6 papers
The Sharp Dimension Bound in the Johnson--Lindenstrauss Lemma
Vishesh Jain
The Johnson--Lindenstrauss lemma asserts that every set of points in -dimensional Euclidean space embeds into -dimensional Euclidean space with di…
Multimodal Large Language Models as Image Classifiers
Nikita Kisel, Illia Volkov, Klara Janouskova +1
Multimodal Large Language Models (MLLM) classification performance depends critically on evaluation protocol and ground truth quality. Studies comparing MLLMs with supervised and v…
Koo-Fu CLIP: Closed-Form Adaptation of Vision-Language Models via Fukunaga-Koontz Linear Discriminant Analysis
Matej Suchanek, Klara Janouskova, Ondrej Vasatko +1
Visual-language models such as CLIP provide powerful general-purpose representations, but their raw embeddings are not optimized for supervised classification, often exhibiting lim…
Image Recognition with Vision and Language Embeddings of VLMs
Illia Volkov, Nikita Kisel, Klara Janouskova +1
Vision-language models (VLMs) have enabled strong zero-shot classification through image-text alignment. Yet, their purely visual inference capabilities remain under-explored. In t…
Bringing the Context Back into Object Recognition, Robustly
Klara Janouskova, Cristian Gavrus, Jiri Matas
In object recognition, both the subject of interest (referred to as foreground, FG, for simplicity) and its surrounding context (background, BG) may play an important role. However…
Flaws of ImageNet, Computer Vision's Favourite Dataset
Nikita Kisel, Illia Volkov, Katerina Hanzelkova +2
Since its release, ImageNet-1k dataset has become a gold standard for evaluating model performance. It has served as the foundation for numerous other datasets and training tasks i…