167 citations · 1k across the 73 of their papers we have counts for
10 papers · 1 filter
Interpreting CLIP with Hierarchical Sparse Autoencoders
Vladimir Zaigrajew, Hubert Baniecki, Przemyslaw Biecek
Sparse autoencoders (SAEs) are useful for detecting and steering interpretable features in neural networks, with particular potential for understanding complex multimodal represent…
Position: Do Not Explain Vision Models Without Context
Paulina Tomaszewska, Przemysław Biecek
Does the stethoscope in the picture make the adjacent person a doctor or a patient? This, of course, depends on the contextual relationship of the two objects. If it's obvious, why…
Does context matter in digital pathology?
Paulina Tomaszewska, Mateusz Sperkowski, Przemysław Biecek
The development of Artificial Intelligence for healthcare is of great importance. Models can sometimes achieve even superior performance to human experts, however, they can reason…
Red-Teaming Segment Anything Model
Krzysztof Jankowski, Bartlomiej Sobieski, Mateusz Kwiatkowski +4
Foundation models have emerged as pivotal tools, tackling many complex tasks through pre-training on vast datasets and subsequent fine-tuning for specific applications. The Segment…
Red Teaming Models for Hyperspectral Image Analysis Using Explainable AI
Vladimir Zaigrajew, Hubert Baniecki, Lukasz Tulczyjew +4
Remote sensing (RS) applications in the space domain demand machine learning (ML) models that are reliable, robust, and quality-assured, making red teaming a vital approach for ide…
Deep spatial context: when attention-based models meet spatial regression
Paulina Tomaszewska, Elżbieta Sienkiewicz, Mai P. Hoang +1
We propose 'Deep spatial context' (DSCon) method, which serves for investigation of the attention-based vision models using the concept of spatial context. It was inspired by histo…