Lorenzo Baraldi

Zeno Testa, Antonino Furnari, Lorenzo Baraldi et al.

Sign Language Translation (SLT) is typically evaluated with surface-form metrics such as BLEU and ROUGE, which reward lexical overlap but do not directly measure whether a translation preserves the meaning of the source sign sequence. This is in contrast with the final objective of integrating SLT in assistive technology. In this work, we shift the focus from Sign Language Translation (SLT) to Sign Language Understanding (SLU), with particular emphasis on semantic understanding. Specifically, we evaluate systems based on their ability to correctly recover, from the input video, key semantic aspects of the original sentence, such as actions taking place and facts about people and objects. To enable this evaluation systematically, we propose SLU-2K, a dataset of 2,350 closed-ended video question-answer pairs based on the popular PHOENIX-2014T and CSL-Daily datasets. To obtain SLU-2K, we propose and extensively evaluate an automated data generation pipeline which produces questions across 7 categories, namely actions, locations, numbers, objects, people, time, and weather conditions. We show the potential of SLU-2K by evaluating popular Multimodal Large Language Models (MLLMs) and two representative state-of-the-art systems, MMSTL and SpaMo. Our results show that MLLMs reach near-random performance, highlighting the need for a more systematic integration of SLU in current AI systems. Furthermore, state-of-the-art translation systems carefully fine-tuned on in-domain data still exhibit a substantial semantic gap, with results ranging from 56.7% to 75.2%. These findings suggest that current SLT evaluation protocols overestimate true understanding and that future progress should be measured not only by fluency and n-gram overlap, but also by semantic correctness. Code, prompts, and benchmark files are available at https://github.com/ZenoTsT/SLU-2K

Sara Sarto, Manuele Barraco, Marcella Cornia et al.

The CLIP model has been recently proven to be very effective for a variety of cross-modal tasks, including the evaluation of captions generated from vision-and-language architectures. In this paper, we propose a new recipe for a contrastive-based evaluation metric for image captioning, namely Positive-Augmented Contrastive learning Score (PAC-S), that in a novel way unifies the learning of a contrastive visual-semantic space with the addition of generated images and text on curated data. Experiments spanning several datasets demonstrate that our new metric achieves the highest correlation with human judgments on both images and videos, outperforming existing reference-based metrics like CIDEr and SPICE and reference-free metrics like CLIP-Score. Finally, we test the system-level correlation of the proposed metric when considering popular image captioning approaches, and assess the impact of employing different cross-modal features. Our source code and trained models are publicly available at: https://github.com/aimagelab/pacscore.

Lorenzo Baraldi, Federico Cocchi, Marcella Cornia et al.

Discerning between authentic content and that generated by advanced AI methods has become increasingly challenging. While previous research primarily addresses the detection of fake faces, the identification of generated natural images has only recently surfaced. This prompted the recent exploration of solutions that employ foundation vision-and-language models, like CLIP. However, the CLIP embedding space is optimized for global image-to-text alignment and is not inherently designed for deepfake detection, neglecting the potential benefits of tailored training and local image features. In this study, we propose CoDE (Contrastive Deepfake Embeddings), a novel embedding space specifically designed for deepfake detection. CoDE is trained via contrastive learning by additionally enforcing global-local similarities. To sustain the training of our model, we generate a comprehensive dataset that focuses on images generated by diffusion models and encompasses a collection of 9.2 million images produced by using four different generators. Experimental results demonstrate that CoDE achieves state-of-the-art accuracy on the newly collected dataset, while also showing excellent generalization capabilities to unseen image generators. Our source code, trained models, and collected dataset are publicly available at: https://github.com/aimagelab/CoDE.

Manuele Barraco, Sara Sarto, Marcella Cornia et al.

Image captioning, like many tasks involving vision and language, currently relies on Transformer-based architectures for extracting the semantics in an image and translating it into linguistically coherent descriptions. Although successful, the attention operator only considers a weighted summation of projections of the current input sample, therefore ignoring the relevant semantic information which can come from the joint observation of other samples. In this paper, we devise a network which can perform attention over activations obtained while processing other training samples, through a prototypical memory model. Our memory models the distribution of past keys and values through the definition of prototype vectors which are both discriminative and compact. Experimentally, we assess the performance of the proposed model on the COCO dataset, in comparison with carefully designed baselines and state-of-the-art approaches, and by investigating the role of each of the proposed components. We demonstrate that our proposal can increase the performance of an encoder-decoder Transformer by 3.7 CIDEr points both when training in cross-entropy only and when fine-tuning with self-critical sequence training. Source code and trained models are available at: https://github.com/aimagelab/PMA-Net.

Nicola Messina, Matteo Stefanini, Marcella Cornia et al.

Image-text matching is gaining a leading role among tasks involving the joint understanding of vision and language. In literature, this task is often used as a pre-training objective to forge architectures able to jointly deal with images and texts. Nonetheless, it has a direct downstream application: cross-modal retrieval, which consists in finding images related to a given query text or vice-versa. Solving this task is of critical importance in cross-modal search engines. Many recent methods proposed effective solutions to the image-text matching problem, mostly using recent large vision-language (VL) Transformer networks. However, these models are often computationally expensive, especially at inference time. This prevents their adoption in large-scale cross-modal retrieval scenarios, where results should be provided to the user almost instantaneously. In this paper, we propose to fill in the gap between effectiveness and efficiency by proposing an ALign And DIstill Network (ALADIN). ALADIN first produces high-effective scores by aligning at fine-grained level images and texts. Then, it learns a shared embedding space - where an efficient kNN search can be performed - by distilling the relevance scores obtained from the fine-grained alignments. We obtained remarkable results on MS-COCO, showing that our method can compete with state-of-the-art VL Transformers while being almost 90 times faster. The code for reproducing our results is available at https://github.com/mesnico/ALADIN.

Sara Sarto, Marcella Cornia, Lorenzo Baraldi et al.

Effectively aligning with human judgment when evaluating machine-generated image captions represents a complex yet intriguing challenge. Existing evaluation metrics like CIDEr or CLIP-Score fall short in this regard as they do not take into account the corresponding image or lack the capability of encoding fine-grained details and penalizing hallucinations. To overcome these issues, in this paper, we propose BRIDGE, a new learnable and reference-free image captioning metric that employs a novel module to map visual features into dense vectors and integrates them into multi-modal pseudo-captions which are built during the evaluation process. This approach results in a multimodal metric that properly incorporates information from the input image without relying on reference captions, bridging the gap between human judgment and machine-generated image captions. Experiments spanning several datasets demonstrate that our proposal achieves state-of-the-art results compared to existing reference-free evaluation scores. Our source code and trained models are publicly available at: https://github.com/aimagelab/bridge-score.

Samuele Poppi, Tobia Poppi, Federico Cocchi et al.

Large-scale vision-and-language models, such as CLIP, are typically trained on web-scale data, which can introduce inappropriate content and lead to the development of unsafe and biased behavior. This, in turn, hampers their applicability in sensitive and trustworthy contexts and could raise significant concerns in their adoption. Our research introduces a novel approach to enhancing the safety of vision-and-language models by diminishing their sensitivity to NSFW (not safe for work) inputs. In particular, our methodology seeks to sever "toxic" linguistic and visual concepts, unlearning the linkage between unsafe linguistic or visual items and unsafe regions of the embedding space. We show how this can be done by fine-tuning a CLIP model on synthetic data obtained from a large language model trained to convert between safe and unsafe sentences, and a text-to-image generator. We conduct extensive experiments on the resulting embedding space for cross-modal retrieval, text-to-image, and image-to-text generation, where we show that our model can be remarkably employed with pre-trained generative models. Our source code and trained models are available at: https://github.com/aimagelab/safe-clip.

Lorenzo Baraldi, Roberto Amoroso, Marcella Cornia et al.

The use of self-supervised pre-training has emerged as a promising approach to enhance the performance of many different visual tasks. In this context, recent approaches have employed the Masked Image Modeling paradigm, which pre-trains a backbone by reconstructing visual tokens associated with randomly masked image patches. This masking approach, however, introduces noise into the input data during pre-training, leading to discrepancies that can impair performance during the fine-tuning phase. Furthermore, input masking neglects the dependencies between corrupted patches, increasing the inconsistencies observed in downstream fine-tuning tasks. To overcome these issues, we propose a new self-supervised pre-training approach, named Masked and Permuted Vision Transformer (MaPeT), that employs autoregressive and permuted predictions to capture intra-patch dependencies. In addition, MaPeT employs auxiliary positional information to reduce the disparity between the pre-training and fine-tuning phases. In our experiments, we employ a fair setting to ensure reliable and meaningful comparisons and conduct investigations on multiple visual tokenizers, including our proposed $k$-CLIP which directly employs discretized CLIP features. Our results demonstrate that MaPeT achieves competitive performance on ImageNet, compared to baselines and competitors under the same model setting. We release an implementation of our code and models at https://github.com/aimagelab/MaPeT.

Nicholas Moratelli, Davide Caffagni, Marcella Cornia et al.

The conventional training approach for image captioning involves pre-training a network using teacher forcing and subsequent fine-tuning with Self-Critical Sequence Training to maximize hand-crafted captioning metrics. However, when attempting to optimize modern and higher-quality metrics like CLIP-Score and PAC-Score, this training method often encounters instability and fails to acquire the genuine descriptive capabilities needed to produce fluent and informative captions. In this paper, we propose a new training paradigm termed Direct CLIP-Based Optimization (DiCO). Our approach jointly learns and optimizes a reward model that is distilled from a learnable captioning evaluator with high human correlation. This is done by solving a weighted classification problem directly inside the captioner. At the same time, DiCO prevents divergence from the original model, ensuring that fluency is maintained. DiCO not only exhibits improved stability and enhanced quality in the generated captions but also aligns more closely with human preferences compared to existing methods, especially in modern metrics. Additionally, it maintains competitive performance in traditional metrics. Our source code and trained models are publicly available at https://github.com/aimagelab/DiCO.

Tobia Poppi, Silvia Cappelletti, Sara Sarto et al.

Recent progress in generative modeling has made safety control a central challenge, yet existing approaches remain largely model-specific, requiring retraining or tailored interventions for each new architecture. In this work, we ask whether safety can be represented as a portable latent direction, learned once and reused across heterogeneous generators. We introduce the first framework for cross-model safety steering, in which a safety direction is estimated in a source LLM from paired safe-unsafe prompts, transported to a target generator through a lightweight alignment fitted on benign data alone, and applied at inference time. Crucially, our pipeline never accesses unsafe data on the target side, isolating whether safety can be transferred through shared representation geometry. Beyond a single global direction, we also identify a multi-vector extension that captures category-specific safety behaviors, enabling more selective control. We evaluate our approach in text-to-image and text-to-video generation across diverse source-target model pairs. Across models, transferred safety directions achieve ASR reduction and CLIP-Score/FID trade-offs comparable to directions learned natively on the target model using unsafe data, while requiring no target-side unsafe data. This indicates that safety improvements do not come at the expense of generation quality. Our results point to a modular view of safety: safety-relevant behavior is not purely model-local, but can be controlled through latent directions that persist across models. This suggests a new path toward lightweight, reusable safety mechanisms that do not require target-side unsafe data.

Sara Sarto, Marcella Cornia, Lorenzo Baraldi et al.

Image captioning models aim at connecting Vision and Language by providing natural language descriptions of input images. In the past few years, the task has been tackled by learning parametric models and proposing visual feature extraction advancements or by modeling better multi-modal connections. In this paper, we investigate the development of an image captioning approach with a kNN memory, with which knowledge can be retrieved from an external corpus to aid the generation process. Our architecture combines a knowledge retriever based on visual similarities, a differentiable encoder, and a kNN-augmented attention layer to predict tokens based on the past context and on text retrieved from the external memory. Experimental results, conducted on the COCO dataset, demonstrate that employing an explicit external memory can aid the generation process and increase caption quality. Our work opens up new avenues for improving image captioning models at larger scale.

Roberto Amoroso, Davide Morelli, Marcella Cornia et al.

Recent advancements in diffusion models have enabled the generation of realistic deepfakes from textual prompts in natural language. While these models have numerous benefits across various sectors, they have also raised concerns about the potential misuse of fake images and cast new pressures on fake image detection. In this work, we pioneer a systematic study on deepfake detection generated by state-of-the-art diffusion models. Firstly, we conduct a comprehensive analysis of the performance of contrastive and classification-based visual features, respectively extracted from CLIP-based models and ResNet or ViT-based architectures trained on image classification datasets. Our results demonstrate that fake images share common low-level cues, which render them easily recognizable. Further, we devise a multimodal setting wherein fake images are synthesized by different textual captions, which are used as seeds for a generator. Under this setting, we quantify the performance of fake detection strategies and introduce a contrastive-based disentangling method that lets us analyze the role of the semantics of textual descriptions and low-level perceptual cues. Finally, we release a new dataset, called COCOFake, containing about 1.2M images generated from the original COCO image-caption pairs using two recent text-to-image diffusion models, namely Stable Diffusion v1.4 and v2.0.

Silvia Cascianelli, Marcella Cornia, Lorenzo Baraldi et al.

Handwritten Text Recognition (HTR) in free-layout pages is a challenging image understanding task that can provide a relevant boost to the digitization of handwritten documents and reuse of their content. The task becomes even more challenging when dealing with historical documents due to the variability of the writing style and degradation of the page quality. State-of-the-art HTR approaches typically couple recurrent structures for sequence modeling with Convolutional Neural Networks for visual feature extraction. Since convolutional kernels are defined on fixed grids and focus on all input pixels independently while moving over the input image, this strategy disregards the fact that handwritten characters can vary in shape, scale, and orientation even within the same document and that the ink pixels are more relevant than the background ones. To cope with these specific HTR difficulties, we propose to adopt deformable convolutions, which can deform depending on the input at hand and better adapt to the geometric variations of the text. We design two deformable architectures and conduct extensive experiments on both modern and historical datasets. Experimental results confirm the suitability of deformable convolutions for the HTR task.

Davide Caffagni, Sara Sarto, Marcella Cornia et al.

Multimodal Large Language Models (MLLMs) have recently demonstrated impressive capabilities in connecting vision and language, yet their proficiency in fundamental visual reasoning tasks remains limited. This limitation can be attributed to the fact that MLLMs learn visual understanding primarily from textual descriptions, which constitute a subjective and inherently incomplete supervisory signal. Furthermore, the modest scale of multimodal instruction tuning compared to massive text-only pre-training leads MLLMs to overfit language priors while overlooking visual details. To address these issues, we introduce JARVIS, a JEPA-inspired framework for self-supervised visual enhancement in MLLMs. Specifically, we integrate the I-JEPA learning paradigm into the standard vision-language alignment pipeline of MLLMs training. Our approach leverages frozen vision foundation models as context and target encoders, while training the predictor, implemented as the early layers of an LLM, to learn structural and semantic regularities from images without relying exclusively on language supervision. Extensive experiments on standard MLLM benchmarks show that JARVIS consistently improves performance on vision-centric benchmarks across different LLM families, without degrading multimodal reasoning abilities. Our source code is publicly available at: https://github.com/aimagelab/JARVIS.

Silvia Cascianelli, Vittorio Pippi, Martin Maarand et al.

Handwritten Text Recognition (HTR) is an open problem at the intersection of Computer Vision and Natural Language Processing. The main challenges, when dealing with historical manuscripts, are due to the preservation of the paper support, the variability of the handwriting -- even of the same author over a wide time-span -- and the scarcity of data from ancient, poorly represented languages. With the aim of fostering the research on this topic, in this paper we present the Ludovico Antonio Muratori (LAM) dataset, a large line-level HTR dataset of Italian ancient manuscripts edited by a single author over 60 years. The dataset comes in two configurations: a basic splitting and a date-based splitting which takes into account the age of the author. The first setting is intended to study HTR on ancient documents in Italian, while the second focuses on the ability of HTR systems to recognize text written by the same writer in time periods for which training data are not available. For both configurations, we analyze quantitative and qualitative characteristics, also with respect to other line-level HTR benchmarks, and present the recognition performance of state-of-the-art HTR architectures. The dataset is available for download at \url{https://aimagelab.ing.unimore.it/go/lam}.

Federico Betti, Jacopo Staiano, Lorenzo Baraldi et al.

Research in Image Generation has recently made significant progress, particularly boosted by the introduction of Vision-Language models which are able to produce high-quality visual content based on textual inputs. Despite ongoing advancements in terms of generation quality and realism, no methodical frameworks have been defined yet to quantitatively measure the quality of the generated content and the adherence with the prompted requests: so far, only human-based evaluations have been adopted for quality satisfaction and for comparing different generative methods. We introduce a novel automated method for Visual Concept Evaluation (ViCE), i.e. to assess consistency between a generated/edited image and the corresponding prompt/instructions, with a process inspired by the human cognitive behaviour. ViCE combines the strengths of Large Language Models (LLMs) and Visual Question Answering (VQA) into a unified pipeline, aiming to replicate the human cognitive process in quality assessment. This method outlines visual concepts, formulates image-specific verification questions, utilizes the Q&A system to investigate the image, and scores the combined outcome. Although this brave new hypothesis of mimicking humans in the image evaluation process is in its preliminary assessment stage, results are promising and open the door to a new form of automatic evaluation which could have significant impact as the image generation or the image target editing tasks become more and more sophisticated.

Samuele Poppi, Sara Sarto, Marcella Cornia et al.

Machine Unlearning is an emerging paradigm for selectively removing the impact of training datapoints from a network. Unlike existing methods that target a limited subset or a single class, our framework unlearns all classes in a single round. We achieve this by modulating the network's components using memory matrices, enabling the network to demonstrate selective unlearning behavior for any class after training. By discovering weights that are specific to each class, our approach also recovers a representation of the classes which is explainable by design. We test the proposed framework on small- and medium-scale image classification datasets, with both convolution- and Transformer-based backbones, showcasing the potential for explainable solutions through unlearning.

Roberto Bigazzi, Marcella Cornia, Silvia Cascianelli et al.

The development of embodied agents that can communicate with humans in natural language has gained increasing interest over the last years, as it facilitates the diffusion of robotic platforms in human-populated environments. As a step towards this objective, in this work, we tackle a setting for visual navigation in which an autonomous agent needs to explore and map an unseen indoor environment while portraying interesting scenes with natural language descriptions. To this end, we propose and evaluate an approach that combines recent advances in visual robotic exploration and image captioning on images generated through agent-environment interaction. Our approach can generate smart scene descriptions that maximize semantic knowledge of the environment and avoid repetitions. Further, such descriptions offer user-understandable insights into the robot's representation of the environment by highlighting the prominent objects and the correlation between them as encountered during the exploration. To quantitatively assess the performance of the proposed approach, we also devise a specific score that takes into account both exploration and description skills. The experiments carried out on both photorealistic simulated environments and real-world ones demonstrate that our approach can effectively describe the robot's point of view during exploration, improving the human-friendly interpretability of its observations.

Vittorio Pippi, Silvia Cascianelli, Lorenzo Baraldi et al.

In this work, we explore massive pre-training on synthetic word images for enhancing the performance on four benchmark downstream handwriting analysis tasks. To this end, we build a large synthetic dataset of word images rendered in several handwriting fonts, which offers a complete supervision signal. We use it to train a simple convolutional neural network (ConvNet) with a fully supervised objective. The vector representations of the images obtained from the pre-trained ConvNet can then be considered as encodings of the handwriting style. We exploit such representations for Writer Retrieval, Writer Identification, Writer Verification, and Writer Classification and demonstrate that our pre-training strategy allows extracting rich representations of the writers' style that enable the aforementioned tasks with competitive results with respect to task-specific State-of-the-Art approaches.

Federico Landi, Roberto Bigazzi, Marcella Cornia et al.

Embodied AI is a recent research area that aims at creating intelligent agents that can move and operate inside an environment. Existing approaches in this field demand the agents to act in completely new and unexplored scenes. However, this setting is far from realistic use cases that instead require executing multiple tasks in the same environment. Even if the environment changes over time, the agent could still count on its global knowledge about the scene while trying to adapt its internal representation to the current state of the environment. To make a step towards this setting, we propose Spot the Difference: a novel task for Embodied AI where the agent has access to an outdated map of the environment and needs to recover the correct layout in a fixed time budget. To this end, we collect a new dataset of occupancy maps starting from existing datasets of 3D spaces and generating a number of possible layouts for a single environment. This dataset can be employed in the popular Habitat simulator and is fully compliant with existing methods that employ reconstructed occupancy maps during navigation. Furthermore, we propose an exploration policy that can take advantage of previous knowledge of the environment and identify changes in the scene faster and more effectively than existing agents. Experimental results show that the proposed architecture outperforms existing state-of-the-art models for exploration on this new setting.

Fabio D'Oronzio, Federico Putamorsi, Leonardo Zini et al.

Despite recent advances, single-image super-resolution (SR) remains challenging, especially in real-world scenarios with complex degradations. Diffusion-based SR methods, particularly those built on Stable Diffusion, leverage strong generative priors but commonly rely on text conditioning derived from semantic captioning. Such textual descriptions provide only high-level semantics and lack the spatially aligned visual information required for faithful restoration, leading to a representation gap between abstract semantics and spatially aligned visual details. To address this limitation, we propose GramSR, a one-step diffusion-based SR framework that replaces text conditioning with dense visual features extracted from the low-resolution input using a pre-trained DINOv3 encoder. GramSR adopts a three-stage LoRA architecture, where pixel-level, semantic-level, and texture-level LoRA modules are trained sequentially. The pixel-level module focuses on degradation removal using $\ell_2$ loss, the semantic-level module enhances perceptual details via LPIPS and CSD losses, and the texture-level module enforces feature correlation consistency through a Gram matrix loss computed from DINOv3 features. At inference, independent guidance scales enable flexible control over degradation removal, semantic enhancement, and texture preservation. Extensive experiments on standard SR benchmarks demonstrate that GramSR consistently outperforms existing one-step diffusion-based methods, achieving superior structural fidelity and texture realism. The code for this work is available at: https://github.com/aimagelab/GramSR.

Roberto Bigazzi, Federico Landi, Silvia Cascianelli et al.

Embodied agents, trained to explore and navigate indoor photorealistic environments, have achieved impressive results on standard datasets and benchmarks. So far, experiments and evaluations have involved domestic and working scenes like offices, flats, and houses. In this paper, we build and release a new 3D space with unique characteristics: the one of a complete art museum. We name this environment ArtGallery3D (AG3D). Compared with existing 3D scenes, the collected space is ampler, richer in visual features, and provides very sparse occupancy information. This feature is challenging for occupancy-based agents which are usually trained in crowded domestic environments with plenty of occupancy information. Additionally, we annotate the coordinates of the main points of interest inside the museum, such as paintings, statues, and other items. Thanks to this manual process, we deliver a new benchmark for PointGoal navigation inside this new space. Trajectories in this dataset are far more complex and lengthy than existing ground-truth paths for navigation in Gibson and Matterport3D. We carry on extensive experimental evaluation using our new space for evaluation and prove that existing methods hardly adapt to this scenario. As such, we believe that the availability of this 3D model will foster future research and help improve existing solutions.

Federico Betti, Lorenzo Baraldi, Lorenzo Baraldi et al.

Text-to-Image generation has seen significant advancements in output realism with the advent of diffusion models. However, diffusion models encounter difficulties when tasked with generating multiple objects, frequently resulting in hallucinations where certain entities are omitted. While existing solutions typically focus on optimizing latent representations within diffusion models, the relevance of the initial generation seed is typically underestimated. While using various seeds in multiple iterations can improve results, this method also significantly increases time and energy costs. To address this challenge, we introduce HEaD+ (Hallucination Early Detection +), a novel approach designed to identify incorrect generations early in the diffusion process. The HEaD+ framework integrates cross-attention maps and textual information with a novel input, the Predicted Final Image. The objective is to assess whether to proceed with the current generation or restart it with a different seed, thereby exploring multiple-generation seeds while conserving time. HEaD+ is trained on the newly created InsideGen dataset of 45,000 generated images, each containing prompts with up to seven objects. Our findings demonstrate a 6-8% increase in the likelihood of achieving a complete generation (i.e., an image accurately representing all specified subjects) with four objects when applying HEaD+ alongside existing models. Additionally, HEaD+ reduces generation times by up to 32% when aiming for a complete image, enhancing the efficiency of generating complete and accurate object representations relative to leading models. Moreover, we propose an integrated localization module that predicts object centroid positions and verifies pairwise spatial relations (if requested by the users) at an intermediate timestep, gating generation together with object presence to further improve relation-consistent outcomes.

Gabriele Mattioli, Evelyn Turri, Sara Sarto et al.

Tool learning with foundation models aims to endow AI systems with the ability to invoke external resources -- such as APIs, computational utilities, and specialized models -- to solve complex tasks beyond the reach of standalone language generation. While recent advances in Large Language Models (LLMs) and Multimodal Large Language Models (MLLMs) have expanded their reasoning and perception capabilities, existing tool-use methods are predominantly limited to text-only inputs and closed-world settings. Consequently, they struggle to interpret multimodal user instructions and cannot generalize to tools unseen during training. In this work, we introduce RaTA-Tool, a novel framework for open-world multimodal tool selection. Rather than learning direct mappings from user queries to fixed tool identifiers, our approach enables an MLLM to convert a multimodal query into a structured task description and subsequently retrieve the most appropriate tool by matching this representation against semantically rich, machine-readable tool descriptions. This retrieval-based formulation naturally supports extensibility to new tools without retraining. To further improve alignment between task descriptions and tool selection, we incorporate a preference-based optimization stage using Direct Preference Optimization (DPO). To support research in this setting, we also introduce the first dataset for open-world multimodal tool use, featuring standardized tool descriptions derived from Hugging Face model cards. Extensive experiments demonstrate that our approach significantly improves tool-selection performance, particularly in open-world, multimodal scenarios.

Federico Betti, Lorenzo Baraldi, Lorenzo Baraldi et al.

Diffusion models have significantly advanced generative AI, but they encounter difficulties when generating complex combinations of multiple objects. As the final result heavily depends on the initial seed, accurately ensuring the desired output can require multiple iterations of the generation process. This repetition not only leads to a waste of time but also increases energy consumption, echoing the challenges of efficiency and accuracy in complex generative tasks. To tackle this issue, we introduce HEaD (Hallucination Early Detection), a new paradigm designed to swiftly detect incorrect generations at the beginning of the diffusion process. The HEaD pipeline combines cross-attention maps with a new indicator, the Predicted Final Image, to forecast the final outcome by leveraging the information available at early stages of the generation process. We demonstrate that using HEaD saves computational resources and accelerates the generation process to get a complete image, i.e. an image where all requested objects are accurately depicted. Our findings reveal that HEaD can save up to 12% of the generation time on a two objects scenario and underscore the importance of early detection mechanisms in generative models.

Davide Bucciarelli, Evelyn Turri, Lorenzo Baraldi et al.

Inference-time scaling has emerged as an effective way to improve generative models at test time by using a verifier to score and select candidate outputs. A common choice is to employ Multimodal Large Language Models (MLLMs) as verifiers, which can improve performance but introduce substantial inference-time cost. Indeed, diffusion pipelines operate in an autoencoder latent space to reduce computation, yet MLLM verifiers still require decoding candidates to pixel space and re-encoding them into the visual embedding space, leading to redundant and costly operations. In this work, we propose Verifier on Hidden States (VHS), a verifier that operates directly on intermediate hidden representations of Diffusion Transformer (DiT) single-step generators. VHS analyzes generator features without decoding to pixel space, thereby reducing the per-candidate verification cost while improving or matching the performance of MLLM-based competitors. We show that, under tiny inference budgets with only a small number of candidates per prompt, VHS enables more efficient inference-time scaling reducing joint generation-and-verification time by 63.3%, compute FLOPs by 51% and VRAM usage by 14.5% with respect to a standard MLLM verifier, achieving a +2.7% improvement on GenEval at the same inference-time budget.

Nicholas Moratelli, Marcella Cornia, Lorenzo Baraldi et al.

Fine-tuning image captioning models with hand-crafted rewards like the CIDEr metric has been a classical strategy for promoting caption quality at the sequence level. This approach, however, is known to limit descriptiveness and semantic richness and tends to drive the model towards the style of ground-truth sentences, thus losing detail and specificity. On the contrary, recent attempts to employ image-text models like CLIP as reward have led to grammatically incorrect and repetitive captions. In this paper, we propose Self-Cap, a captioning approach that relies on a learnable reward model based on self-generated negatives that can discriminate captions based on their consistency with the image. Specifically, our discriminator is a fine-tuned contrastive image-text model trained to promote caption correctness while avoiding the aberrations that typically happen when training with a CLIP-based reward. To this end, our discriminator directly incorporates negative samples from a frozen captioner, which significantly improves the quality and richness of the generated captions but also reduces the fine-tuning time in comparison to using the CIDEr score as the sole metric for optimization. Experimental results demonstrate the effectiveness of our training strategy on both standard and zero-shot image captioning datasets.

Tobia Poppi, Burak Uzkent, Amanmeet Garg et al.

Video-language models (VLMs) achieve strong multimodal understanding but remain prone to hallucinations, especially when reasoning about actions and temporal order. Existing mitigation strategies, such as textual filtering or random video perturbations, often fail to address the root cause: over-reliance on language priors rather than fine-grained visual dynamics. We propose a scalable framework for counterfactual video generation that synthesizes videos differing only in actions or temporal structure while preserving scene context. Our pipeline combines multimodal LLMs for action proposal and editing guidance with diffusion-based image and video models to generate semantic hard negatives at scale. Using this framework, we build CounterVid, a synthetic dataset of ~26k preference pairs targeting action recognition and temporal reasoning. We further introduce MixDPO, a unified Direct Preference Optimization approach that jointly leverages textual and visual preferences. Fine-tuning Qwen2.5-VL with MixDPO yields consistent improvements, notably in temporal ordering, and transfers effectively to standard video hallucination benchmarks. Code and models will be made publicly available.

Marco Morini, Sara Sarto, Marcella Cornia et al.

Answering questions about images often requires combining visual understanding with external knowledge. Multimodal Large Language Models (MLLMs) provide a natural framework for this setting, but they often struggle to identify the most relevant visual and textual evidence when answering knowledge-intensive queries. In such scenarios, models must integrate visual cues with retrieved textual evidence that is often noisy or only partially relevant, while also localizing fine-grained visual information in the image. In this work, we introduce Look Twice (LoT), a training-free inference-time framework that improves how pretrained MLLMs utilize multimodal evidence. Specifically, we exploit the model attention patterns to estimate which visual regions and retrieved textual elements are relevant to a query, and then generate the answer conditioned on this highlighted evidence. The selected cues are highlighted through lightweight prompt-level markers that encourage the model to re-attend to the relevant evidence during generation. Experiments across multiple knowledge-based VQA benchmarks show consistent improvements over zero-shot MLLMs. Additional evaluations on vision-centric and hallucination-oriented benchmarks further demonstrate that visual evidence highlighting alone improves model performance in settings without textual context, all without additional training or architectural modifications. Source code will be publicly released.

Federico Cocchi, Nicholas Moratelli, Davide Caffagni et al.

Recent progress in Multimodal Large Language Models (MLLMs) has highlighted the critical roles of both the visual backbone and the underlying language model. While prior work has primarily focused on scaling these components to billions of parameters, the trade-offs between model size, architecture, and performance remain underexplored. Additionally, inconsistencies in training data and evaluation protocols have hindered direct comparisons, making it difficult to derive optimal design choices. In this paper, we introduce LLaVA-MORE, a new family of MLLMs that integrates recent language models with diverse visual backbones. To ensure fair comparisons, we employ a unified training protocol applied consistently across all architectures. Our analysis systematically explores both small- and medium-scale LLMs -- including Phi-4, LLaMA-3.1, and Gemma-2 -- to evaluate multimodal reasoning, generation, and instruction following, while examining the relationship between model size and performance. Beyond evaluating the LLM impact on final results, we conduct a comprehensive study of various visual encoders, ranging from CLIP-based architectures to alternatives such as DINOv2, SigLIP, and SigLIP2. Additional experiments investigate the effects of increased image resolution and variations in pre-training datasets. Overall, our results provide insights into the design of more effective MLLMs, offering a reproducible evaluation framework that facilitates direct comparisons and can guide future model development. Our source code and trained models are publicly available at: https://github.com/aimagelab/LLaVA-MORE.

Federico Melis, Davide Bilardello, Emanuele Prato et al.

Classifying artworks presents a significant challenge due to the complex interplay of fine-grained details and abstract features that condition the style or genre of an artwork. This paper presents a systematic investigation of the effectiveness of supervised and self-supervised backbones as feature extractors for both artwork classification and retrieval, with a particular focus on paintings. We conduct an extensive experimental evaluation using the DINO family and CLIP models, assessing multiple classification strategies and feature representations. Our results demonstrate that employing a self-supervised backbone leads to consistent improvements in artwork classification performance. Moreover, our work provides insights into the applicability of classification and retrieval modules in real-world applications, such as virtual reality (VR) applications that support museum navigation.

Tobia Poppi, Tejaswi Kasarla, Pascal Mettes et al.

Addressing the retrieval of unsafe content from vision-language models such as CLIP is an important step towards real-world integration. Current efforts have relied on unlearning techniques that try to erase the model's knowledge of unsafe concepts. While effective in reducing unwanted outputs, unlearning limits the model's capacity to discern between safe and unsafe content. In this work, we introduce a novel approach that shifts from unlearning to an awareness paradigm by leveraging the inherent hierarchical properties of the hyperbolic space. We propose to encode safe and unsafe content as an entailment hierarchy, where both are placed in different regions of hyperbolic space. Our HySAC, Hyperbolic Safety-Aware CLIP, employs entailment loss functions to model the hierarchical and asymmetrical relations between safe and unsafe image-text pairs. This modelling, ineffective in standard vision-language models due to their reliance on Euclidean embeddings, endows the model with awareness of unsafe content, enabling it to serve as both a multimodal unsafe classifier and a flexible content retriever, with the option to dynamically redirect unsafe queries toward safer alternatives or retain the original output. Extensive experiments show that our approach not only enhances safety recognition but also establishes a more adaptable and interpretable framework for content moderation in vision-language models. Our source code is available at https://github.com/aimagelab/HySAC.

Davide Caffagni, Sara Sarto, Marcella Cornia et al.

Cross-modal retrieval is gaining increasing efficacy and interest from the research community, thanks to large-scale training, novel architectural and learning designs, and its application in LLMs and multimodal LLMs. In this paper, we move a step forward and design an approach that allows for multimodal queries, composed of both an image and a text, and can search within collections of multimodal documents, where images and text are interleaved. Our model, ReT, employs multi-level representations extracted from different layers of both visual and textual backbones, both at the query and document side. To allow for multi-level and cross-modal understanding and feature extraction, ReT employs a novel Transformer-based recurrent cell that integrates both textual and visual features at different layers, and leverages sigmoidal gates inspired by the classical design of LSTMs. Extensive experiments on M2KR and M-BEIR benchmarks show that ReT achieves state-of-the-art performance across diverse settings. Our source code and trained models are publicly available at https://github.com/aimagelab/ReT.

Evelyn Turri, Davide Bucciarelli, Sara Sarto et al.

Diffusion Transformers (DiTs) and related flow-based architectures are now among the strongest text-to-image generators, yet the internal mechanisms through which prompts shape image semantics remain poorly understood. In this work, we study massive activations: a small subset of hidden-state channels whose responses are consistently much larger than the rest. We show that, despite their sparsity, these few channels effectively draw the whole picture, in three complementary senses. First, they are functionally critical: a controlled disruption probe that zeroes the massive channels causes a sharp collapse in generation quality, while disrupting an equally-sized set of low-statistic channels has marginal effect. Second, they are spatially organized: restricting image-stream tokens to massive channels and clustering them yields coherent partitions that closely align with the main subject and salient regions, exposing a structured spatial code hidden inside an apparently outlier-like subspace. Third, they are transferable: transporting massive activations from one prompt-conditioned trajectory into another, shifts the final image toward the source prompt while preserving substantial content from the target, producing localized semantic interpolation rather than unstructured pixel blending. We exploit this property in two use cases: text-conditioned and image-conditioned semantic transport, where massive activations transport enables prompt interpolation and subject-driven generation without any additional training. Together, these results recast massive activations not as activation anomalies, but as a sparse prompt-conditioned carrier subspace that organizes and controls semantic information in modern DiT models.

Alberto Compagnoni, Davide Caffagni, Nicholas Moratelli et al.

Multimodal Large Language Models (MLLMs) emerge as a unified interface to address a multitude of tasks, ranging from NLP to computer vision. Despite showcasing state-of-the-art results in many benchmarks, a long-standing issue is the tendency of MLLMs to hallucinate, that is to generate answers to the user's query that are not reflected in the visual input. In this paper, we address the problem of hallucinations as an alignment problem, seeking to steer the MLLM so that it prefers generating content without hallucinations. In contrast to recent approaches that require complicated pipelines to build synthetic preference data for alignment training, often relying on proprietary models, we capitalize on the well-known CHAIR metric, originally proposed to gauge the degree of hallucinations in image captioning. Given a pair of generated answers, we leverage CHAIR to distinguish winner and loser options (i.e., non-hallucinated and hallucinated samples) and fine-tune off-the-shelf MLLMs via Direct Preference Optimization (DPO). The resulting method, which we refer to as CHAIR-DPO, effectively diminishes the amount of hallucinated answers on several hallucination benchmarks, demonstrating the effectiveness of fine-tuning the MLLM with a CHAIR-based reward. Source code and trained models are publicly available at https://github.com/aimagelab/CHAIR-DPO.

Alberto Compagnoni, Marco Morini, Sara Sarto et al.

Multimodal Large Language Models (MLLMs) have shown impressive capabilities in jointly understanding text, images, and videos, often evaluated via Visual Question Answering (VQA). However, even state-of-the-art MLLMs struggle with domain-specific or knowledge-intensive queries, where relevant information is underrepresented in pre-training data. Knowledge-based VQA (KB-VQA) addresses this by retrieving external documents to condition answer generation, but current retrieval-augmented approaches suffer from low precision, noisy passages, and limited reasoning. To address this, we propose ReAG, a novel Reasoning-Augmented Multimodal RAG approach that combines coarse- and fine-grained retrieval with a critic model that filters irrelevant passages, ensuring high-quality additional context. The model follows a multi-stage training strategy leveraging reinforcement learning to enhance reasoning over retrieved content, while supervised fine-tuning serves only as a cold start. Extensive experiments on Encyclopedic-VQA and InfoSeek demonstrate that ReAG significantly outperforms prior methods, improving answer accuracy and providing interpretable reasoning grounded in retrieved evidence. Our source code is publicly available at: https://github.com/aimagelab/ReAG.

Davide Caffagni, Federico Cocchi, Luca Barsellotti et al.

Connecting text and visual modalities plays an essential role in generative intelligence. For this reason, inspired by the success of large language models, significant research efforts are being devoted to the development of Multimodal Large Language Models (MLLMs). These models can seamlessly integrate visual and textual modalities, while providing a dialogue-based interface and instruction-following capabilities. In this paper, we provide a comprehensive review of recent visual-based MLLMs, analyzing their architectural choices, multimodal alignment strategies, and training techniques. We also conduct a detailed analysis of these models across a wide range of tasks, including visual grounding, image generation and editing, visual understanding, and domain-specific applications. Additionally, we compile and describe training datasets and evaluation benchmarks, conducting comparisons among existing models in terms of performance and computational requirements. Overall, this survey offers a comprehensive overview of the current state of the art, laying the groundwork for future MLLMs.

Davide Caffagni, Sara Sarto, Marcella Cornia et al.

With the rapid advancement of multimodal retrieval and its application in LLMs and multimodal LLMs, increasingly complex retrieval tasks have emerged. Existing methods predominantly rely on task-specific fine-tuning of vision-language models and are limited to single-modality queries or documents. In this paper, we propose ReT-2, a unified retrieval model that supports multimodal queries, composed of both images and text, and searches across multimodal document collections where text and images coexist. ReT-2 leverages multi-layer representations and a recurrent Transformer architecture with LSTM-inspired gating mechanisms to dynamically integrate information across layers and modalities, capturing fine-grained visual and textual details. We evaluate ReT-2 on the challenging M2KR and M-BEIR benchmarks across different retrieval configurations. Results demonstrate that ReT-2 consistently achieves state-of-the-art performance across diverse settings, while offering faster inference and reduced memory usage compared to prior approaches. When integrated into retrieval-augmented generation pipelines, ReT-2 also improves downstream performance on Encyclopedic-VQA and InfoSeek datasets. Our source code and trained models are publicly available at: https://github.com/aimagelab/ReT-2

Hicham Eddoubi, Jonas Ricker, Federico Cocchi et al.

AI-generated images have reached a quality level at which humans are incapable of reliably distinguishing them from real images. To counteract the inherent risk of fraud and disinformation, the detection of AI-generated images is a pressing challenge and an active research topic. While many of the presented methods claim to achieve high detection accuracy, they are usually evaluated under idealized conditions. In particular, the adversarial robustness is often neglected, potentially due to a lack of awareness or the substantial effort required to conduct a comprehensive robustness analysis. In this work, we tackle this problem by providing a simpler means to assess the robustness of AI-generated image detectors. We present RAID (Robust evaluation of AI-generated image Detectors), a dataset of 72k diverse and highly transferable adversarial examples. The dataset is created by running attacks against an ensemble of seven state-of-the-art detectors and images generated by four different text-to-image models. Extensive experiments show that our methodology generates adversarial images that transfer with a high success rate to unseen detectors, which can be used to quickly provide an approximate yet still reliable estimate of a detector's adversarial robustness. Our findings indicate that current state-of-the-art AI-generated image detectors can be easily deceived by adversarial examples, highlighting the critical need for the development of more robust methods. We release our dataset at https://huggingface.co/datasets/aimagelab/RAID and evaluation code at https://github.com/pralab/RAID.

Manuele Barraco, Matteo Stefanini, Marcella Cornia et al.

Describing images in natural language is a fundamental step towards the automatic modeling of connections between the visual and textual modalities. In this paper we present CaMEL, a novel Transformer-based architecture for image captioning. Our proposed approach leverages the interaction of two interconnected language models that learn from each other during the training phase. The interplay between the two language models follows a mean teacher learning paradigm with knowledge distillation. Experimentally, we assess the effectiveness of the proposed solution on the COCO dataset and in conjunction with different visual feature extractors. When comparing with existing proposals, we demonstrate that our model provides state-of-the-art caption quality with a significantly reduced number of parameters. According to the CIDEr metric, we obtain a new state of the art on COCO when training without using external data. The source code and trained models are publicly available at: https://github.com/aimagelab/camel.

Roberto Bigazzi, Federico Landi, Marcella Cornia et al.

The research field of Embodied AI has witnessed substantial progress in visual navigation and exploration thanks to powerful simulating platforms and the availability of 3D data of indoor and photorealistic environments. These two factors have opened the doors to a new generation of intelligent agents capable of achieving nearly perfect PointGoal Navigation. However, such architectures are commonly trained with millions, if not billions, of frames and tested in simulation. Together with great enthusiasm, these results yield a question: how many researchers will effectively benefit from these advances? In this work, we detail how to transfer the knowledge acquired in simulation into the real world. To that end, we describe the architectural discrepancies that damage the Sim2Real adaptation ability of models trained on the Habitat simulator and propose a novel solution tailored towards the deployment in real-world scenarios. We then deploy our models on a LoCoBot, a Low-Cost Robot equipped with a single Intel RealSense camera. Different from previous work, our testing scene is unavailable to the agent in simulation. The environment is also inaccessible to the agent beforehand, so it cannot count on scene-specific semantic priors. In this way, we reproduce a setting in which a research group (potentially from other fields) needs to employ the agent visual navigation capabilities as-a-Service. Our experiments indicate that it is possible to achieve satisfying results when deploying the obtained model in the real world. Our code and models are available at https://github.com/aimagelab/LoCoNav.

Marcella Cornia, Matteo Stefanini, Lorenzo Baraldi et al.

Transformer-based architectures represent the state of the art in sequence modeling tasks like machine translation and language understanding. Their applicability to multi-modal contexts like image captioning, however, is still largely under-explored. With the aim of filling this gap, we present M$^2$ - a Meshed Transformer with Memory for Image Captioning. The architecture improves both the image encoding and the language generation steps: it learns a multi-level representation of the relationships between image regions integrating learned a priori knowledge, and uses a mesh-like connectivity at decoding stage to exploit low- and high-level features. Experimentally, we investigate the performance of the M$^2$ Transformer and different fully-attentive models in comparison with recurrent ones. When tested on COCO, our proposal achieves a new state of the art in single-model and ensemble configurations on the "Karpathy" test split and on the online test server. We also assess its performances when describing objects unseen in the training set. Trained models and code for reproducing the experiments are publicly available at: https://github.com/aimagelab/meshed-memory-transformer.

Matteo Tomei, Lorenzo Baraldi, Simone Calderara et al.

Action Detection is a complex task that aims to detect and classify human actions in video clips. Typically, it has been addressed by processing fine-grained features extracted from a video classification backbone. Recently, thanks to the robustness of object and people detectors, a deeper focus has been added on relationship modelling. Following this line, we propose a graph-based framework to learn high-level interactions between people and objects, in both space and time. In our formulation, spatio-temporal relationships are learned through self-attention on a multi-layer graph structure which can connect entities from consecutive clips, thus considering long-range spatial and temporal dependencies. The proposed module is backbone independent by design and does not require end-to-end training. Extensive experiments are conducted on the AVA dataset, where our model demonstrates state-of-the-art results and consistent improvements over baselines built with different backbones. Code is publicly available at https://github.com/aimagelab/STAGE_action_detection.

Federico Landi, Lorenzo Baraldi, Marcella Cornia et al.

Vision-and-Language Navigation (VLN) is a challenging task in which an agent needs to follow a language-specified path to reach a target destination. The goal gets even harder as the actions available to the agent get simpler and move towards low-level, atomic interactions with the environment. This setting takes the name of low-level VLN. In this paper, we strive for the creation of an agent able to tackle three key issues: multi-modality, long-term dependencies, and adaptability towards different locomotive settings. To that end, we devise "Perceive, Transform, and Act" (PTA): a fully-attentive VLN architecture that leaves the recurrent approach behind and the first Transformer-like architecture incorporating three different modalities - natural language, images, and low-level actions for the agent control. In particular, we adopt an early fusion strategy to merge lingual and visual information efficiently in our encoder. We then propose to refine the decoding phase with a late fusion extension between the agent's history of actions and the perceptual modalities. We experimentally validate our model on two datasets: PTA achieves promising results in low-level VLN on R2R and achieves good performance in the recently proposed R4R benchmark. Our code is publicly available at https://github.com/aimagelab/perceive-transform-and-act.

Matteo Tomei, Marcella Cornia, Lorenzo Baraldi et al.

The applicability of computer vision to real paintings and artworks has been rarely investigated, even though a vast heritage would greatly benefit from techniques which can understand and process data from the artistic domain. This is partially due to the small amount of annotated artistic data, which is not even comparable to that of natural images captured by cameras. In this paper, we propose a semantic-aware architecture which can translate artworks to photo-realistic visualizations, thus reducing the gap between visual features of artistic and realistic data. Our architecture can generate natural images by retrieving and learning details from real photos through a similarity matching strategy which leverages a weakly-supervised semantic understanding of the scene. Experimental results show that the proposed technique leads to increased realism and to a reduction in domain shift, which improves the performance of pre-trained architectures for classification, detection, and segmentation. Code is publicly available at: https://github.com/aimagelab/art2real.

Marcella Cornia, Lorenzo Baraldi, Rita Cucchiara

Current captioning approaches can describe images using black-box architectures whose behavior is hardly controllable and explainable from the exterior. As an image can be described in infinite ways depending on the goal and the context at hand, a higher degree of controllability is needed to apply captioning algorithms in complex scenarios. In this paper, we introduce a novel framework for image captioning which can generate diverse descriptions by allowing both grounding and controllability. Given a control signal in the form of a sequence or set of image regions, we generate the corresponding caption through a recurrent architecture which predicts textual chunks explicitly grounded on regions, following the constraints of the given control. Experiments are conducted on Flickr30k Entities and on COCO Entities, an extended version of COCO in which we add grounding annotations collected in a semi-automatic manner. Results demonstrate that our method achieves state of the art performances on controllable image captioning, in terms of caption quality and diversity. Code and annotations are publicly available at: https://github.com/aimagelab/show-control-and-tell.

Davide Caffagni, Federico Cocchi, Nicholas Moratelli et al.

Multimodal LLMs are the natural evolution of LLMs, and enlarge their capabilities so as to work beyond the pure textual modality. As research is being carried out to design novel architectures and vision-and-language adapters, in this paper we concentrate on endowing such models with the capability of answering questions that require external knowledge. Our approach, termed Wiki-LLaVA, aims at integrating an external knowledge source of multimodal documents, which is accessed through a hierarchical retrieval pipeline. Relevant passages, using this approach, are retrieved from the external knowledge source and employed as additional context for the LLM, augmenting the effectiveness and precision of generated dialogues. We conduct extensive experiments on datasets tailored for visual question answering with external data and demonstrate the appropriateness of our approach.

Luca Barsellotti, Roberto Amoroso, Marcella Cornia et al.

Open-vocabulary semantic segmentation aims at segmenting arbitrary categories expressed in textual form. Previous works have trained over large amounts of image-caption pairs to enforce pixel-level multimodal alignments. However, captions provide global information about the semantics of a given image but lack direct localization of individual concepts. Further, training on large-scale datasets inevitably brings significant computational costs. In this paper, we propose FreeDA, a training-free diffusion-augmented method for open-vocabulary semantic segmentation, which leverages the ability of diffusion models to visually localize generated concepts and local-global similarities to match class-agnostic regions with semantic classes. Our approach involves an offline stage in which textual-visual reference embeddings are collected, starting from a large set of captions and leveraging visual and semantic contexts. At test time, these are queried to support the visual matching process, which is carried out by jointly considering class-agnostic regions and global semantic similarities. Extensive analyses demonstrate that FreeDA achieves state-of-the-art performance on five datasets, surpassing previous methods by more than 7.0 average points in terms of mIoU and without requiring any training.

Davide Bucciarelli, Nicholas Moratelli, Marcella Cornia et al.

The task of image captioning demands an algorithm to generate natural language descriptions of visual inputs. Recent advancements have seen a convergence between image captioning research and the development of Large Language Models (LLMs) and Multimodal LLMs -- like GPT-4V and Gemini -- which extend the capabilities of text-only LLMs to multiple modalities. This paper investigates whether Multimodal LLMs can supplant traditional image captioning networks by evaluating their performance on various image description benchmarks. We explore both the zero-shot capabilities of these models and their adaptability to different semantic domains through fine-tuning methods, including prompt learning, prefix tuning, and low-rank adaptation. Our results demonstrate that while Multimodal LLMs achieve impressive zero-shot performance, fine-tuning for specific domains while maintaining their generalization capabilities intact remains challenging. We discuss the implications of these findings for future research in image captioning and the development of more adaptable Multimodal LLMs.

Sara Sarto, Marcella Cornia, Lorenzo Baraldi et al.

The objective of image captioning models is to bridge the gap between the visual and linguistic modalities by generating natural language descriptions that accurately reflect the content of input images. In recent years, researchers have leveraged deep learning-based models and made advances in the extraction of visual features and the design of multimodal connections to tackle this task. This work presents a novel approach towards developing image captioning models that utilize an external kNN memory to improve the generation process. Specifically, we propose two model variants that incorporate a knowledge retriever component that is based on visual similarities, a differentiable encoder to represent input images, and a kNN-augmented language model to predict tokens based on contextual cues and text retrieved from the external memory. We experimentally validate our approach on COCO and nocaps datasets and demonstrate that incorporating an explicit external memory can significantly enhance the quality of captions, especially with a larger retrieval corpus. This work provides valuable insights into retrieval-augmented captioning models and opens up new avenues for improving image captioning at a larger scale.