Search Results for author:
Found 28 papers, 4 papers with code
Adaptive Convolutional Neural Networks
The quest for increased visual recognition performance has led to the development of highly complex neural networks with very deep topologies.
Uncertainty Quantification in Continual Open-World Learning
We rigorously apply and evaluate COUQ on key sub-tasks in the Continual Open-World: continual novelty detection, uncertainty guided active learning, and uncertainty guided pseudo-labeling for semi-supervised CL.
CONCLAD: COntinuous Novel CLAss Detector
In the field of continual learning, relying on so-called oracles for novelty detection is commonplace albeit unrealistic.
CUAL: Continual Uncertainty-aware Active Learner
Here, we consider a challenging, under-explored and realistic continual adaptation problem: a deployed AI agent is continuously provided with unlabeled data that may contain not only unseen samples of known classes but also samples from novel (unknown) classes.
Enhancing Trust in Large Language Models with Uncertainty-Aware Fine-Tuning
Through rigorous evaluation on multiple free-form question-answering datasets and models, we demonstrate that our uncertainty-aware fine-tuning approach yields better calibrated uncertainty estimates in natural language generation tasks than fine-tuning with the standard causal language modeling loss.
Rate-Distortion Theory in Coding for Machines and its Application
To meet this growing demand, several methods have been developed for image and video coding for machines.
Neural Rate Estimator and Unsupervised Learning for Efficient Distributed Image Analytics in Split-DNN Models
Optimizing the pipeline for both compression and task-performance requires high-quality estimates of the information-theoretic rate of the intermediate features.
Reliable Multimodal Trajectory Prediction via Error Aligned Uncertainty Optimization
Reliable uncertainty quantification in deep neural networks is very crucial in safety-critical applications such as automated driving for trustworthy and informed decision-making.
FRE: A Fast Method For Anomaly Detection And Segmentation
This paper presents a fast and principled approach for solving the visual anomaly detection and segmentation problem.
A Low-Complexity Approach to Rate-Distortion Optimized Variable Bit-Rate Compression for Split DNN Computing
Split computing has emerged as a recent paradigm for implementation of DNN-based AI workloads, wherein a DNN model is split into two parts, one of which is executed on a mobile/client device and the other on an edge-server (or cloud).
Subspace Modeling for Fast Out-Of-Distribution and Anomaly Detection
This paper presents a fast, principled approach for detecting anomalous and out-of-distribution (OOD) samples in deep neural networks (DNN).
Robust Contrastive Active Learning with Feature-guided Query Strategies
We introduce supervised contrastive active learning (SCAL) and propose efficient query strategies in active learning based on the feature similarity (featuresim) and principal component analysis based feature-reconstruction error (fre) to select informative data samples with diverse feature representations.
Mitigating Sampling Bias and Improving Robustness in Active Learning
This paper presents simple and efficient methods to mitigate sampling bias in active learning while achieving state-of-the-art accuracy and model robustness.
Partially-Supervised Novel Object Captioning Leveraging Context from Paired Data
PS-NOC is agnostic to model architecture, and primarily focuses on the training approach that uses existing fully paired image-caption data and the images with only the novel object detection labels (partially paired data).
Data augmentation to improve robustness of image captioning solutions
In this paper, we study the impact of motion blur, a common quality flaw in real world images, on a state-of-the-art two-stage image captioning solution, and notice a degradation in solution performance as blur intensity increases.
Energy-Based Anomaly Detection and Localization
This brief sketches initial progress towards a unified energy-based solution for the semi-supervised visual anomaly detection and localization problem.
Improving model calibration with accuracy versus uncertainty optimization
Obtaining reliable and accurate quantification of uncertainty estimates from deep neural networks is important in safety-critical applications.
Out-Of-Distribution Detection With Subspace Techniques And Probabilistic Modeling Of Features
We also show that the feature reconstruction error, which is the $L_2$-norm of the difference between the original feature and the pre-image of its embedding, is highly effective for OOD detection and in some cases superior to the log-likelihood scores.
Uncertainty as a Form of Transparency: Measuring, Communicating, and Using Uncertainty
Explainability attempts to provide reasons for a machine learning model's behavior to stakeholders.
B-SCST: Bayesian Self-Critical Sequence Training for Image Captioning
The "baseline" for the policy-gradients in B-SCST is generated by averaging predictive quality metrics (CIDEr-D) of the captions drawn from the distribution obtained using a Bayesian DNN model.
Tree pyramidal adaptive importance sampling
After each new sample operation, a set of tree leaves are subdivided for improving the approximation of the proposal distribution to the target density.
Deep Probabilistic Models to Detect Data Poisoning Attacks
In the second approach, we use Bayesian deep neural networks trained with mean-field variational inference to estimate model uncertainty associated with the predictions.
Probabilistic Modeling of Deep Features for Out-of-Distribution and Adversarial Detection
We present a principled approach for detecting out-of-distribution (OOD) and adversarial samples in deep neural networks.
Specifying Weight Priors in Bayesian Deep Neural Networks with Empirical Bayes
We propose MOdel Priors with Empirical Bayes using DNN (MOPED) method to choose informed weight priors in Bayesian neural networks.
Real-time Approximate Bayesian Computation for Scene Understanding
The underlying generative models are built from realistic simulation software, wrapped in a Bayesian error model for the gap between simulation outputs and real data.
Uncertainty aware audiovisual activity recognition using deep Bayesian variational inference
In the multimodal setting, the proposed framework improved precision-recall AUC by 10. 2% on the subset of MiT dataset as compared to non-Bayesian baseline.
BAR: Bayesian Activity Recognition using variational inference
We show that the Bayesian inference applied to DNNs provide reliable confidence measures for visual activity recognition task as compared to conventional DNNs.
A Greedy Part Assignment Algorithm for Real-time Multi-person 2D Pose Estimation
We propose a greedy part assignment algorithm that exploits the inherent structure of the human body to achieve a lower complexity, compared to any of the prior published works.
