Search Results for author:
Found 91 papers, 31 papers with code
Benchmarking Adversarial Robustness of Image Shadow Removal with Shadow-adaptive Attacks
This is primarily due to the unique characteristic of spatially varying illumination within shadow images.
Progressive Divide-and-Conquer via Subsampling Decomposition for Accelerated MRI
Starting from decomposing the original maximum-a-posteriori problem of accelerated MRI, we present a rigorous derivation of the proposed PDAC framework, which could be further unfolded into an end-to-end trainable network.
MM1: Methods, Analysis & Insights from Multimodal LLM Pre-training
Through careful and comprehensive ablations of the image encoder, the vision language connector, and various pre-training data choices, we identified several crucial design lessons.
Ranked #18 on
Visual Question Answering
on MM-Vet
Recurrent Drafter for Fast Speculative Decoding in Large Language Models
In this paper, we introduce an improved approach of speculative decoding aimed at enhancing the efficiency of serving large language models.
Learn Suspected Anomalies from Event Prompts for Video Anomaly Detection
Most models for weakly supervised video anomaly detection (WS-VAD) rely on multiple instance learning, aiming to distinguish normal and abnormal snippets without specifying the type of anomaly.
Security Code Review by LLMs: A Deep Dive into Responses
To explore the challenges of applying LLMs in practical code review for security defect detection, this study compared the detection performance of three state-of-the-art LLMs (Gemini Pro, GPT-4, and GPT-3. 5) under five prompts on 549 code files that contain security defects from real-world code reviews.
A Prompt Learning Framework for Source Code Summarization
PromptCS trains a prompt agent that can generate continuous prompts to unleash the potential for LLMs in code summarization.
Mixture of Gaussian-distributed Prototypes with Generative Modelling for Interpretable Image Classification
Such an approach enables the learning of more powerful prototype representations since each learned prototype will own a measure of variability, which naturally reduces the sparsity given the spread of the distribution around each prototype, and we also integrate a prototype diversity objective function into the GMM optimisation to reduce redundancy.
Wildfire Smoke Detection with Cross Contrast Patch Embedding
By using two different negative instance sampling strategies on positive images and negative images respectively, the problem of supervision signal confusion caused by label diversity in the process of network training is alleviated.
Spec-NeRF: Multi-spectral Neural Radiance Fields
We propose Multi-spectral Neural Radiance Fields(Spec-NeRF) for jointly reconstructing a multispectral radiance field and spectral sensitivity functions(SSFs) of the camera from a set of color images filtered by different filters.
Partial Label Supervision for Agnostic Generative Noisy Label Learning
Second, we introduce a new Partial Label Supervision (PLS) for noisy label learning that accounts for both clean label coverage and uncertainty.
Ranked #5 on
Learning with noisy labels
on CIFAR-10N-Random3
Unraveling Instance Associations: A Closer Look for Audio-Visual Segmentation
We show empirical results that demonstrate the effectiveness of our benchmark.
Netflix and Forget: Efficient and Exact Machine Unlearning from Bi-linear Recommendations
Without incurring the cost of re-training, and without degrading the model unnecessarily, we develop Unlearn-ALS by making a few key modifications to the fine-tuning procedure under Alternating Least Squares optimisation, thus applicable to any bi-linear models regardless of the training procedure.
Efficient Attention via Control Variates
Built upon previous progress of RFA, we characterize this gap through the lens of control variates and show that RFA can be decomposed into a sum of multiple control variate estimators for each element in the sequence.
BRAIxDet: Learning to Detect Malignant Breast Lesion with Incomplete Annotations
Given the large size of such datasets, researchers usually face a dilemma with the weakly annotated subset: to not use it or to fully annotate it.
Learning Support and Trivial Prototypes for Interpretable Image Classification
Prototypical part network (ProtoPNet) methods have been designed to achieve interpretable classification by associating predictions with a set of training prototypes, which we refer to as trivial prototypes because they are trained to lie far from the classification boundary in the feature space.
Explainable Artificial Intelligence (XAI)
Image Classification
+1
Boundary-Aware Divide and Conquer: A Diffusion-Based Solution for Unsupervised Shadow Removal
Recent deep learning methods have achieved superior results in shadow removal.
Asymmetric Co-teaching with Multi-view Consensus for Noisy Label Learning
Also, the new sample selection is based on multi-view consensus, which uses the label views from training labels and model predictions to divide the training set into clean and noisy for training the multi-class model and to re-label the training samples with multiple top-ranked labels for training the multi-label model.
ShadowDiffusion: When Degradation Prior Meets Diffusion Model for Shadow Removal
Recent deep learning methods have achieved promising results in image shadow removal.
Supervised Pretraining for Molecular Force Fields and Properties Prediction
Experiments show that, compared to training from scratch, fine-tuning the pretrained model can significantly improve the performance for seven molecular property prediction tasks and two force field tasks.
Learning Regularized Positional Encoding for Molecular Prediction
To model the complex nonlinearity in predicting molecular properties in an more end-to-end approach, we propose to encode the positional quantities with a learnable embedding that is continuous and differentiable.
Learning to Counterfactually Explain Recommendations
The key idea is to train a surrogate model to learn the effect of removing a subset of user history on the recommendation.
Knowledge Distillation to Ensemble Global and Interpretable Prototype-Based Mammogram Classification Models
On the other hand, prototype-based models improve interpretability by associating predictions with training image prototypes, but they are less accurate than global models and their prototypes tend to have poor diversity.
Multi-view Local Co-occurrence and Global Consistency Learning Improve Mammogram Classification Generalisation
When analysing screening mammograms, radiologists can naturally process information across two ipsilateral views of each breast, namely the cranio-caudal (CC) and mediolateral-oblique (MLO) views.
Collaborative Anomaly Detection
In recommendation systems, items are likely to be exposed to various users and we would like to learn about the familiarity of a new user with an existing item.
DPAUC: Differentially Private AUC Computation in Federated Learning
Federated learning (FL) has gained significant attention recently as a privacy-enhancing tool to jointly train a machine learning model by multiple participants.
REPNP: Plug-and-Play with Deep Reinforcement Learning Prior for Robust Image Restoration
To this end, we propose a novel deep reinforcement learning (DRL) based PnP framework, dubbed RePNP, by leveraging a light-weight DRL-based denoiser for robust image restoration tasks.
Differentially Private Multi-Party Data Release for Linear Regression
Differentially Private (DP) data release is a promising technique to disseminate data without compromising the privacy of data subjects.
Differentially Private AUC Computation in Vertical Federated Learning
In this work, we propose two evaluation algorithms that can more accurately compute the widely used AUC (area under curve) metric when using label DP in vFL.
Linear Complexity Randomized Self-attention Mechanism
By combining the expressiveness in RA and the efficiency in RFA, we develop a novel linear complexity self-attention mechanism called linear randomized attention (LARA).
Translation Consistent Semi-supervised Segmentation for 3D Medical Images
The most successful SSL approaches are based on consistency learning that minimises the distance between model responses obtained from perturbed views of the unlabelled data.
Contrastive Transformer-based Multiple Instance Learning for Weakly Supervised Polyp Frame Detection
Current polyp detection methods from colonoscopy videos use exclusively normal (i. e., healthy) training images, which i) ignore the importance of temporal information in consecutive video frames, and ii) lack knowledge about the polyps.
Unsupervised Anomaly Detection in Medical Images with a Memory-augmented Multi-level Cross-attentional Masked Autoencoder
Our UAD approach, the memory-augmented multi-level cross-attentional masked autoencoder (MemMC-MAE), is a transformer-based approach, consisting of a novel memory-augmented self-attention operator for the encoder and a new multi-level cross-attention operator for the decoder.
Differentially Private Label Protection in Split Learning
Split learning is a distributed training framework that allows multiple parties to jointly train a machine learning model over vertically partitioned data (partitioned by attributes).
BoMD: Bag of Multi-label Descriptors for Noisy Chest X-ray Classification
Deep learning methods have shown outstanding classification accuracy in medical imaging problems, which is largely attributed to the availability of large-scale datasets manually annotated with clean labels.
Label Leakage and Protection from Forward Embedding in Vertical Federated Learning
As the raw labels often contain highly sensitive information, some recent work has been proposed to prevent the label leakage from the backpropagated gradients effectively in vFL.
Counterfactually Evaluating Explanations in Recommender Systems
Modern recommender systems face an increasing need to explain their recommendations.
Learning to Simulate Unseen Physical Systems with Graph Neural Networks
Simulation of the dynamics of physical systems is essential to the development of both science and engineering.
Learning Large-Time-Step Molecular Dynamics with Graph Neural Networks
Molecular dynamics (MD) simulation predicts the trajectory of atoms by solving Newton's equation of motion with a numeric integrator.
Nonuniform Negative Sampling and Log Odds Correction with Rare Events Data
We first prove that, with imbalanced data, the available information about unknown parameters is only tied to the relatively small number of positive instances, which justifies the usage of negative sampling.
Heterogeneous relational message passing networks for molecular dynamics simulations
With many frameworks based on message passing neural networks proposed to predict molecular and bulk properties, machine learning methods have tremendously shifted the paradigms of computational sciences underpinning physics, material science, chemistry, and biology.
Dynamic Relevance Learning for Few-Shot Object Detection
By adjusting the prediction distribution of the base detector using the output of this GCN, the proposed model serves as a hard auxiliary classification task, which guides the detector to improve the class representation implicitly.
Defending against Reconstruction Attack in Vertical Federated Learning
Recently researchers have studied input leakage problems in Federated Learning (FL) where a malicious party can reconstruct sensitive training inputs provided by users from shared gradient.
AutoLoss: Automated Loss Function Search in Recommendations
Unlike existing algorithms, the proposed controller can adaptively generate the loss probabilities for different data examples according to their varied convergence behaviors.
Vertical Federated Learning without Revealing Intersection Membership
In this paper, we propose a vFL framework based on Private Set Union (PSU) that allows each party to keep sensitive membership information to itself.
Efficient state and parameter estimation for high-dimensional nonlinear system identification with application to MEG brain network modeling
Intuitively, our approach consists of solving for the parameters that generate the most accurate state estimator (Extended Kalman Filter).
NVUM: Non-Volatile Unbiased Memory for Robust Medical Image Classification
In this paper, we propose a new training module called Non-Volatile Unbiased Memory (NVUM), which non-volatility stores running average of model logits for a new regularization loss on noisy multi-label problem.
Image Classification with Label Noise
Learning with noisy labels
+1
Label Leakage and Protection in Two-party Split Learning
Two-party split learning is a popular technique for learning a model across feature-partitioned data.
Symmetry-adapted graph neural networks for constructing molecular dynamics force fields
Molecular dynamics is a powerful simulation tool to explore material properties.
Abrupt switching of the anomalous Hall effect by field-rotation in nonmagnetic ZrTe5
The angular dependence of the Hall resistivity approaches a signum function, persisting down to an extremely low field of 0. 03 T. By varying the carrier density of ZrTe5 over three orders of magnitude, we show that this singular behavior is due to the anomalous Hall effect generated by the ultra-dilute massive Dirac carriers in the quantum limit of Pauli paramagnetism when the Zeeman energy exceeds the Fermi energy.
Mesoscale and Nanoscale Physics
Deep Retrieval: An End-to-End Structure Model for Large-Scale Recommendations
With the model learnt, a beam search over the latent codes is performed to retrieve the top candidates.
Theory of Dirac spin liquids on spin-$S$ triangular lattice: possible application to $α$-CrOOH(D)
We argue that in the most natural scenario, a spin-$S$ system realizes a $U(2S)$ DSL, described at low energy by gapless Dirac fermions coupled with an emergent $U(2S)$ gauge field (also known as $U(2S)$ QCD$_3$).
Strongly Correlated Electrons
Towards Earnings Call and Stock Price Movement
Earnings calls are hosted by management of public companies to discuss the company's financial performance with analysts and investors.
Deep Retrieval: Learning A Retrievable Structure for Large-Scale Recommendations
With the model learnt, a beam search over the structure is performed to retrieve the top candidates for reranking.
AutoEmb: Automated Embedding Dimensionality Search in Streaming Recommendations
Deep learning based recommender systems (DLRSs) often have embedding layers, which are utilized to lessen the dimensionality of categorical variables (e. g. user/item identifiers) and meaningfully transform them in the low-dimensional space.
Learning to Structure Long-term Dependence for Sequential Recommendation
To better model the long-term dependence structure, we propose a GatedLongRec solution in this work.
Short-Term Temporal Convolutional Networks for Dynamic Hand Gesture Recognition
Subsequently, in temporal analysis, we use TCNs to extract temporal features and employ improved Squeeze-and-Excitation Networks (SENets) to strengthen the representational power of temporal features from each TCNs' layers.
Multi-Domain Neural Machine Translation with Word-Level Adaptive Layer-wise Domain Mixing
To overcome this limitation, we propose a novel multi-domain NMT model using individual modules for each domain, on which we apply word-level, adaptive and layer-wise domain mixing.
Feature Partitioning for Efficient Multi-Task Architectures
Multi-task learning holds the promise of less data, parameters, and time than training of separate models.
Neural Logic Machines
We propose the Neural Logic Machine (NLM), a neural-symbolic architecture for both inductive learning and logic reasoning.
Prior-aware Neural Network for Partially-Supervised Multi-Organ Segmentation
Accurate multi-organ abdominal CT segmentation is essential to many clinical applications such as computer-aided intervention.
Doubly Sparse: Sparse Mixture of Sparse Experts for Efficient Softmax Inference
In this paper, we present a novel softmax inference speedup method, Doubly Sparse Softmax (DS-Softmax), that leverages sparse mixture of sparse experts to efficiently retrieve top-k classes.
Neural Phrase-to-Phrase Machine Translation
We also design an efficient dynamic programming algorithm to decode segments that allows the model to be trained faster than the existing neural phrase-based machine translation method by Huang et al. (2018).
Fully Supervised Speaker Diarization
In this paper, we propose a fully supervised speaker diarization approach, named unbounded interleaved-state recurrent neural networks (UIS-RNN).
Ranked #1 on
Speaker Diarization
on Hub5'00 CallHome
Rate Distortion For Model Compression: From Theory To Practice
Theoretically, we prove that the proposed scheme is optimal for compressing one-hidden-layer ReLU neural networks.
Adaptive Mixture of Low-Rank Factorizations for Compact Neural Modeling
Modern deep neural networks have a large amount of weights, which make them difficult to deploy on computation constrained devices such as mobile phones.
Subgoal Discovery for Hierarchical Dialogue Policy Learning
Experiments with simulated and real users show that our approach performs competitively against a state-of-the-art method that requires human-defined subgoals.
Attention-based Graph Neural Network for Semi-supervised Learning
Recently popularized graph neural networks achieve the state-of-the-art accuracy on a number of standard benchmark datasets for graph-based semi-supervised learning, improving significantly over existing approaches.
Ranked #10 on
Graph Regression
on Lipophilicity
Q-LDA: Uncovering Latent Patterns in Text-based Sequential Decision Processes
In sequential decision making, it is often important and useful for end users to understand the underlying patterns or causes that lead to the corresponding decisions.
Thoracic Disease Identification and Localization with Limited Supervision
Accurate identification and localization of abnormalities from radiology images play an integral part in clinical diagnosis and treatment planning.
Model Distillation with Knowledge Transfer from Face Classification to Alignment and Verification
The idea is to make a small student network imitate the target of a large teacher network, then the student network can be competitive to the teacher one.
How to Train Triplet Networks with 100K Identities?
However, as the number of identities becomes extremely large, the training will suffer from bad local minima because effective hard triplets are difficult to be found.
Towards Neural Phrase-based Machine Translation
In this paper, we present Neural Phrase-based Machine Translation (NPMT).
Ranked #7 on
Machine Translation
on IWSLT2015 English-German
Scaffolding Networks: Incremental Learning and Teaching Through Questioning
We introduce a new paradigm of learning for reasoning, understanding, and prediction, as well as the scaffolding network to implement this paradigm.
Sequence Modeling via Segmentations
The probability of a segmented sequence is calculated as the product of the probabilities of all its segments, where each segment is modeled using existing tools such as recurrent neural networks.
TopicRNN: A Recurrent Neural Network with Long-Range Semantic Dependency
The proposed TopicRNN model integrates the merits of RNNs and latent topic models: it captures local (syntactic) dependencies using an RNN and global (semantic) dependencies using latent topics.
Scalable Modeling of Conversational-role based Self-presentation Characteristics in Large Online Forums
Online discussion forums are complex webs of overlapping subcommunities (macrolevel structure, across threads) in which users enact different roles depending on which subcommunity they are participating in within a particular time point (microlevel structure, within threads).
Deep Speech 2: End-to-End Speech Recognition in English and Mandarin
We show that an end-to-end deep learning approach can be used to recognize either English or Mandarin Chinese speech--two vastly different languages.
A General Method for Robust Bayesian Modeling
Robust Bayesian models are appealing alternatives to standard models, providing protection from data that contains outliers or other departures from the model assumptions.
Embarrassingly Parallel Variational Inference in Nonconjugate Models
We develop a parallel variational inference (VI) procedure for use in data-distributed settings, where each machine only has access to a subset of data and runs VI independently, without communicating with other machines.
Dynamic Language Models for Streaming Text
We present a probabilistic language model that captures temporal dynamics and conditions on arbitrary non-linguistic context features.
Variance Reduction for Stochastic Gradient Optimization
We demonstrate how to construct the control variate for two practical problems using stochastic gradient optimization.
Modeling Overlapping Communities with Node Popularities
We evaluate the link prediction accuracy of our algorithm on eight real-world networks with up to 60, 000 nodes, and 24 benchmark networks.
Asymptotically Exact, Embarrassingly Parallel MCMC
This embarrassingly parallel algorithm allows each machine to act independently on a subset of the data (without communication) until the final combination stage.
Truncation-free Online Variational Inference for Bayesian Nonparametric Models
We present a truncation-free online variational inference algorithm for Bayesian nonparametric models.
Nested Hierarchical Dirichlet Processes
We develop a nested hierarchical Dirichlet process (nHDP) for hierarchical topic modeling.
Stochastic Variational Inference
We develop stochastic variational inference, a scalable algorithm for approximating posterior distributions.
Continuous Time Dynamic Topic Models
In contrast to the cDTM, the original discrete-time dynamic topic model (dDTM) requires that time be discretized.
Fast Large-scale Mixture Modeling with Component-specific Data Partitions
Remarkably easy implementation and guaranteed convergence has made the EM algorithm one of the most used algorithms for mixture modeling.
Variational Inference for the Nested Chinese Restaurant Process
The nested Chinese restaurant process (nCRP) is a powerful nonparametric Bayesian model for learning tree-based hierarchies from data.
Decoupling Sparsity and Smoothness in the Discrete Hierarchical Dirichlet Process
We present a nonparametric hierarchical Bayesian model of document collections that decouples sparsity and smoothness in the component distributions (i. e., the ``topics).
