to learning visual representations.
SBEED: Convergent Reinforcement Learning with Nonlinear Function Approximation
When function approximation is used, solving the Bellman optimality equation with stability guarantees has remained a major open problem in reinforcement learning for decades.
Deep Forward and Inverse Perceptual Models for Tracking and Prediction
We consider the problems of learning forward models that map state to high-dimensional images and inverse models that map high-dimensional images to state in robotics.
Towards Black-box Iterative Machine Teaching
We propose an active teacher model that can actively query the learner (i. e., make the learner take exams) for estimating the learner's status and provably guide the learner to achieve faster convergence.
One-Shot Learning for Semantic Segmentation
Low-shot learning methods for image classification support learning from sparse data.
Kernelized Deep Convolutional Neural Network for Describing Complex Images
With the impressive capability to capture visual content, deep convolutional neural networks (CNN) have demon- strated promising performance in various vision-based ap- plications, such as classification, recognition, and objec- t detection.
Efficient Bayesian analysis of multiple changepoint models with dependence across segments
We consider Bayesian analysis of a class of multiple changepoint models.
