Search Results for author:
Found 72 papers, 27 papers with code
RGL: A Simple yet Effective Relation Graph Augmented Prompt-based Tuning Approach for Few-Shot Learning
In this work, we show that Relation Graph augmented Learning (RGL) can improve the performance of few-shot natural language understanding tasks.
TiC: Exploring Vision Transformer in Convolution
While models derived from Vision Transformers (ViTs) have been phonemically surging, pre-trained models cannot seamlessly adapt to arbitrary resolution images without altering the architecture and configuration, such as sampling the positional encoding, limiting their flexibility for various vision tasks.
CUPre: Cross-domain Unsupervised Pre-training for Few-Shot Cell Segmentation
While pre-training on object detection tasks, such as Common Objects in Contexts (COCO) [1], could significantly boost the performance of cell segmentation, it still consumes on massive fine-annotated cell images [2] with bounding boxes, masks, and cell types for every cell in every image, to fine-tune the pre-trained model.
MUSCLE: Multi-task Self-supervised Continual Learning to Pre-train Deep Models for X-ray Images of Multiple Body Parts
In this work, we study a novel self-supervised pre-training pipeline, namely Multi-task Self-super-vised Continual Learning (MUSCLE), for multiple medical imaging tasks, such as classification and segmentation, using X-ray images collected from multiple body parts, including heads, lungs, and bones.
Natural Language based Context Modeling and Reasoning with LLMs: A Tutorial
Recently, with the rise of LLMs and their improved natural language understanding and reasoning capabilities, it has become feasible to model contexts using natural language and perform context reasoning by interacting with LLMs such as ChatGPT and GPT-4.
Robust Cross-Modal Knowledge Distillation for Unconstrained Videos
However, such semantic consistency from the synchronization is hard to guarantee in unconstrained videos, due to the irrelevant modality noise and differentiated semantic correlation.
Doubly Stochastic Models: Learning with Unbiased Label Noises and Inference Stability
While previous studies primarily focus on the affects of label noises to the performance of learning, our work intends to investigate the implicit regularization effects of the label noises, under mini-batch sampling settings of stochastic gradient descent (SGD), with assumptions that label noises are unbiased.
Video4MRI: An Empirical Study on Brain Magnetic Resonance Image Analytics with CNN-based Video Classification Frameworks
Due to the high similarity between MRI data and videos, we conduct extensive empirical studies on video recognition techniques for MRI classification to answer the questions: (1) can we directly use video recognition models for MRI classification, (2) which model is more appropriate for MRI, (3) are the common tricks like data augmentation in video recognition still useful for MRI classification?
Towards Long-Term Time-Series Forecasting: Feature, Pattern, and Distribution
Long-term time-series forecasting (LTTF) has become a pressing demand in many applications, such as wind power supply planning.
Temporal Output Discrepancy for Loss Estimation-based Active Learning
Inspired by the fact that the samples with higher loss are usually more informative to the model than the samples with lower loss, in this paper we present a novel deep active learning approach that queries the oracle for data annotation when the unlabeled sample is believed to incorporate high loss.
Learning from Training Dynamics: Identifying Mislabeled Data Beyond Manually Designed Features
While mislabeled or ambiguously-labeled samples in the training set could negatively affect the performance of deep models, diagnosing the dataset and identifying mislabeled samples helps to improve the generalization power.
ExpNet: A unified network for Expert-Level Classification
In the paper, we call them expert-level classification.
MedSegDiff: Medical Image Segmentation with Diffusion Probabilistic Model
Inspired by the success of DPM, we propose the first DPM based model toward general medical image segmentation tasks, which we named MedSegDiff.
RAIS: Robust and Accurate Interactive Segmentation via Continual Learning
Interactive image segmentation aims at segmenting a target region through a way of human-computer interaction.
GLARE: A Dataset for Traffic Sign Detection in Sun Glare
Real-time machine learning detection algorithms are often found within autonomous vehicle technology and depend on quality datasets.
AA-Forecast: Anomaly-Aware Forecast for Extreme Events
Moreover, the framework employs a dynamic uncertainty optimization algorithm that reduces the uncertainty of forecasts in an online manner.
$\textbf{P$^2$A}$: A Dataset and Benchmark for Dense Action Detection from Table Tennis Match Broadcasting Videos
While deep learning has been widely used for video analytics, such as video classification and action detection, dense action detection with fast-moving subjects from sports videos is still challenging.
Distilling Ensemble of Explanations for Weakly-Supervised Pre-Training of Image Segmentation Models
Though image classification datasets could provide the backbone networks with rich visual features and discriminative ability, they are incapable of fully pre-training the target model (i. e., backbone+segmentation modules) in an end-to-end manner.
Pareto Optimization for Active Learning under Out-of-Distribution Data Scenarios
In this paper, we propose a sampling scheme, Monte-Carlo Pareto Optimization for Active Learning (POAL), which selects optimal subsets of unlabeled samples with fixed batch size from the unlabeled data pool.
A Survey on Video Action Recognition in Sports: Datasets, Methods and Applications
Finally, we discuss the challenges and unsolved problems in this area and to facilitate sports analytics, we develop a toolbox using PaddlePaddle, which supports football, basketball, table tennis and figure skating action recognition.
SE-MoE: A Scalable and Efficient Mixture-of-Experts Distributed Training and Inference System
With the increasing diversity of ML infrastructures nowadays, distributed training over heterogeneous computing systems is desired to facilitate the production of big models.
A Simple yet Effective Framework for Active Learning to Rank
To handle the diverse query requests from users at web-scale, Baidu has done tremendous efforts in understanding users' queries, retrieve relevant contents from a pool of trillions of webpages, and rank the most relevant webpages on the top of results.
A Comparative Survey of Deep Active Learning
In this work, We construct a DAL toolkit, DeepAL+, by re-implementing 19 highly-cited DAL methods.
Towards Inadequately Pre-trained Models in Transfer Learning
Based on the contradictory phenomenon between FE and FT that better feature extractor fails to be fine-tuned better accordingly, we conduct comprehensive analyses on features before softmax layer to provide insightful explanations.
PP-HumanSeg: Connectivity-Aware Portrait Segmentation with a Large-Scale Teleconferencing Video Dataset
This work is the first to construct a large-scale video portrait dataset that contains 291 videos from 23 conference scenes with 14K fine-labeled frames and extensions to multi-camera teleconferencing.
SenseMag: Enabling Low-Cost Traffic Monitoring using Non-invasive Magnetic Sensing
Extensive experiment based on real-word field deployment (on the highways in Shenzhen, China) shows that SenseMag significantly outperforms the existing methods in both classification accuracy and the granularity of vehicle types (i. e., 7 types by SenseMag versus 4 types by the existing work in comparisons).
AgFlow: Fast Model Selection of Penalized PCA via Implicit Regularization Effects of Gradient Flow
Principal component analysis (PCA) has been widely used as an effective technique for feature extraction and dimension reduction.
Exploring the Common Principal Subspace of Deep Features in Neural Networks
Specifically, we design a new metric $\mathcal{P}$-vector to represent the principal subspace of deep features learned in a DNN, and propose to measure angles between the principal subspaces using $\mathcal{P}$-vectors.
Do What Nature Did To Us: Evolving Plastic Recurrent Neural Networks For Generalized Tasks
While artificial neural networks (ANNs) have been widely adopted in machine learning, researchers are increasingly obsessed by the gaps between ANNs and natural neural networks (NNNs).
AutoGCL: Automated Graph Contrastive Learning via Learnable View Generators
Most of the existing contrastive learning methods employ pre-defined view generation methods, e. g., node drop or edge perturbation, which usually cannot adapt to input data or preserve the original semantic structures well.
Evolving Decomposed Plasticity Rules for Information-Bottlenecked Meta-Learning
In contrast, biological neural networks (BNNs) can adapt to various new tasks by continually updating the neural connections based on the inputs, which is aligned with the paradigm of learning effective learning rules in addition to static parameters, e. g., meta-learning.
Cross-Model Consensus of Explanations and Beyond for Image Classification Models: An Empirical Study
Existing interpretation algorithms have found that, even deep models make the same and right predictions on the same image, they might rely on different sets of input features for classification.
Semi-Supervised Active Learning with Temporal Output Discrepancy
To lower the cost of data annotation, active learning has been proposed to interactively query an oracle to annotate a small proportion of informative samples in an unlabeled dataset.
Structure-aware Interactive Graph Neural Networks for the Prediction of Protein-Ligand Binding Affinity
To this end, we propose a structure-aware interactive graph neural network (SIGN) which consists of two components: polar-inspired graph attention layers (PGAL) and pairwise interactive pooling (PiPool).
Ranked #2 on
Protein-Ligand Affinity Prediction
on PDBbind
Face.evoLVe: A High-Performance Face Recognition Library
In this paper, we develop face. evoLVe -- a comprehensive library that collects and implements a wide range of popular deep learning-based methods for face recognition.
From Personalized Medicine to Population Health: A Survey of mHealth Sensing Techniques
Mobile Sensing Apps have been widely used as a practical approach to collect behavioral and health-related information from individuals and provide timely intervention to promote health and well-beings, such as mental health and chronic cares.
Robust Matrix Factorization with Grouping Effect
Compared with existing algorithms, the proposed GRMF can automatically learn the grouping structure and sparsity in MF without prior knowledge, by introducing a naturally adjustable non-convex regularization to achieve simultaneous sparsity and grouping effect.
Practical Assessment of Generalization Performance Robustness for Deep Networks via Contrastive Examples
Incorporating with a set of randomized strategies for well-designed data transformations over the training set, ContRE adopts classification errors and Fisher ratios on the generated contrastive examples to assess and analyze the generalization performance of deep models in complement with a testing set.
Optimization Variance: Exploring Generalization Properties of DNNs
Unlike the conventional wisdom in statistical learning theory, the test error of a deep neural network (DNN) often demonstrates double descent: as the model complexity increases, it first follows a classical U-shaped curve and then shows a second descent.
JIZHI: A Fast and Cost-Effective Model-As-A-Service System for Web-Scale Online Inference at Baidu
In this work, we present JIZHI - a Model-as-a-Service system - that per second handles hundreds of millions of online inference requests to huge deep models with more than trillions of sparse parameters, for over twenty real-time recommendation services at Baidu, Inc.
From Distributed Machine Learning to Federated Learning: A Survey
Because of laws or regulations, the distributed data and computing resources cannot be directly shared among different regions or organizations for machine learning tasks.
SMILE: Self-Distilled MIxup for Efficient Transfer LEarning
Performing mixup for transfer learning with pre-trained models however is not that simple, a high capacity pre-trained model with a large fully-connected (FC) layer could easily overfit to the target dataset even with samples-to-labels mixed up.
Interpretable Deep Learning: Interpretation, Interpretability, Trustworthiness, and Beyond
Then, to understand the interpretation results, we also survey the performance metrics for evaluating interpretation algorithms.
Implicit Regularization Effects of Unbiased Random Label Noises with SGD
Random label noises (or observational noises) widely exist in practical machinelearning settings.
Empirical Studies on the Convergence of Feature Spaces in Deep Learning
While deep learning is effective to learn features/representations from data, the distributions of samples in feature spaces learned by various architectures for different training tasks (e. g., latent layers of AEs and feature vectors in CNN classifiers) have not been well-studied or compared.
Can We Use Gradient Norm as a Measure of Generalization Error for Model Selection in Practice?
The recent theoretical investigation (Li et al., 2020) on the upper bound of generalization error of deep neural networks (DNNs) demonstrates the potential of using the gradient norm as a measure that complements validation accuracy for model selection in practice.
Democratizing Evaluation of Deep Model Interpretability through Consensus
Given any task/dataset, Consensus first obtains the interpretation results using existing tools, e. g., LIME (Ribeiro et al., 2016), for every model in the committee, then aggregates the results from the entire committee and approximates the “ground truth” of interpretations through voting.
C-Watcher: A Framework for Early Detection of High-Risk Neighborhoods Ahead of COVID-19 Outbreak
Furthermore, to transfer the firsthand knowledge (witted in epicenters) to the target city before local outbreaks, we adopt a novel adversarial encoder framework to learn "city-invariant" representations from the mobility-related features for precise early detection of high-risk neighborhoods, even before any confirmed cases known, in the target city.
Distance-aware Molecule Graph Attention Network for Drug-Target Binding Affinity Prediction
The hierarchical attentive aggregation can capture spatial dependencies among atoms, as well as fuse the position-enhanced information with the capability of discriminating multiple spatial relations among atoms.
Towards Accurate Knowledge Transfer via Target-awareness Representation Disentanglement
Fine-tuning deep neural networks pre-trained on large scale datasets is one of the most practical transfer learning paradigm given limited quantity of training samples.
XMixup: Efficient Transfer Learning with Auxiliary Samples by Cross-domain Mixup
While the existing multitask learning algorithms need to run backpropagation over both the source and target datasets and usually consume a higher gradient complexity, XMixup transfers the knowledge from source to target tasks more efficiently: for every class of the target task, XMixup selects the auxiliary samples from the source dataset and augments training samples via the simple mixup strategy.
Generating Person Images with Appearance-aware Pose Stylizer
Generation of high-quality person images is challenging, due to the sophisticated entanglements among image factors, e. g., appearance, pose, foreground, background, local details, global structures, etc.
RIFLE: Backpropagation in Depth for Deep Transfer Learning through Re-Initializing the Fully-connected LayEr
RIFLE brings meaningful updates to the weights of deep CNN layers and improves low-level feature learning, while the effects of randomization can be easily converged throughout the overall learning procedure.
Quantifying the Economic Impact of COVID-19 in Mainland China Using Human Mobility Data
While these strategies have effectively dealt with the critical situations of outbreaks, the combination of the pandemic and mobility controls has slowed China's economic growth, resulting in the first quarterly decline of Gross Domestic Product (GDP) since GDP began to be calculated, in 1992.
Rethink the Connections among Generalization, Memorization and the Spectral Bias of DNNs
Over-parameterized deep neural networks (DNNs) with sufficient capacity to memorize random noise can achieve excellent generalization performance, challenging the bias-variance trade-off in classical learning theory.
COLAM: Co-Learning of Deep Neural Networks and Soft Labels via Alternating Minimization
Softening labels of training datasets with respect to data representations has been frequently used to improve the training of deep neural networks (DNNs).
Parameter-Free Style Projection for Arbitrary Style Transfer
This paper further presents a real-time feed-forward model to leverage Style Projection for arbitrary image style transfer, which includes a regularization term for matching the semantics between input contents and stylized outputs.
Curriculum Audiovisual Learning
Associating sound and its producer in complex audiovisual scene is a challenging task, especially when we are lack of annotated training data.
Ultrafast Photorealistic Style Transfer via Neural Architecture Search
Our method consists of a construction step (C-step) to build a photorealistic stylization network and a pruning step (P-step) for acceleration.
SecureGBM: Secure Multi-Party Gradient Boosting
Our experiments using the real-world data showed that SecureGBM can well secure the communication and computation of LightGBM training and inference procedures for the both parties while only losing less than 3% AUC, using the same number of iterations for gradient boosting, on a wide range of benchmark datasets.
Towards Making Deep Transfer Learning Never Hurt
The empirical results show that the proposed descent direction estimation strategy DTNH can always improve the performance of deep transfer learning tasks based on all above regularizers, even when transferring pre-trained weights from inappropriate networks.
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.
On the Noisy Gradient Descent that Generalizes as SGD
The gradient noise of SGD is considered to play a central role in the observed strong generalization abilities of deep learning.
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.
SHE2: Stochastic Hamiltonian Exploration and Exploitation for Derivative-Free Optimization
Derivative-free optimization (DFO) using trust region methods is frequently used for machine learning applications, such as (hyper-)parameter optimization without the derivatives of objective functions known.
DELTA: DEep Learning Transfer using Feature Map with Attention for Convolutional Networks
Instead of constraining the weights of neural network, DELTA aims to preserve the outer layer outputs of the target network.
Quasi-potential as an implicit regularizer for the loss function in the stochastic gradient descent
We show in this case that the quasi-potential function is related to the noise covariance structure of SGD via a partial differential equation of Hamilton-Jacobi type.
Neural Control Variates for Variance Reduction
In statistics and machine learning, approximation of an intractable integration is often achieved by using the unbiased Monte Carlo estimator, but the variances of the estimation are generally high in many applications.
CSWA: Aggregation-Free Spatial-Temporal Community Sensing
In this paper, we present a novel community sensing paradigm -- {C}ommunity {S}ensing {W}ithout {A}ggregation}.
FWDA: a Fast Wishart Discriminant Analysis with its Application to Electronic Health Records Data Classification
Classical LDA for EHR data classification, however, suffers from two handicaps: the ill-posed estimation of LDA parameters (e. g., covariance matrix), and the "linear inseparability" of EHR data.
Improving Covariance-Regularized Discriminant Analysis for EHR-based Predictive Analytics of Diseases
In this paper, we revised the problem of predictive analysis of disease using personal EHR data and LDA classifier.
CT-Mapper: Mapping Sparse Multimodal Cellular Trajectories using a Multilayer Transportation Network
One of the main strengths of CT-Mapper is its capability to map noisy sparse cellular multimodal trajectories over a multilayer transportation network where the layers have different physical properties and not only to map trajectories associated with a single layer.
