Recent advances in text-to-image (T2I) diffusion models have enabled remarkable control over various attributes, yet precise color specification remains a fundamental challenge. Existing approaches, such as ColorPeel, rely on model personalization, requiring additional optimization and limiting flexibility in specifying arbitrary colors. In this work, we introduce ColorWave, a novel training-free approach that achieves exact RGB-level color control in diffusion models without fine-tuning. By systematically analyzing the cross-attention mechanisms within IP-Adapter, we uncover an implicit binding between textual color descriptors and reference image features. Leveraging this insight, our method rewires these bindings to enforce precise color attribution while preserving the generative capabilities of pretrained models. Our approach maintains generation quality and diversity, outperforming prior methods in accuracy and applicability across diverse object categories. Through extensive evaluations, we demonstrate that ColorWave establishes a new paradigm for structured, color-consistent diffusion-based image synthesis.

• We introduce a psychophysics-inspired way to probe the perception of Multimodal Large Language Models (MLLMs) • We estimate the contrast sensitivity functions (CSFs) of MLLMs using prompt-based psychometric functions • We show the CSF shape and scale vary widely across models, diverging from human vision • We reveal that models and CSF estimates are highly sensitive to prompt phrasing • We demonstrate the CSF of models predicts classification robustness under filtering and adversarial noise Understanding how Multimodal Large Language Models (MLLMs) process low-level visual features is critical for evaluating their perceptual abilities and has not been systematically characterized. Inspired by human psychophysics, we introduce a behavioural method for estimating the Contrast Sensitivity Function (CSF) in MLLMs by treating them as end-to-end observers. Models are queried with structured prompts while viewing noise-based stimuli filtered at specific spatial frequencies. Psychometric functions are derived from the binary verbal responses. Therefore, contrast thresholds (and CSFs) are obtained without relying on internal activations or classifier-based proxies, as opposed to previous reports on artificial networks. Our results reveal that some models resemble human CSFs in shape or scale, but none capture both. We also find that CSF estimates are highly sensitive to prompt phrasing, indicating limited linguistic robustness. Finally, we show that CSFs predict model performance under frequency-filtered and adversarial conditions. These findings highlight systematic differences in frequency tuning across MLLMs and establish this CSF estimation as a scalable diagnostic tool for multimodal perception.

Visual illusions in humans arise when interpreting out- of-distribution stimuli: if the observer is adapted to certain statistics, perception of outliers deviates from reality. Recent studies have shown that artificial neural networks (ANNs) can also be deceived by visual illusions. This revelation raises profound questions about the nature of visual information. Why are two independent systems, both human brains and ANNs, susceptible to the same illusions? Should any ANN be capable of perceiving visual illusions? Are these perceptions a feature or a flaw? In this work, we study how visual illusions are encoded in diffusion models. Remarkably, we show that they present human-like brightness/color shifts in their latent space. We use this fact to demonstrate that diffusion models can predict visual illusions. Furthermore, we also show how to generate new unseen visual illusions in realistic images using text-to-image diffusion models. We validate this ability through psychophysical experiments that show how our model-generated illusions also fool humans.

Online Continual Learning (OCL) methods train a model on a non-stationary data stream where only a few examples are available at a time, often leveraging replay strategies.However, usage of replay is sometimes forbidden, especially in applications with strict privacy regulations.Therefore, we propose Continual MultiPatches (CMP), an effective plugin for existing OCL self-supervised learning strategies that avoids the use of replay samples.CMP generates multiple patches from a single example and projects them into a shared feature space, where patches coming from the same example are pushed together without collapsing into a single point.CMP surpasses replay and other SSL-based strategies on OCL streams, challenging the role of replay as a go-to solution for self-supervised OCL.Code available at https://github.com/giacomo-cgn/cmp .

Recent advances in Text-to-Image (T2I) diffusion models have transformed image generation, enabling significant progress in stylized generation using only a few style reference images. However, current diffusion-based methods struggle with \textit{fine-grained} style customization due to challenges in controlling multiple style attributes, such as color and texture. This paper introduces the first tuning-free approach to achieve free-lunch color-texture disentanglement in stylized T2I generation, addressing the need for independently controlled style elements for the Disentangled Stylized Image Generation (DisIG) problem. Our approach leverages the \textit{Image-Prompt Additivity} property in the CLIP image embedding space to develop techniques for separating and extracting Color-Texture Embeddings (CTE) from individual color and texture reference images. To ensure that the color palette of the generated image aligns closely with the color reference, we apply a whitening and coloring transformation to enhance color consistency. Additionally, to prevent texture loss due to the signal-leak bias inherent in diffusion training, we introduce a noise term that preserves textural fidelity during the Regularized Whitening and Coloring Transformation (RegWCT). Through these methods, our Style Attributes Disentanglement approach (SADis) delivers a more precise and customizable solution for stylized image generation. Experiments on images from the WikiArt and StyleDrop datasets demonstrate that, both qualitatively and quantitatively, SADis surpasses state-of-the-art stylization methods in the DisIG task.

Continuous unsupervised representation learning (CURL) research has greatly benefited from improvements in self-supervised learning (SSL) techniques. As a result, existing CURL methods using SSL can learn high-quality representations without any labels, but with a notable performance drop when learning on a many-tasks data stream. We hypothesize that this is caused by the regularization losses that are imposed to prevent forgetting, leading to a suboptimal plasticity-stability trade-off: they either do not adapt fully to the incoming data (low plasticity), or incur significant forgetting when allowed to fully adapt to a new SSL pretext-task (low stability). In this work, we propose to train an expert network that is relieved of the duty of keeping the previous knowledge and can focus on performing optimally on the new tasks (optimizing plasticity). In the second phase, we combine this new knowledge with the previous network in an adaptation-retrospection phase to avoid forgetting and initialize a new expert with the knowledge of the old network. We perform several experiments showing that our proposed approach outperforms other CURL exemplar-free methods in few- and many-task split settings. Furthermore, we show how to adapt our approach to semi-supervised continual learning (Semi-SCL) and show that we surpass the accuracy of other exemplar-free Semi-SCL methods and reach the results of some others that use exemplars.

Visual illusions teach us that what we see is not always what is represented in the physical world. Their special nature make them a fascinating tool to test and validate any new vision model proposed. In general, current vision models are based on the concatenation of linear and non-linear operations. The similarity of this structure with the operations present in Convolutional Neural Networks (CNNs) has motivated us to study if CNNs trained for low-level visual tasks are deceived by visual illusions. In particular, we show that CNNs trained for image denoising, image deblurring, and computational color constancy are able to replicate the human response to visual illusions, and that the extent of this replication varies with respect to variation in architecture and spatial pattern size. These results suggest that in order to obtain CNNs that better replicate human behaviour, we may need to start aiming for them to better replicate visual illusions.

The segmentation and classification of animals from camera-trap images is a difficult task due to the conditions under which the images are taken. This work presents a method for recognizing mammal genera from camera-trap images. Our method uses Multi-Layer Robust Principal Component Analysis (RPCA) for segmenting, Convolutional Neural Networks (CNNs) for extracting features, Least Absolute Shrinkage and Selection Operator (LASSO) for selecting features, and Artificial Neural Networks (ANNs) or Support Vector Machines (SVM) for classifying mammal genera present in the Colombian forest. Our classification method mixes the features of several CNNs. We evaluated our method with the camera-trap images from the Instituto de Investigación de Recursos Biológicos Alexander von Humboldt. We obtained an accuracy of 92.65% classifying 8 mammal genera and a False Positive (FP) class, using automatic-segmented images. On the other hand, we reached 90.32% of accuracy classifying 10 mammal genera, using ground-truth images only. Unlike all previous works, we confront the animal segmentation and genera classification on the camera-trap framework. This method shows a new approach toward a fully-automatic detection of animals from camera-trap images.