Search Results for author:
Found 31 papers, 8 papers with code
$α$-TCVAE: On the relationship between Disentanglement and Diversity
The proposed TC bound is grounded in information theory constructs, generalizes the $\beta$-VAE lower bound, and can be reduced to a convex combination of the known variational information bottleneck (VIB) and conditional entropy bottleneck (CEB) terms.
Object-Centric Temporal Consistency via Conditional Autoregressive Inductive Biases
Unsupervised object-centric learning from videos is a promising approach towards learning compositional representations that can be applied to various downstream tasks, such as prediction and reasoning.
Masked Generative Priors Improve World Models Sequence Modelling Capabilities
Building on the Efficient Stochastic Transformer-based World Models (STORM) architecture, we replace the traditional MLP prior with a Masked Generative Prior (e. g., MaskGIT Prior) and introduce GIT-STORM.
Bayesian-LoRA: LoRA based Parameter Efficient Fine-Tuning using Optimal Quantization levels and Rank Values trough Differentiable Bayesian Gates
In this work, we propose Bayesian-LoRA which approaches low-rank adaptation and quantization from a Bayesian perspective by employing a prior distribution on both quantization levels and rank values.
Precipitation Nowcasting Using Physics Informed Discriminator Generative Models
The proposed model adopts a GAN structure, featuring a Vector Quantization Generative Adversarial Network (VQ-GAN) and a Transformer as the generator, with a temporal discriminator serving as the discriminator.
Extreme Precipitation Nowcasting using Transformer-based Generative Models
This paper presents an innovative approach to extreme precipitation nowcasting by employing Transformer-based generative models, namely NowcastingGPT with Extreme Value Loss (EVL) regularization.
Slot-VAE: Object-Centric Scene Generation with Slot Attention
Slot attention has shown remarkable object-centric representation learning performance in computer vision tasks without requiring any supervision.
MERLIon CCS Challenge Evaluation Plan
This paper introduces the inaugural Multilingual Everyday Recordings- Language Identification on Code-Switched Child-Directed Speech (MERLIon CCS) Challenge, focused on developing robust language identification and language diarization systems that are reliable for non-standard, accented, spontaneous code-switched, child-directed speech collected via Zoom.
Investigating model performance in language identification: beyond simple error statistics
These overview metrics do not provide information about model performance at the level of individual speakers, recordings, or units of speech with different linguistic characteristics.
MERLIon CCS Challenge: A English-Mandarin code-switching child-directed speech corpus for language identification and diarization
To enhance the reliability and robustness of language identification (LID) and language diarization (LD) systems for heterogeneous populations and scenarios, there is a need for speech processing models to be trained on datasets that feature diverse language registers and speech patterns.
TC-VAE: Uncovering Out-of-Distribution Data Generative Factors
We show that the proposed model is able to uncover OOD generative factors on different datasets and outperforms on average the related baselines in terms of downstream disentanglement metrics.
PEM: Perception Error Model for Virtual Testing of Autonomous Vehicles
In this article, we define Perception Error Models (PEM), a virtual simulation component that can enable the analysis of the impact of perception errors on AV safety, without the need to model the sensors themselves.
CoPEM: Cooperative Perception Error Models for Autonomous Driving
In this paper, we introduce the notion of Cooperative Perception Error Models (coPEMs) towards achieving an effective and efficient integration of V2X solutions within a virtual test environment.
Learning to Solve Multiple-TSP with Time Window and Rejections via Deep Reinforcement Learning
We propose a manager-worker framework based on deep reinforcement learning to tackle a hard yet nontrivial variant of Travelling Salesman Problem (TSP), \ie~multiple-vehicle TSP with time window and rejections (mTSPTWR), where customers who cannot be served before the deadline are subject to rejections.
Transformer Convolutional Neural Networks for Automated Artifact Detection in Scalp EEG
Next, for each of these five types of artifacts, we combine the output of these channel-wise detectors to detect artifacts in multi-channel EEG segments.
Six-center Assessment of CNN-Transformer with Belief Matching Loss for Patient-independent Seizure Detection in EEG
In this study, we propose a patient-independent seizure detector to automatically detect seizures in both scalp EEG and intracranial EEG (iEEG).
Enhance Language Identification using Dual-mode Model with Knowledge Distillation
In this paper, we propose to employ a dual-mode framework on the x-vector self-attention (XSA-LID) model with knowledge distillation (KD) to enhance its language identification (LID) performance for both long and short utterances.
R3L: Connecting Deep Reinforcement Learning to Recurrent Neural Networks for Image Denoising via Residual Recovery
To benchmark the effectiveness of reinforcement learning in R3L, we train a recurrent neural network with the same architecture for residual recovery using the deterministic loss, thus to analyze how the two different training strategies affect the denoising performance.
Ranked #1 on
Image Denoising
on BSD68 sigma30
ADIS-GAN: Affine Disentangled GAN
This paper proposes Affine Disentangled GAN (ADIS-GAN), which is a Generative Adversarial Network that can explicitly disentangle affine transformations in a self-supervised and rigorous manner.
Multi-center validation study of automated classification of pathological slowing in adult scalp electroencephalograms via frequency features
The TDS, SLDS, and DLDS performs prediction via detecting slowing at individual channels, and those detections are arranged in histograms for detection of slowing at the segment- and EEG-level.
Efficient Variational Bayes Learning of Graphical Models with Smooth Structural Changes
Estimating time-varying graphical models are of paramount importance in various social, financial, biological, and engineering systems, since the evolution of such networks can be utilized for example to spot trends, detect anomalies, predict vulnerability, and evaluate the impact of interventions.
On the Quality Requirements of Demand Prediction for Dynamic Public Transport
Our results suggest that the optimized performance is mainly affected by the skew of the noise distribution and the presence of infrequently large prediction errors.
Modeling Perception Errors towards Robust Decision Making in Autonomous Vehicles
Sensing and Perception (S&P) is a crucial component of an autonomous system (such as a robot), especially when deployed in highly dynamic environments where it is required to react to unexpected situations.
Factored Latent-Dynamic Conditional Random Fields for Single and Multi-label Sequence Modeling
In addition, LSTM based models display inconsistent performance across validation and test data, and pose diffculty to select models on validation data during our experiments.
Context Model for Pedestrian Intention Prediction using Factored Latent-Dynamic Conditional Random Fields
Such systems call for early and accurate prediction of a pedestrian's crossing/not-crossing behaviour in front of the vehicle.
Affine Disentangled GAN for Interpretable and Robust AV Perception
Autonomous vehicles (AV) have progressed rapidly with the advancements in computer vision algorithms.
Online Predictive Optimization Framework for Stochastic Demand-Responsive Transit Services
This study develops an online predictive optimization framework for dynamically operating a transit service in an area of crowd movements.
Actor-Action Semantic Segmentation with Region Masks
One major challenge for this task is that when an actor performs an action, different body parts of the actor provide different types of cues for the action category and may receive inconsistent action labeling when they are labeled independently.
Multi-atomic Annealing Heuristic for Static Dial-a-ride Problem
It is observed that MATA attains a first feasible solution 29. 8 to 65. 1% faster, and obtains a final solution that is 3. 9 to 5. 2% better, when compared to other algorithms within 60 sec.
An Improved Tabu Search Heuristic for Static Dial-A-Ride Problem
Multi-vehicle routing has become increasingly important with the rapid development of autonomous vehicle technology.
Neurology-as-a-Service for the Developing World
In this work, we present a cloud-based deep neural network approach to provide decision support for non-specialist physicians in EEG analysis and interpretation.
