arXiv subjects

Barbara Toniella Corradini

Publications and source records attributed to Barbara Toniella Corradini.

5 recordsLinked to original sources

arXiv2026

APEX: Assumption-free Projection-based Embedding eXamination Metric for Generative Distribution Evaluation

As generative models achieve unprecedented visual quality, the gold standard for image evaluation remains traditional feature-distribution metrics. However, these metrics are provably hindered by the closed-vocabulary bottleneck of outdated features and the assumptive bias of rigid parametric formulations. Recent alternatives exploit modern backbones to solve the feature bottleneck, yet continue to suffer from parametric limitations. To close this gap, we introduce APEX (Assumption-free Projection-based Embedding eXamination), a novel evaluation framework leveraging two open-vocabulary foundation models (CLIP and DINOv2) as feature extractors and the Sliced Wasserstein Distance (SWD) as similarity measure. Since SWD requires no assumptions about the compared data distributions, APEX operates as an assumption-free metric. Moreover, we prove with theoretical and empirical evidences that it inherits effective scalability to high-dimensional spaces. Benchmarking APEX metrics against established baselines, we show that they exhibit strong robustness to visual degradations, intra- and cross-dataset stability, ensuring highly stable evaluations on out-of-domain datasets.

cs.CV↗

arXiv2026

From What to Which: Decoding Modifier Grounding in Frozen MLLMs

As Multimodal Large Language Models (MLLMs) can describe increasingly complex visual scenes, token-level grounding becomes crucial. Yet, when an MLLM generates "the yellow banana on the left", established grounding approaches focus on what is in the image ("banana"), overlooking tokens that help describe which instance is meant ("yellow", "left"). In this work, we ask whether frozen MLLM representations contain decodable grounding information about the referred instance across generated tokens, extending to modifiers such as attributes, spatial expressions, and relational/action terms. To address this question, we introduce OTTER, a lightweight supervised probe over frozen MLLM representations that uses Optimal Transport (OT) to align generated tokens with visual regions and produce compact grounding maps. Our results show that (i) instance-discriminative visual information can be decoded from modifier tokens, with the clearest evidence for spatial terms, but (ii) is not confined to them, as contextualized object nouns also carry referential information; (iii) the recovered grounding remains informative under context perturbations, while selected regions remain relevant to generation; and (iv) the learned OT-based grounding extends beyond the controlled setting to free generation and cross-dataset transfer.

cs.CV↗

arXiv2026

Who Made This? Fake Detection and Source Attribution with Diffusion Features

The rapid rise of generative models has yielded synthetic images of striking realism, blurring the line between real and fake content. As novel models proliferate, detectors must go beyond mere fake identification to robustly generalise across unseen generators and synthetic content. We introduce FRIDA (Fake image Recognition and source Identification via Diffusion features Analysis), a lightweight, data-efficient framework that uses features from a pre-trained Stable Diffusion Model to detect and attribute AI-generated images. Through an in-depth analysis of how data from different generators are encoded across diffusion U-Net layers, we propose a method that (i) detects synthetic images using a training-free $k$-Nearest Neighbour approach and (ii) performs source model attribution via a compact neural classifier. On the GenImage benchmark, FRIDA achieves state-of-the-art cross-generator detection with limited data while maintaining robust source model attribution capabilities. These results establish diffusion features as a reliable framework for AI-generated image forensics.

cs.CV↗

arXiv2026

Neural Learning of Fast Matrix Multiplication Algorithms: A StrassenNet Approach

Fast matrix multiplication can be described as searching for low-rank decompositions of the matrix--multiplication tensor. We design a neural architecture, \textsc{StrassenNet}, which reproduces the Strassen algorithm for $2\times 2$ multiplication. Across many independent runs the network always converges to a rank-$7$ tensor, thus numerically recovering Strassen's optimal algorithm. We then train the same architecture on $3\times 3$ multiplication with rank $r\in\{19,\dots,23\}$. Our experiments reveal a clear numerical threshold: models with $r=23$ attain significantly lower validation error than those with $r\le 22$, suggesting that $r=23$ could actually be the smallest effective rank of the matrix multiplication tensor $3\times 3$. We also sketch an extension of the method to border-rank decompositions via an $\varepsilon$--parametrisation and report preliminary results consistent with the known bounds for the border rank of the $3\times 3$ matrix--multiplication tensor.

math.AG↗

arXiv2025

FreeSeg-Diff: Training-Free Open-Vocabulary Segmentation with Diffusion Models

Foundation models have exhibited unprecedented capabilities in tackling many domains and tasks. Models such as CLIP are currently widely used to bridge cross-modal representations, and text-to-image diffusion models are arguably the leading models in terms of realistic image generation. Image generative models are trained on massive datasets that provide them with powerful internal spatial representations. In this work, we explore the potential benefits of such representations, beyond image generation, in particular, for dense visual prediction tasks. We focus on the task of image segmentation, which is traditionally solved by training models on closed-vocabulary datasets, with pixel-level annotations. To avoid the annotation cost or training large diffusion models, we constraint our setup to be zero-shot and training-free. In a nutshell, our pipeline leverages different and relatively small-sized, open-source foundation models for zero-shot open-vocabulary segmentation. The pipeline is as follows: the image is passed to both a captioner model (i.e. BLIP) and a diffusion model (i.e., Stable Diffusion Model) to generate a text description and visual representation, respectively. The features are clustered and binarized to obtain class agnostic masks for each object. These masks are then mapped to a textual class, using the CLIP model to support open-vocabulary. Finally, we add a refinement step that allows to obtain a more precise segmentation mask. Our approach (dubbed FreeSeg-Diff), which does not rely on any training, outperforms many training-based approaches on both Pascal VOC and COCO datasets. In addition, we show very competitive results compared to the recent weakly-supervised segmentation approaches. We provide comprehensive experiments showing the superiority of diffusion model features compared to other pretrained models. Project page: https://bcorrad.github.io/freesegdiff/

cs.CV↗