10 citations · 11 across the 8 of their papers we have counts for
11 papers
Atomizer-IO: Beyond Pixels, Patches and Grids
Hugo Riffaud de Turckheim, Sylvain Lobry, Nicolas Houdré +3
Most vision architectures assume that observations lie on a regular grid, an effective abstraction for natural images but a restrictive one for sensing data whose channels, tempora…
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…
RAMEN: Resolution-Adjustable Multimodal Encoder for Earth Observation
Nicolas Houdré, Diego Marcos, Hugo Riffaud de Turckheim +4
Earth observation (EO) data spans a wide range of spatial, spectral, and temporal resolutions, from high-resolution optical imagery to low resolution multispectral products or rada…
TimeSenCLIP: A Time Series Vision-Language Model for Remote Sensing
Pallavi Jain, Diego Marcos, Dino Ienco +2
Vision-language models (VLMs) have shown significant promise in remote sensing applications, particularly for land-use and land-cover (LULC) mapping via zero-shot classification an…
Atomizer: Generalizing to new modalities by breaking satellite images down to a set of scalars
Hugo Riffaud de Turckheim, Sylvain Lobry, Roberto Interdonato +1
The growing number of Earth observation satellites has led to increasingly diverse remote sensing data, with varying spatial, spectral, and temporal configurations. Most existing m…
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…
SenCLIP: Enhancing zero-shot land-use mapping for Sentinel-2 with ground-level prompting
Pallavi Jain, Dino Ienco, Roberto Interdonato +2
Pre-trained vision-language models (VLMs), such as CLIP, demonstrate impressive zero-shot classification capabilities with free-form prompts and even show some generalization in sp…
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…
Coarse-to-Fine Concept Bottleneck Models
Konstantinos P. Panousis, Dino Ienco, Diego Marcos
Deep learning algorithms have recently gained significant attention due to their impressive performance. However, their high complexity and un-interpretable mode of operation hinde…
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…