Search Results for author:
Found 80 papers, 20 papers with code
RandAlign: A Parameter-Free Method for Regularizing Graph Convolutional Networks
Intuitively, we can expect the generated embeddings become smooth asymptotically layerwisely, that is each layer of graph convolution generates a smoothed version of embeddings as compared to that generated by the previous layer.
CryoMAE: Few-Shot Cryo-EM Particle Picking with Masked Autoencoders
Cryo-electron microscopy (cryo-EM) emerges as a pivotal technology for determining the architecture of cells, viruses, and protein assemblies at near-atomic resolution.
Neighbour-level Message Interaction Encoding for Improved Representation Learning on Graphs
To address this issue, we propose a neighbour-level message interaction information encoding method for improving graph representation learning.
Optimal convex $M$-estimation via score matching
As an example of a non-log-concave setting, for Cauchy errors, the optimal convex loss function is Huber-like, and our procedure yields an asymptotic efficiency greater than 0. 87 relative to the oracle maximum likelihood estimator of the regression coefficients that uses knowledge of this error distribution; in this sense, we obtain robustness without sacrificing much efficiency.
Uncertainty-Aware Adapter: Adapting Segment Anything Model (SAM) for Ambiguous Medical Image Segmentation
The Segment Anything Model (SAM) gained significant success in natural image segmentation, and many methods have tried to fine-tune it to medical image segmentation.
RealNet: A Feature Selection Network with Realistic Synthetic Anomaly for Anomaly Detection
Self-supervised feature reconstruction methods have shown promising advances in industrial image anomaly detection and localization.
Not just Birds and Cars: Generic, Scalable and Explainable Models for Professional Visual Recognition
Some visual recognition tasks are more challenging then the general ones as they require professional categories of images.
Causal Disentanglement for Regulating Social Influence Bias in Social Recommendation
Building upon this insight, we propose a disentangled encoder that focuses on disentangling user and item embeddings into interest and social influence embeddings.
A Privacy-Preserving Framework with Multi-Modal Data for Cross-Domain Recommendation
Furthermore, we introduce a privacy-preserving decoder to mitigate user privacy leakage during knowledge transfer.
Enhancing Weakly Supervised 3D Medical Image Segmentation through Probabilistic-aware Learning
3D medical image segmentation is a challenging task with crucial implications for disease diagnosis and treatment planning.
Leveraging Generative Language Models for Weakly Supervised Sentence Component Analysis in Video-Language Joint Learning
Orthogonal to the previous approaches to this limitation, we postulate that understanding the significance of the sentence components according to the target task can potentially enhance the performance of the models.
Weakly Supervised Anomaly Detection for Chest X-Ray Image
Chest X-Ray (CXR) examination is a common method for assessing thoracic diseases in clinical applications.
Supervised Anomaly Detection
Weakly-supervised Anomaly Detection
Multi-dimensional Fusion and Consistency for Semi-supervised Medical Image Segmentation
In this paper, we introduce a novel semi-supervised learning framework tailored for medical image segmentation.
DenseMP: Unsupervised Dense Pre-training for Few-shot Medical Image Segmentation
Few-shot medical image semantic segmentation is of paramount importance in the domain of medical image analysis.
One-Prompt to Segment All Medical Images
Tested on 14 previously unseen datasets, the One-Prompt Model showcases superior zero-shot segmentation capabilities, outperforming a wide range of related methods.
Medical SAM Adapter: Adapting Segment Anything Model for Medical Image Segmentation
In Med-SA, we propose Space-Depth Transpose (SD-Trans) to adapt 2D SAM to 3D medical images and Hyper-Prompting Adapter (HyP-Adpt) to achieve prompt-conditioned adaptation.
PyTorch FSDP: Experiences on Scaling Fully Sharded Data Parallel
It is widely acknowledged that large models have the potential to deliver superior performance across a broad range of domains.
Vital Sign Monitoring in Dynamic Environment via mmWave Radar and Camera Fusion
Contact-free vital sign monitoring, which uses wireless signals for recognizing human vital signs (i. e, breath and heartbeat), is an attractive solution to health and security.
Multimodal Hyperspectral Image Classification via Interconnected Fusion
More specifically, they overlook the contextual information across modalities of HSI and LiDAR and the intra-modality characteristics of LiDAR.
BiCro: Noisy Correspondence Rectification for Multi-modality Data via Bi-directional Cross-modal Similarity Consistency
As one of the most fundamental techniques in multimodal learning, cross-modal matching aims to project various sensory modalities into a shared feature space.
CoNIC Challenge: Pushing the Frontiers of Nuclear Detection, Segmentation, Classification and Counting
Nuclear detection, segmentation and morphometric profiling are essential in helping us further understand the relationship between histology and patient outcome.
BenchDirect: A Directed Language Model for Compiler Benchmarks
We improve this with BenchDirect which utilizes a directed LM that infills programs by jointly observing source code context and the compiler features that are targeted.
MedSegDiff-V2: Diffusion based Medical Image Segmentation with Transformer
To effectively integrate these two cutting-edge techniques for the Medical image segmentation, we propose a novel Transformer-based Diffusion framework, called MedSegDiff-V2.
Confidence-Calibrated Face and Kinship Verification
In this paper, we investigate the problem of prediction confidence in face and kinship verification.
BenchPress: A Deep Active Benchmark Generator
We develop BenchPress, the first ML benchmark generator for compilers that is steerable within feature space representations of source code.
Deep Active Learning with Noise Stability
We provide theoretical analyses by leveraging the small Gaussian noise theory and demonstrate that our method favors a subset with large and diverse gradients.
Dataset Pruning: Reducing Training Data by Examining Generalization Influence
To answer these, we propose dataset pruning, an optimization-based sample selection method that can (1) examine the influence of removing a particular set of training samples on model's generalization ability with theoretical guarantee, and (2) construct the smallest subset of training data that yields strictly constrained generalization gap.
SHREC 2021: Classification in cryo-electron tomograms
To promote innovation in computational methods, we generate a novel simulated dataset to benchmark different methods of localization and classification of biological macromolecules in tomograms.
Sparse Local Patch Transformer for Robust Face Alignment and Landmarks Inherent Relation Learning
The SLPT generates the representation of each single landmark from a local patch and aggregates them by an adaptive inherent relation based on the attention mechanism.
Ranked #2 on
Face Alignment
on COFW-68
Color Space-based HoVer-Net for Nuclei Instance Segmentation and Classification
Nuclei segmentation and classification is the first and most crucial step that is utilized for many different microscopy medical analysis applications.
Harmony: A Generic Unsupervised Approach for Disentangling Semantic Content From Parameterized Transformations
Harmony leverages a simple cross-contrastive learning framework with multiple explicitly parameterized latent representations to disentangle content from transformations.
Boosting Active Learning via Improving Test Performance
In this work, we explore such an impact by theoretically proving that selecting unlabeled data of higher gradient norm leads to a lower upper-bound of test loss, resulting in better test performance.
Cryo-shift: Reducing domain shift in cryo-electron subtomograms with unsupervised domain adaptation and randomization
Cryo-Electron Tomography (cryo-ET) is a 3D imaging technology that enables the visualization of subcellular structures in situ at near-atomic resolution.
Objects in Semantic Topology
A more realistic object detection paradigm, Open-World Object Detection, has arisen increasing research interests in the community recently.
Task-wise Split Gradient Boosting Trees for Multi-center Diabetes Prediction
To tackle the above challenges, we employ gradient boosting decision trees (GBDT) to handle data heterogeneity and introduce multi-task learning (MTL) to solve data insufficiency.
A Hybrid Vehicle Platoon for Connected and Automated Vehicles: Formulation, Stability Analysis, and Applications
The findings have demonstrated the merits of the combined implementation of CTG and CS policy in enhancing the performance and applicability of the platoon system for CAVs.
Disentangling semantic features of macromolecules in Cryo-Electron Tomography
Cryo-electron tomography (Cryo-ET) is a 3D imaging technique that enables the systemic study of shape, abundance, and distribution of macromolecular structures in single cells in near-atomic resolution.
Estimating Instance-dependent Bayes-label Transition Matrix using a Deep Neural Network
Motivated by that classifiers mostly output Bayes optimal labels for prediction, in this paper, we study to directly model the transition from Bayes optimal labels to noisy labels (i. e., Bayes-label transition matrix (BLTM)) and learn a classifier to predict Bayes optimal labels.
An Efficient Multitask Neural Network for Face Alignment, Head Pose Estimation and Face Tracking
Moreover, we generate a cheap heatmap based on the face alignment result and fuse it with features to improve the performance of the other two tasks.
Ranked #28 on
Face Alignment
on WFLW
Improving Transformation-based Defenses against Adversarial Examples with First-order Perturbations
Based on this observation, we propose a method for counteracting adversarial perturbations to improve adversarial robustness.
Self-supervised Pretraining of Visual Features in the Wild
Recently, self-supervised learning methods like MoCo, SimCLR, BYOL and SwAV have reduced the gap with supervised methods.
Ranked #6 on
Image Classification
on Places205
Self-Supervised Image Classification
Self-Supervised Learning
+1
Active Learning to Classify Macromolecular Structures in situ for Less Supervision in Cryo-Electron Tomography
Deep learning based subtomogram classification have played critical roles for such tasks.
SSFG: Stochastically Scaling Features and Gradients for Regularizing Graph Convolutional Networks
We show that applying stochastic scaling at the gradient level is complementary to that applied at the feature level to improve the overall performance.
Free Lunch for Few-shot Learning: Distribution Calibration
In this paper, we calibrate the distribution of these few-sample classes by transferring statistics from the classes with sufficient examples, then an adequate number of examples can be sampled from the calibrated distribution to expand the inputs to the classifier.
Towards Counteracting Adversarial Perturbations to Resist Adversarial Examples
We validate the proposed method on CIFAR-10 and CIFAR-100.
End-to-End Robust Joint Unsupervised Image Alignment and Clustering
To our knowledge, Jim-Net is the first end-to-end model that can simultaneously align and cluster images, which significantly improves the performance as compared to performing each task alone.
Weakly Supervised 3D Semantic Segmentation Using Cross-Image Consensus and Inter-Voxel Affinity Relations
We propose a novel weakly supervised approach for 3D semantic segmentation on volumetric images.
Towards Robust Partially Supervised Multi-Structure Medical Image Segmentation on Small-Scale Data
To bridge the methodological gaps in partially supervised learning (PSL) under data scarcity, we propose Vicinal Labels Under Uncertainty (VLUU), a simple yet efficient framework utilizing the human structure similarity for partially supervised medical image segmentation.
Weight Encode Reconstruction Network for Computed Tomography in a Semi-Case-Wise and Learning-Based Way
In the generalization test of the model, the encoder is transferable from a voxel set with complex structure to the unseen cases without the deduction of the accuracy.
Experimental Analysis of Legendre Decomposition in Machine Learning
In this technical report, we analyze Legendre decomposition for non-negative tensor in theory and application.
Few shot domain adaptation for in situ macromolecule structural classification in cryo-electron tomograms
Motivation: Cryo-Electron Tomography (cryo-ET) visualizes structure and spatial organization of macromolecules and their interactions with other subcellular components inside single cells in the close-to-native state at sub-molecular resolution.
Improving Lesion Segmentation for Diabetic Retinopathy using Adversarial Learning
Diabetic Retinopathy (DR) is a leading cause of blindness in working age adults.
SiamSNN: Siamese Spiking Neural Networks for Energy-Efficient Object Tracking
Recently spiking neural networks (SNNs), the third-generation of neural networks has shown remarkable capabilities of energy-efficient computing, which is a promising alternative for deep neural networks (DNNs) with high energy consumption.
Single-View 3D Object Reconstruction from Shape Priors in Memory
Inspired by this, we propose a novel method, named Mem3D, that explicitly constructs shape priors to supplement the missing information in the image.
AITom: Open-source AI platform for cryo-electron tomography data analysis
Cryo-electron tomography (cryo-ET) is an emerging technology for the 3D visualization of structural organizations and interactions of subcellular components at near-native state and sub-molecular resolution.
A Deep Learning System That Generates Quantitative CT Reports for Diagnosing Pulmonary Tuberculosis
The best model was selected to annotate the spatial location of lesions and classify them into miliary, infiltrative, caseous, tuberculoma and cavitary types simultaneously. Then the Noisy-Or Bayesian function was used to generate an overall infection probability. Finally, a quantitative diagnostic report was exported. The results showed that the recall and precision rates, from the perspective of a single lesion region of PTB, were 85. 9% and 89. 2% respectively.
Structured Modeling of Joint Deep Feature and Prediction Refinement for Salient Object Detection
We formulate the CRF graphical model that involves message-passing of feature-feature, feature-prediction, and prediction-prediction, from the coarse scale to the finer scale, to update the features and the corresponding predictions.
Visual Analytics of Student Learning Behaviors on K-12 Mathematics E-learning Platforms
With increasing popularity in online learning, a surge of E-learning platforms have emerged to facilitate education opportunities for k-12 (from kindergarten to 12th grade) students and with this, a wealth of information on their learning logs are getting recorded.
Improving Utility and Security of the Shuffler-based Differential Privacy
When collecting information, local differential privacy (LDP) alleviates privacy concerns of users because their private information is randomized before being sent it to the central aggregator.
Deep Learning-Based Strategy for Macromolecules Classification with Imbalanced Data from Cellular Electron Cryotomography
Deep learning model trained by imbalanced data may not work satisfactorily since it could be determined by major classes and thus may ignore the classes with small amount of data.
Dual Pattern Learning Networks by Empirical Dual Prediction Risk Minimization
This architecture forces the network to learn discriminative class-specific features by analyzing and comparing two input images.
Respond-CAM: Analyzing Deep Models for 3D Imaging Data by Visualizations
The weighted feature maps are combined to produce a heatmap that highlights the important regions in the image for predicting the target concept.
Multi-task Learning for Macromolecule Classification, Segmentation and Coarse Structural Recovery in Cryo-Tomography
Cellular Electron Cryo-Tomography (CECT) is a powerful 3D imaging tool for studying the native structure and organization of macromolecules inside single cells.
Image-derived generative modeling of pseudo-macromolecular structures - towards the statistical assessment of Electron CryoTomography template matching
Cellular Electron CryoTomography (CECT) is a 3D imaging technique that captures information about the structure and spatial organization of macromolecular complexes within single cells, in near-native state and at sub-molecular resolution.
An integration of fast alignment and maximum-likelihood methods for electron subtomogram averaging and classification
Existing subtomogram alignment based methods are prone to the missing wedge effects and low signal-to-noise ratio (SNR).
AAANE: Attention-based Adversarial Autoencoder for Multi-scale Network Embedding
Existing methods usually adopt a "one-size-fits-all" approach when concerning multi-scale structure information, such as first- and second-order proximity of nodes, ignoring the fact that different scales play different roles in the embedding learning.
Deep learning based supervised semantic segmentation of Electron Cryo-Subtomograms
Cellular Electron Cryo-Tomography (CECT) is a powerful imaging technique for the 3D visualization of cellular structure and organization at submolecular resolution.
Model compression for faster structural separation of macromolecules captured by Cellular Electron Cryo-Tomography
Electron Cryo-Tomography (ECT) enables 3D visualization of macromolecule structure inside single cells.
Feature Decomposition Based Saliency Detection in Electron Cryo-Tomograms
To complement and speed up existing segmentation methods, it is desirable to develop a generic cell component segmentation method that is 1) not specific to particular types of cellular components, 2) able to segment unknown cellular components, 3) fully unsupervised and does not rely on the availability of training data.
A convolutional autoencoder approach for mining features in cellular electron cryo-tomograms and weakly supervised coarse segmentation
We demonstrate that the autoencoder can be used for efficient and coarse characterization of features of macromolecular complexes and surfaces, such as membranes.
Weakly supervised Semantic Segmentation
Weakly-Supervised Semantic Segmentation
Experience enrichment based task independent reward model
For most reinforcement learning approaches, the learning is performed by maximizing an accumulative reward that is expectedly and manually defined for specific tasks.
Learning Multi-level Deep Representations for Image Emotion Classification
The proposed MldrNet combines deep representations of different levels, i. e. image semantics, image aesthetics, and low-level visual features to effectively classify the emotion types of different kinds of images, such as abstract paintings and web images.
Modelling Temporal Information Using Discrete Fourier Transform for Recognizing Emotions in User-generated Videos
By this way, static image features extracted from a pre-trained deep CNN and temporal information represented by DFT features are jointly considered for video emotion recognition.
Integrative analysis of gene expression and phenotype data
We propose a method of automated multi-dimensional profiling which uses gene expression similarity.
Gene selection for cancer classification using a hybrid of univariate and multivariate feature selection methods
Various approaches to gene selection for cancer classification based on microarray data can be found in the literature and they may be grouped into two categories: univariate methods and multivariate methods.
Global Gene Expression Analysis Using Machine Learning Methods
The large amount of expression data generated by this technology makes the study of certain complex biological problems possible and machine learning methods are playing a crucial role in the analysis process.
Automatic tracking of protein vesicles
In this thesis, we formulate such tracking problem as video object tracking problem, and design a dynamic programming method for tracking single object.
Faithful Variable Screening for High-Dimensional Convex Regression
We study the problem of variable selection in convex nonparametric regression.
Estimation Bias in Multi-Armed Bandit Algorithms for Search Advertising
In search advertising, the search engine needs to select the most profitable advertisements to display, which can be formulated as an instance of online learning with partial feedback, also known as the stochastic multi-armed bandit (MAB) problem.
Noise Thresholds for Spectral Clustering
Although spectral clustering has enjoyed considerable empirical success in machine learning, its theoretical properties are not yet fully developed.
