Search Results for author:
Found 35 papers, 18 papers with code
Towards Understanding and Quantifying Uncertainty for Text-to-Image Generation
Alongside adapting existing approaches designed to measure uncertainty in the image space, we also introduce Prompt-based UNCertainty Estimation for T2I models (PUNC), a novel method leveraging Large Vision-Language Models (LVLMs) to better address uncertainties arising from the semantics of the prompt and generated images.
Collaborative Instance Navigation: Leveraging Agent Self-Dialogue to Minimize User Input
Existing embodied instance goal navigation tasks, driven by natural language, assume human users to provide complete and nuanced instance descriptions prior to the navigation, which can be impractical in the real world as human instructions might be brief and ambiguous.
Benchmarking XAI Explanations with Human-Aligned Evaluations
Our first key contribution is a human evaluation of XAI explanations on four diverse datasets (COCO, Pascal Parts, Cats Dogs Cars, and MonumAI) which constitutes the first large-scale benchmark dataset for XAI, with annotations at both the image and concept levels.
Double Descent Meets Out-of-Distribution Detection: Theoretical Insights and Empirical Analysis on the role of model complexity
While overparameterization is known to benefit generalization, its impact on Out-Of-Distribution (OOD) detection is less understood.
Out-of-Distribution Detection
Out of Distribution (OOD) Detection
Organizing Unstructured Image Collections using Natural Language
Our framework, Text Driven Semantic Multiple Clustering (TeDeSC), uses text as a proxy to concurrently reason over large image collections, discover partitioning criteria, expressed in natural language, and reveal semantic substructures.
Frustratingly Easy Test-Time Adaptation of Vision-Language Models
Thanks to its simplicity and comparatively negligible computation, ZERO can serve as a strong baseline for future work in this field.
Hierarchical Light Transformer Ensembles for Multimodal Trajectory Forecasting
Accurate trajectory forecasting is crucial for the performance of various systems, such as advanced driver-assistance systems and self-driving vehicles.
Towards Understanding Why Label Smoothing Degrades Selective Classification and How to Fix It
We then demonstrate the empirical effectiveness of post-hoc logit normalisation for recovering lost SC performance caused by LS.
Make Me a BNN: A Simple Strategy for Estimating Bayesian Uncertainty from Pre-trained Models
Deep Neural Networks (DNNs) are powerful tools for various computer vision tasks, yet they often struggle with reliable uncertainty quantification - a critical requirement for real-world applications.
CLIP-QDA: An Explainable Concept Bottleneck Model
In this paper, we introduce an explainable algorithm designed from a multi-modal foundation model, that performs fast and explainable image classification.
A Symmetry-Aware Exploration of Bayesian Neural Network Posteriors
The distribution of the weights of modern deep neural networks (DNNs) - crucial for uncertainty quantification and robustness - is an eminently complex object due to its extremely high dimensionality.
NECO: NEural Collapse Based Out-of-distribution detection
Detecting out-of-distribution (OOD) data is a critical challenge in machine learning due to model overconfidence, often without awareness of their epistemological limits.
How To Effectively Train An Ensemble Of Faster R-CNN Object Detectors To Quantify Uncertainty
This paper presents a new approach for training two-stage object detection ensemble models, more specifically, Faster R-CNN models to estimate uncertainty.
Scaling for Training Time and Post-hoc Out-of-distribution Detection Enhancement
The capacity of a modern deep learning system to determine if a sample falls within its realm of knowledge is fundamental and important.
Ranked #1 on
Out-of-Distribution Detection
on Far-OOD
Out-of-Distribution Detection
Out of Distribution (OOD) Detection
InfraParis: A multi-modal and multi-task autonomous driving dataset
Current deep neural networks (DNNs) for autonomous driving computer vision are typically trained on specific datasets that only involve a single type of data and urban scenes.
The Robust Semantic Segmentation UNCV2023 Challenge Results
This paper outlines the winning solutions employed in addressing the MUAD uncertainty quantification challenge held at ICCV 2023.
Improving CLIP Robustness with Knowledge Distillation and Self-Training
This paper examines the robustness of a multi-modal computer vision model, CLIP (Contrastive Language-Image Pretraining), in the context of unsupervised learning.
Discretization-Induced Dirichlet Posterior for Robust Uncertainty Quantification on Regression
In this work, we propose a generalized AuxUE scheme for more robust uncertainty quantification on regression tasks.
Learning to Generate Training Datasets for Robust Semantic Segmentation
We propose a novel approach to improve the robustness of semantic segmentation techniques by leveraging the synergy between label-to-image generators and image-to-label segmentation models.
Packed-Ensembles for Efficient Uncertainty Estimation
Deep Ensembles (DE) are a prominent approach for achieving excellent performance on key metrics such as accuracy, calibration, uncertainty estimation, and out-of-distribution detection.
Greybox XAI: a Neural-Symbolic learning framework to produce interpretable predictions for image classification
As a result, there is a widespread agreement on the importance of endowing Deep Learning models with explanatory capabilities so that they can themselves provide an answer to why a particular prediction was made.
Explainable artificial intelligence
Explainable Artificial Intelligence (XAI)
+1
Latent Discriminant deterministic Uncertainty
Predictive uncertainty estimation is essential for deploying Deep Neural Networks in real-world autonomous systems.
MUAD: Multiple Uncertainties for Autonomous Driving, a benchmark for multiple uncertainty types and tasks
However, disentangling the different types and sources of uncertainty is non trivial for most datasets, especially since there is no ground truth for uncertainty.
On Monocular Depth Estimation and Uncertainty Quantification using Classification Approaches for Regression
To this end, this paper will introduce a taxonomy and summary of CAR approaches, a new uncertainty estimation solution for CAR, and a set of experiments on depth accuracy and uncertainty quantification for CAR-based models on KITTI dataset.
A study of deep perceptual metrics for image quality assessment
Several metrics exist to quantify the similarity between images, but they are inefficient when it comes to measure the similarity of highly distorted images.
SLURP: Side Learning Uncertainty for Regression Problems
It has become critical for deep learning algorithms to quantify their output uncertainties to satisfy reliability constraints and provide accurate results.
Robust Semantic Segmentation with Superpixel-Mix
Along with predictive performance and runtime speed, reliability is a key requirement for real-world semantic segmentation.
Learning a Discriminant Latent Space with Neural Discriminant Analysis
NDA transforms deep features to become more discriminative and, therefore, improves the performances in various tasks.
Learning Deep Morphological Networks with Neural Architecture Search
Using a combination of linear and non-linear procedures is critical for generating a sufficiently deep feature space.
EXplainable Neural-Symbolic Learning (X-NeSyL) methodology to fuse deep learning representations with expert knowledge graphs: the MonuMAI cultural heritage use case
We tackle such problem by considering the symbolic knowledge is expressed in form of a domain expert knowledge graph.
Encoding the latent posterior of Bayesian Neural Networks for uncertainty quantification
Bayesian neural networks (BNNs) have been long considered an ideal, yet unscalable solution for improving the robustness and the predictive uncertainty of deep neural networks.
Ranked #142 on
Image Classification
on CIFAR-10
One Versus all for deep Neural Network Incertitude (OVNNI) quantification
This is due to the fact that modern DNNs are usually uncalibrated and we cannot characterize their epistemic uncertainty.
TRADI: Tracking deep neural network weight distributions for uncertainty estimation
During training, the weights of a Deep Neural Network (DNN) are optimized from a random initialization towards a nearly optimum value minimizing a loss function.
Supervised Deep Kriging for Single-Image Super-Resolution
We propose a novel single-image super-resolution approach based on the geostatistical method of kriging.
Hyperspectral Image Classification with Support Vector Machines on Kernel Distribution Embeddings
We propose a novel approach for pixel classification in hyperspectral images, leveraging on both the spatial and spectral information in the data.
