collaborators

11 papers

cs.CV2026

Representation Recycling for Streaming Video Analysis

Can Ufuk Ertenli, Ramazan Gokberk Cinbis, Emre Akbas

We present StreamDEQ, a method that aims to infer frame-wise representations on videos with minimal per-frame computation. Conventional deep networks perform feature extraction fro…

cs.CV2026

Caption Bottleneck Models

Seref Baris Cagliyan, Umut Ozdemir, Merve Tapli +1

Concept Bottleneck Models (CBMs) provide interpretability by routing predictions through a layer of human-understandable concepts. However, defining an optimal concept set for a sp…

cs.CV2026

Explaining CLIP Zero-shot Predictions Through Concepts

Onat Ozdemir, Anders Christensen, Stephan Alaniz +2

Large-scale vision-language models such as CLIP have achieved remarkable success in zero-shot image recognition, yet their predictions remain largely opaque to human understanding.…

cs.CV2026

Rethinking Concept Bottleneck Models: From Pitfalls to Solutions

Merve Tapli, Quentin Bouniot, Wolfgang Stammer +2

Concept Bottleneck Models (CBMs) ground predictions in human-understandable concepts but face fundamental limitations: the absence of a metric to pre-evaluate concept relevance, th…

cs.LG2026

Intrinsic Dimensionality as a Model-Free Measure of Class Imbalance

Çağrı Eser, Zeynep Sonat Baltacı, Emre Akbaş +1

Imbalance in classification tasks is commonly quantified by the cardinalities of examples across classes. This, however, disregards the presence of redundant examples and inherent…

cs.CV2025

Unsupervised Image Classification with Adaptive Nearest Neighbor Selection and Cluster Ensembles

Melih Baydar, Emre Akbas

Unsupervised image classification, or image clustering, aims to group unlabeled images into semantically meaningful categories. Early methods integrated representation learning and…