Search Results for author:
Found 19 papers, 8 papers with code
Layerwise Early Stopping for Test Time Adaptation
In this paper, we propose Layerwise EArly STopping (LEAST) for TTA to address this problem.
Attention Meets Post-hoc Interpretability: A Mathematical Perspective
Attention-based architectures, in particular transformers, are at the heart of a technological revolution.
Visual Objectification in Films: Towards a New AI Task for Video Interpretation
In film gender studies, the concept of 'male gaze' refers to the way the characters are portrayed on-screen as objects of desire rather than subjects.
Faithful and Robust Local Interpretability for Textual Predictions
Interpretability is essential for machine learning models to be trusted and deployed in critical domains.
Another Point of View on Visual Speech Recognition
Standard Visual Speech Recognition (VSR) systems directly process images as input features without any apriori link between raw pixel data and facial traits.
Ranked #3 on
Landmark-based Lipreading
on LRW
Interpretable Neural-Symbolic Concept Reasoning
Deep learning methods are highly accurate, yet their opaque decision process prevents them from earning full human trust.
Understanding Post-hoc Explainers: The Case of Anchors
In many scenarios, the interpretability of machine learning models is a highly required but difficult task.
Generalised Mutual Information for Discriminative Clustering
In the last decade, recent successes in deep clustering majorly involved the mutual information (MI) as an unsupervised objective for training neural networks with increasing regularisations.
Concept Embedding Models: Beyond the Accuracy-Explainability Trade-Off
Deploying AI-powered systems requires trustworthy models supporting effective human interactions, going beyond raw prediction accuracy.
A Sea of Words: An In-Depth Analysis of Anchors for Text Data
For text data, it proposes to explain a decision by highlighting a small set of words (an anchor) such that the model to explain has similar outputs when they are present in a document.
SMACE: A New Method for the Interpretability of Composite Decision Systems
To explain such decisions, we propose the Semi-Model-Agnostic Contextual Explainer (SMACE), a new interpretability method that combines a geometric approach for decision rules with existing interpretability methods for machine learning models to generate an intuitive feature ranking tailored to the end user.
Active Speaker Detection as a Multi-Objective Optimization with Uncertainty-based Multimodal Fusion
It is now well established from a variety of studies that there is a significant benefit from combining video and audio data in detecting active speakers.
Active Speaker Detection
Audio-Visual Active Speaker Detection
Revisiting Deep Architectures for Head Motion Prediction in 360° Videos
A root-cause analysis of the metrics, datasets and neural architectures shows in particular that (i) the content can inform the prediction for horizons longer than 2 to 3 sec.
Adaptive Bayesian Linear Regression for Automated Machine Learning
To solve a machine learning problem, one typically needs to perform data preprocessing, modeling, and hyperparameter tuning, which is known as model selection and hyperparameter optimization. The goal of automated machine learning (AutoML) is to design methods that can automatically perform model selection and hyperparameter optimization without human interventions for a given dataset.
Textual Deconvolution Saliency (TDS) : a deep tool box for linguistic analysis
In this paper, we propose a new strategy, called Text Deconvolution Saliency (TDS), to visualize linguistic information detected by a CNN for text classification.
Adversarial Active Learning for Deep Networks: a Margin Based Approach
We propose a new active learning strategy designed for deep neural networks.
QBDC: Query by dropout committee for training deep supervised architecture
While the current trend is to increase the depth of neural networks to increase their performance, the size of their training database has to grow accordingly.
Recipe recognition with large multimodal food dataset
We present deep experiments of recipe recognition on our dataset using visual, textual information and fusion.
Assessment of algorithms for mitosis detection in breast cancer histopathology images
The proliferative activity of breast tumors, which is routinely estimated by counting of mitotic figures in hematoxylin and eosin stained histology sections, is considered to be one of the most important prognostic markers.
