9 citations · 27 across the 15 of their papers we have counts for
19 papers
Co-Learning for Missing Arbitrary Modalities in Multi-modal Classification
Francisco Mena, Dino Ienco, Roberto Interdonato +2
Multi-modal classification leverages complementary information across diverse data sources to enhance predictive performance. However, real-world scenarios subject to operational c…
Evaluating the Interpretability of Sparse Autoencoders with Concept Annotations
Jonas Klotz, Cassio F. Dantas, Pallavi Jain +2
Sparse autoencoders (SAEs) are increasingly used to extract interpretable concepts from vision and vision language models, yet existing evaluation methods largely rely on proxy met…
Metonymy in vision models undermines attention-based interpretability
Ananthu Aniraj, Cassio F. Dantas, Dino Ienco +2
Part-based reasoning is a classical strategy to make a computer vision model directly focus on the object parts that are relevant to the downstream task. In the context of deep lea…
Multi-modal Co-learning for Earth Observation: Enhancing single-modality models via modality collaboration
Francisco Mena, Dino Ienco, Cassio F. Dantas +2
Multi-modal co-learning is emerging as an effective paradigm in machine learning, enabling models to collaboratively learn from different modalities to enhance single-modality pred…
Fire severity and recovery across Europe: insights from forest diversity and landscape metrics
Eatidal Amin, Cassio F. Dantas, Dino Ienco +2
In recent decades, European forests have faced an increased incidence of fire disturbances. This phenomenon is likely to persist, given the rising frequency of extreme events expec…
Two-stage Vision Transformers and Hard Masking offer Robust Object Representations
Ananthu Aniraj, Cassio F. Dantas, Dino Ienco +1
Context can strongly affect object representations, sometimes leading to undesired biases, particularly when objects appear in out-of-distribution backgrounds at inference. At the…
Revisiting Cross-Modal Knowledge Distillation: A Disentanglement Approach for RGBD Semantic Segmentation
Roger Ferrod, Cássio F. Dantas, Luigi Di Caro +1
Multi-modal RGB and Depth (RGBD) data are predominant in many domains such as robotics, autonomous driving and remote sensing. The combination of these multi-modal data enhances en…
Geographical Context Matters: Bridging Fine and Coarse Spatial Information to Enhance Continental Land Cover Mapping
Babak Ghassemi, Cassio Fraga-Dantas, Raffaele Gaetano +4
Land use and land cover mapping from Earth Observation (EO) data is a critical tool for sustainable land and resource management. While advanced machine learning and deep learning…
DisCoM-KD: Cross-Modal Knowledge Distillation via Disentanglement Representation and Adversarial Learning
Dino Ienco, Cassio Fraga Dantas
Cross-modal knowledge distillation (CMKD) refers to the scenario in which a learning framework must handle training and test data that exhibit a modality mismatch, more precisely,…
PDiscoFormer: Relaxing Part Discovery Constraints with Vision Transformers
Ananthu Aniraj, Cassio F. Dantas, Dino Ienco +1
Computer vision methods that explicitly detect object parts and reason on them are a step towards inherently interpretable models. Existing approaches that perform part discovery d…
Semi Supervised Heterogeneous Domain Adaptation via Disentanglement and Pseudo-Labelling
Cassio F. Dantas, Raffaele Gaetano, Dino Ienco
Semi-supervised domain adaptation methods leverage information from a source labelled domain with the goal of generalizing over a scarcely labelled target domain. While this settin…
Reuse out-of-year data to enhance land cover mapping via feature disentanglement and contrastive learning
Cassio F. Dantas, Raffaele Gaetano, Claudia Paris +1
Timely up-to-date land use/land cover (LULC) maps play a pivotal role in supporting agricultural territory management, environmental monitoring and facilitating well-informed and s…
PDiscoNet: Semantically consistent part discovery for fine-grained recognition
Robert van der Klis, Stephan Alaniz, Massimiliano Mancini +4
Fine-grained classification often requires recognizing specific object parts, such as beak shape and wing patterns for birds. Encouraging a fine-grained classification model to fir…
Masking Strategies for Background Bias Removal in Computer Vision Models
Ananthu Aniraj, Cassio F. Dantas, Dino Ienco +1
Models for fine-grained image classification tasks, where the difference between some classes can be extremely subtle and the number of samples per class tends to be low, are parti…
Towards Explainable Land Cover Mapping: a Counterfactual-based Strategy
Cassio F. Dantas, Diego Marcos, Dino Ienco
Counterfactual explanations are an emerging tool to enhance interpretability of deep learning models. Given a sample, these methods seek to find and display to the user similar sam…
Benchopt: Reproducible, efficient and collaborative optimization benchmarks
Thomas Moreau, Mathurin Massias, Alexandre Gramfort +18
Numerical validation is at the core of machine learning research as it allows to assess the actual impact of new methods, and to confirm the agreement between theory and practice.…
Accelerating Non-Negative and Bounded-Variable Linear Regression Algorithms with Safe Screening
Cassio F. Dantas, Emmanuel Soubies, Cédric Févotte
Non-negative and bounded-variable linear regression problems arise in a variety of applications in machine learning and signal processing. In this paper, we propose a technique to…
Expanding boundaries of Gap Safe screening
Cassio F. Dantas, Emmanuel Soubies, Cédric Févotte
Sparse optimization problems are ubiquitous in many fields such as statistics, signal/image processing and machine learning. This has led to the birth of many iterative algorithms…
Stable safe screening and structured dictionaries for faster L1 regularization
Cassio Fraga Dantas, Rémi Gribonval
In this paper, we propose a way to combine two acceleration techniques for the -regularized least squares problem: safe screening tests, which allow to eliminate useless…