Fabio Carrara

Lorenzo Bianchi, Fabio Carrara, Nicola Messina et al.

Recent advancements in large vision-language models enabled visual object detection in open-vocabulary scenarios, where object classes are defined in free-text formats during inference. In this paper, we aim to probe the state-of-the-art methods for open-vocabulary object detection to determine to what extent they understand fine-grained properties of objects and their parts. To this end, we introduce an evaluation protocol based on dynamic vocabulary generation to test whether models detect, discern, and assign the correct fine-grained description to objects in the presence of hard-negative classes. We contribute with a benchmark suite of increasing difficulty and probing different properties like color, pattern, and material. We further enhance our investigation by evaluating several state-of-the-art open-vocabulary object detectors using the proposed protocol and find that most existing solutions, which shine in standard open-vocabulary benchmarks, struggle to accurately capture and distinguish finer object details. We conclude the paper by highlighting the limitations of current methodologies and exploring promising research directions to overcome the discovered drawbacks. Data and code are available at https://lorebianchi98.github.io/FG-OVD/.

Alessio Serra, Fabio Carrara, Maurizio Tesconi et al.

Trends and opinion mining in social media increasingly focus on novel interactions involving visual media, like images and short videos, in addition to text. In this work, we tackle the problem of visual sentiment analysis of social media images -- specifically, the prediction of image sentiment polarity. While previous work relied on manually labeled training sets, we propose an automated approach for building sentiment polarity classifiers based on a cross-modal distillation paradigm; starting from scraped multimodal (text + images) data, we train a student model on the visual modality based on the outputs of a textual teacher model that analyses the sentiment of the corresponding textual modality. We applied our method to randomly collected images crawled from Twitter over three months and produced, after automatic cleaning, a weakly-labeled dataset of $\sim$1.5 million images. Despite exploiting noisy labeled samples, our training pipeline produces classifiers showing strong generalization capabilities and outperforming the current state of the art on five manually labeled benchmarks for image sentiment polarity prediction.

Fabio Carrara, Fabrizio Falchi, Maria Girardi et al.

Thanks to recent advancements in numerical methods, computer power, and monitoring technology, seismic ambient noise provides precious information about the structural behavior of old buildings. The measurement of the vibrations produced by anthropic and environmental sources and their use for dynamic identification and structural health monitoring of buildings initiated an emerging, cross-disciplinary field engaging seismologists, engineers, mathematicians, and computer scientists. In this work, we employ recent deep learning techniques for time-series forecasting to inspect and detect anomalies in the large dataset recorded during a long-term monitoring campaign conducted on the San Frediano bell tower in Lucca. We frame the problem as an unsupervised anomaly detection task and train a Temporal Fusion Transformer to learn the normal dynamics of the structure. We then detect the anomalies by looking at the differences between the predicted and observed frequencies.

Taesung Kwon, Lorenzo Bianchi, Lennart Wittke et al.

Recent diffusion models increasingly favor Transformer backbones, motivated by the remarkable scalability of fully attentional architectures. Yet the locality bias, parameter efficiency, and hardware friendliness--the attributes that established ConvNets as the efficient vision backbone--have seen limited exploration in modern generative modeling. Here we introduce the fully convolutional diffusion model (FCDM), a model having a backbone similar to ConvNeXt, but designed for conditional diffusion modeling. We find that using only 50% of the FLOPs of DiT-XL/2, FCDM-XL achieves competitive performance with 7$\times$ and 7.5$\times$ fewer training steps at 256$\times$256 and 512$\times$512 resolutions, respectively. Remarkably, FCDM-XL can be trained on a 4-GPU system, highlighting the exceptional training efficiency of our architecture. Our results demonstrate that modern convolutional designs provide a competitive and highly efficient alternative for scaling diffusion models, reviving ConvNeXt as a simple yet powerful building block for efficient generative modeling.

Lorenzo Bianchi, Fabio Carrara, Nicola Messina et al.

Modern applications increasingly demand flexible computer vision models that adapt to novel concepts not encountered during training. This necessity is pivotal in emerging domains like extended reality, robotics, and autonomous driving, which require the ability to respond to open-world stimuli. A key ingredient is the ability to identify objects based on free-form textual queries defined at inference time - a task known as open-vocabulary object detection. Multimodal backbones like CLIP are the main enabling technology for current open-world perception solutions. Despite performing well on generic queries, recent studies highlighted limitations on the fine-grained recognition capabilities in open-vocabulary settings - i.e., for distinguishing subtle object features like color, shape, and material. In this paper, we perform a detailed examination of these open-vocabulary object recognition limitations to find the root cause. We evaluate the performance of CLIP, the most commonly used vision-language backbone, against a fine-grained object-matching benchmark, revealing interesting analogies between the limitations of open-vocabulary object detectors and their backbones. Experiments suggest that the lack of fine-grained understanding is caused by the poor separability of object characteristics in the CLIP latent space. Therefore, we try to understand whether fine-grained knowledge is present in CLIP embeddings but not exploited at inference time due, for example, to the unsuitability of the cosine similarity matching function, which may discard important object characteristics. Our preliminary experiments show that simple CLIP latent-space re-projections help separate fine-grained concepts, paving the way towards the development of backbones inherently able to process fine-grained details. The code for reproducing these experiments is available at https://github.com/lorebianchi98/FG-CLIP.

Fabio Carrara, Giuseppe Amato, Luca Brombin et al.

In this work, we propose CBiGAN -- a novel method for anomaly detection in images, where a consistency constraint is introduced as a regularization term in both the encoder and decoder of a BiGAN. Our model exhibits fairly good modeling power and reconstruction consistency capability. We evaluate the proposed method on MVTec AD -- a real-world benchmark for unsupervised anomaly detection on high-resolution images -- and compare against standard baselines and state-of-the-art approaches. Experiments show that the proposed method improves the performance of BiGAN formulations by a large margin and performs comparably to expensive state-of-the-art iterative methods while reducing the computational cost. We also observe that our model is particularly effective in texture-type anomaly detection, as it sets a new state of the art in this category. Our code is available at https://github.com/fabiocarrara/cbigan-ad/.

Luca Barsellotti, Lorenzo Bianchi, Nicola Messina et al.

Open-Vocabulary Segmentation (OVS) aims at segmenting images from free-form textual concepts without predefined training classes. While existing vision-language models such as CLIP can generate segmentation masks by leveraging coarse spatial information from Vision Transformers, they face challenges in spatial localization due to their global alignment of image and text features. Conversely, self-supervised visual models like DINO excel in fine-grained visual encoding but lack integration with language. To bridge this gap, we present Talk2DINO, a novel hybrid approach that combines the spatial accuracy of DINOv2 with the language understanding of CLIP. Our approach aligns the textual embeddings of CLIP to the patch-level features of DINOv2 through a learned mapping function without the need to fine-tune the underlying backbones. At training time, we exploit the attention maps of DINOv2 to selectively align local visual patches with textual embeddings. We show that the powerful semantic and localization abilities of Talk2DINO can enhance the segmentation process, resulting in more natural and less noisy segmentations, and that our approach can also effectively distinguish foreground objects from the background. Experimental results demonstrate that Talk2DINO achieves state-of-the-art performance across several unsupervised OVS benchmarks. Source code and models are publicly available at: https://lorebianchi98.github.io/Talk2DINO/.

Lorenzo Bianchi, Giacomo Pacini, Fabio Carrara et al.

Zero-shot captioners are recently proposed models that utilize common-space vision-language representations to caption images without relying on paired image-text data. To caption an image, they proceed by textually decoding a text-aligned image feature, but they limit their scope to global representations and whole-image captions. We present Patch-ioner, a unified framework for zero-shot captioning that shifts from an image-centric to a patch-centric paradigm, enabling the captioning of arbitrary regions without the need of region-level supervision. Instead of relying on global image representations, we treat individual patches as atomic captioning units and aggregate them to describe arbitrary regions, from single patches to non-contiguous areas and entire images. We analyze the key ingredients that enable current latent captioners to work in our novel proposed framework. Experiments demonstrate that backbones producing meaningful, dense visual features, such as DINO, are key to achieving state-of-the-art performance in multiple region-based captioning tasks. Compared to other baselines and state-of-the-art competitors, our models achieve better performance on zero-shot dense, region-set, and a newly introduced trace captioning task, highlighting the effectiveness of patch-wise semantic representations for scalable caption generation. Project page at https://paciosoft.com/Patch-ioner/ .

Nicola Messina, Rosario Leonardi, Luca Ciampi et al.

Pixel-level recognition of objects manipulated by the user from egocentric images enables key applications spanning assistive technologies, industrial safety, and activity monitoring. However, progress in this area is currently hindered by the scarcity of annotated datasets, as existing approaches rely on costly manual labels. In this paper, we propose to learn human-object interaction detection leveraging narrations -- natural language descriptions of the actions performed by the camera wearer which contain clues about manipulated objects (e.g., "I am pouring vegetables from the chopping board to the pan"). Narrations provide a form of weak supervision that is cheap to acquire and readily available in state-of-the-art egocentric datasets. We introduce Narration-Supervised in-Hand Object Segmentation (NS-iHOS), a novel task where models have to learn to segment in-hand objects by learning from natural-language narrations. Narrations are then not employed at inference time. We showcase the potential of the task by proposing Weakly-Supervised In-hand Object Segmentation from Human Narrations (WISH), an end-to-end model distilling knowledge from narrations to learn plausible hand-object associations and enable in-hand object segmentation without using narrations at test time. We benchmark WISH against different baselines based on open-vocabulary object detectors and vision-language models, showing the superiority of its design. Experiments on EPIC-Kitchens and Ego4D show that WISH surpasses all baselines, recovering more than 50% of the performance of fully supervised methods, without employing fine-grained pixel-wise annotations.

Giulio Federico, Fabio Carrara, Claudio Gennaro et al.

Generating consistent multi-view images from a single image remains challenging. Lack of spatial consistency often degrades 3D mesh quality in surface reconstruction. To address this, we propose LoomNet, a novel multi-view diffusion architecture that produces coherent images by applying the same diffusion model multiple times in parallel to collaboratively build and leverage a shared latent space for view consistency. Each viewpoint-specific inference generates an encoding representing its own hypothesis of the novel view from a given camera pose, which is projected onto three orthogonal planes. For each plane, encodings from all views are fused into a single aggregated plane. These aggregated planes are then processed to propagate information and interpolate missing regions, combining the hypotheses into a unified, coherent interpretation. The final latent space is then used to render consistent multi-view images. LoomNet generates 16 high-quality and coherent views in just 15 seconds. In our experiments, LoomNet outperforms state-of-the-art methods on both image quality and reconstruction metrics, also showing creativity by producing diverse, plausible novel views from the same input.

Giulio Federico, Giuseppe Amato, Fabio Carrara et al.

Understanding the nature of human sketches is challenging because of the wide variation in how they are created. Recognizing complex structural patterns improves both the accuracy in recognizing sketches and the fidelity of the generated sketches. In this work, we introduce ViSketch-GPT, a novel algorithm designed to address these challenges through a multi-scale context extraction approach. The model captures intricate details at multiple scales and combines them using an ensemble-like mechanism, where the extracted features work collaboratively to enhance the recognition and generation of key details crucial for classification and generation tasks. The effectiveness of ViSketch-GPT is validated through extensive experiments on the QuickDraw dataset. Our model establishes a new benchmark, significantly outperforming existing methods in both classification and generation tasks, with substantial improvements in accuracy and the fidelity of generated sketches. The proposed algorithm offers a robust framework for understanding complex structures by extracting features that collaborate to recognize intricate details, enhancing the understanding of structures like sketches and making it a versatile tool for various applications in computer vision and machine learning.

Giacomo Pacini, Fabio Carrara, Nicola Messina et al.

Query suggestion, a technique widely adopted in information retrieval, enhances system interactivity and the browsing experience of document collections. In cross-modal retrieval, many works have focused on retrieving relevant items from natural language queries, while few have explored query suggestion solutions. In this work, we address query suggestion in cross-modal retrieval, introducing a novel task that focuses on suggesting minimal textual modifications needed to explore visually consistent subsets of the collection, following the premise of ''Maybe you are looking for''. To facilitate the evaluation and development of methods, we present a tailored benchmark named CroQS. This dataset comprises initial queries, grouped result sets, and human-defined suggested queries for each group. We establish dedicated metrics to rigorously evaluate the performance of various methods on this task, measuring representativeness, cluster specificity, and similarity of the suggested queries to the original ones. Baseline methods from related fields, such as image captioning and content summarization, are adapted for this task to provide reference performance scores. Although relatively far from human performance, our experiments reveal that both LLM-based and captioning-based methods achieve competitive results on CroQS, improving the recall on cluster specificity by more than 115% and representativeness mAP by more than 52% with respect to the initial query. The dataset, the implementation of the baseline methods and the notebooks containing our experiments are available here: https://paciosoft.com/CroQS-benchmark/

Nicola Messina, Giuseppe Amato, Fabio Carrara et al.

Although convolutional neural networks (CNNs) showed remarkable results in many vision tasks, they are still strained by simple yet challenging visual reasoning problems. Inspired by the recent success of the Transformer network in computer vision, in this paper, we introduce the Recurrent Vision Transformer (RViT) model. Thanks to the impact of recurrent connections and spatial attention in reasoning tasks, this network achieves competitive results on the same-different visual reasoning problems from the SVRT dataset. The weight-sharing both in spatial and depth dimensions regularizes the model, allowing it to learn using far fewer free parameters, using only 28k training samples. A comprehensive ablation study confirms the importance of a hybrid CNN + Transformer architecture and the role of the feedback connections, which iteratively refine the internal representation until a stable prediction is obtained. In the end, this study can lay the basis for a deeper understanding of the role of attention and recurrent connections for solving visual abstract reasoning tasks.

Luca Ciampi, Claudio Gennaro, Fabio Carrara et al.

This paper presents a novel solution to automatically count vehicles in a parking lot using images captured by smart cameras. Unlike most of the literature on this task, which focuses on the analysis of single images, this paper proposes the use of multiple visual sources to monitor a wider parking area from different perspectives. The proposed multi-camera system is capable of automatically estimate the number of cars present in the entire parking lot directly on board the edge devices. It comprises an on-device deep learning-based detector that locates and counts the vehicles from the captured images and a decentralized geometric-based approach that can analyze the inter-camera shared areas and merge the data acquired by all the devices. We conduct the experimental evaluation on an extended version of the CNRPark-EXT dataset, a collection of images taken from the parking lot on the campus of the National Research Council (CNR) in Pisa, Italy. We show that our system is robust and takes advantage of the redundant information deriving from the different cameras, improving the overall performance without requiring any extra geometrical information of the monitored scene.

Nicola Messina, Giuseppe Amato, Fabio Carrara et al.

Deep learning demonstrated major abilities in solving many kinds of different real-world problems in computer vision literature. However, they are still strained by simple reasoning tasks that humans consider easy to solve. In this work, we probe current state-of-the-art convolutional neural networks on a difficult set of tasks known as the same-different problems. All the problems require the same prerequisite to be solved correctly: understanding if two random shapes inside the same image are the same or not. With the experiments carried out in this work, we demonstrate that residual connections, and more generally the skip connections, seem to have only a marginal impact on the learning of the proposed problems. In particular, we experiment with DenseNets, and we examine the contribution of residual and recurrent connections in already tested architectures, ResNet-18, and CorNet-S respectively. Our experiments show that older feed-forward networks, AlexNet and VGG, are almost unable to learn the proposed problems, except in some specific scenarios. We show that recently introduced architectures can converge even in the cases where the important parts of their architecture are removed. We finally carry out some zero-shot generalization tests, and we discover that in these scenarios residual and recurrent connections can have a stronger impact on the overall test accuracy. On four difficult problems from the SVRT dataset, we can reach state-of-the-art results with respect to the previous approaches, obtaining super-human performances on three of the four problems.

Giuseppe Amato, Paolo Bolettieri, Fabio Carrara et al.

In this paper, we describe in details VISIONE, a video search system that allows users to search for videos using textual keywords, occurrence of objects and their spatial relationships, occurrence of colors and their spatial relationships, and image similarity. These modalities can be combined together to express complex queries and satisfy user needs. The peculiarity of our approach is that we encode all the information extracted from the keyframes, such as visual deep features, tags, color and object locations, using a convenient textual encoding indexed in a single text retrieval engine. This offers great flexibility when results corresponding to various parts of the query (visual, text and locations) have to be merged. In addition, we report an extensive analysis of the system retrieval performance, using the query logs generated during the Video Browser Showdown (VBS) 2019 competition. This allowed us to fine-tune the system by choosing the optimal parameters and strategies among the ones that we tested.

Danilo Sorano, Fabio Carrara, Paolo Cintia et al.

Soccer analytics is attracting increasing interest in academia and industry, thanks to the availability of data that describe all the spatio-temporal events that occur in each match. These events (e.g., passes, shots, fouls) are collected by human operators manually, constituting a considerable cost for data providers in terms of time and economic resources. In this paper, we describe PassNet, a method to recognize the most frequent events in soccer, i.e., passes, from video streams. Our model combines a set of artificial neural networks that perform feature extraction from video streams, object detection to identify the positions of the ball and the players, and classification of frame sequences as passes or not passes. We test PassNet on different scenarios, depending on the similarity of conditions to the match used for training. Our results show good classification results and significant improvement in the accuracy of pass detection with respect to baseline classifiers, even when the match's video conditions of the test and training sets are considerably different. PassNet is the first step towards an automated event annotation system that may break the time and the costs for event annotation, enabling data collections for minor and non-professional divisions, youth leagues and, in general, competitions whose matches are not currently annotated by data providers.

Fabio Valerio Massoli, Fabio Carrara, Giuseppe Amato et al.

Deep Learning methods have become state-of-the-art for solving tasks such as Face Recognition (FR). Unfortunately, despite their success, it has been pointed out that these learning models are exposed to adversarial inputs - images to which an imperceptible amount of noise for humans is added to maliciously fool a neural network - thus limiting their adoption in real-world applications. While it is true that an enormous effort has been spent in order to train robust models against this type of threat, adversarial detection techniques have recently started to draw attention within the scientific community. A detection approach has the advantage that it does not require to re-train any model, thus it can be added on top of any system. In this context, we present our work on adversarial samples detection in forensics mainly focused on detecting attacks against FR systems in which the learning model is typically used only as a features extractor. Thus, in these cases, train a more robust classifier might not be enough to defence a FR system. In this frame, the contribution of our work is four-fold: i) we tested our recently proposed adversarial detection approach against classifier attacks, i.e. adversarial samples crafted to fool a FR neural network acting as a classifier; ii) using a k-Nearest Neighbor (kNN) algorithm as a guidance, we generated deep features attacks against a FR system based on a DL model acting as features extractor, followed by a kNN which gives back the query identity based on features similarity; iii) we used the deep features attacks to fool a FR system on the 1:1 Face Verification task and we showed their superior effectiveness with respect to classifier attacks in fooling such type of system; iv) we used the detectors trained on classifier attacks to detect deep features attacks, thus showing that such approach is generalizable to different types of offensives.

Fabio Carrara, Andrea Esuli, Fabrizio Falchi et al.

The recently proposed stochastic residual networks selectively activate or bypass the layers during training, based on independent stochastic choices, each of which following a probability distribution that is fixed in advance. In this paper we present a first exploration on the use of an epoch-dependent distribution, starting with a higher probability of bypassing deeper layers and then activating them more frequently as training progresses. Preliminary results are mixed, yet they show some potential of adding an epoch-dependent management of distributions, worth of further investigation.

Fabio Carrara, Andrea Esuli, Tiziano Fagni et al.

In this paper we tackle the problem of image search when the query is a short textual description of the image the user is looking for. We choose to implement the actual search process as a similarity search in a visual feature space, by learning to translate a textual query into a visual representation. Searching in the visual feature space has the advantage that any update to the translation model does not require to reprocess the, typically huge, image collection on which the search is performed. We propose Text2Vis, a neural network that generates a visual representation, in the visual feature space of the fc6-fc7 layers of ImageNet, from a short descriptive text. Text2Vis optimizes two loss functions, using a stochastic loss-selection method. A visual-focused loss is aimed at learning the actual text-to-visual feature mapping, while a text-focused loss is aimed at modeling the higher-level semantic concepts expressed in language and countering the overfit on non-relevant visual components of the visual loss. We report preliminary results on the MS-COCO dataset.