Andrea Prati

Tomaso Fontanini, Claudio Ferrari, Giuseppe Lisanti et al.

In semantic image synthesis the state of the art is dominated by methods that use customized variants of the SPatially-Adaptive DE-normalization (SPADE) layers, which allow for good visual generation quality and editing versatility. By design, such layers learn pixel-wise modulation parameters to de-normalize the generator activations based on the semantic class each pixel belongs to. Thus, they tend to overlook global image statistics, ultimately leading to unconvincing local style editing and causing global inconsistencies such as color or illumination distribution shifts. Also, SPADE layers require the semantic segmentation mask for mapping styles in the generator, preventing shape manipulations without manual intervention. In response, we designed a novel architecture where cross-attention layers are used in place of SPADE for learning shape-style correlations and so conditioning the image generation process. Our model inherits the versatility of SPADE, at the same time obtaining state-of-the-art generation quality, as well as improved global and local style transfer. Code and models available at https://github.com/TFonta/CA2SIS.

Leonardo Rossi, Vittorio Bernuzzi, Tomaso Fontanini et al.

The ability to understand the surrounding scene is of paramount importance for Autonomous Vehicles (AVs). This paper presents a system capable to work in an online fashion, giving an immediate response to the arise of anomalies surrounding the AV, exploiting only the videos captured by a dash-mounted camera. Our architecture, called MOVAD, relies on two main modules: a Short-Term Memory Module to extract information related to the ongoing action, implemented by a Video Swin Transformer (VST), and a Long-Term Memory Module injected inside the classifier that considers also remote past information and action context thanks to the use of a Long-Short Term Memory (LSTM) network. The strengths of MOVAD are not only linked to its excellent performance, but also to its straightforward and modular architecture, trained in a end-to-end fashion with only RGB frames with as less assumptions as possible, which makes it easy to implement and play with. We evaluated the performance of our method on Detection of Traffic Anomaly (DoTA) dataset, a challenging collection of dash-mounted camera videos of accidents. After an extensive ablation study, MOVAD is able to reach an AUC score of 82.17\%, surpassing the current state-of-the-art by +2.87 AUC. Our code will be available on https://github.com/IMPLabUniPr/movad/tree/movad_vad

Tomaso Fontanini, Claudio Ferrari, Massimo Bertozzi et al.

Semantic image synthesis (SIS) refers to the problem of generating realistic imagery given a semantic segmentation mask that defines the spatial layout of object classes. Most of the approaches in the literature, other than the quality of the generated images, put effort in finding solutions to increase the generation diversity in terms of style i.e. texture. However, they all neglect a different feature, which is the possibility of manipulating the layout provided by the mask. Currently, the only way to do so is manually by means of graphical users interfaces. In this paper, we describe a network architecture to address the problem of automatically manipulating or generating the shape of object classes in semantic segmentation masks, with specific focus on human faces. Our proposed model allows embedding the mask class-wise into a latent space where each class embedding can be independently edited. Then, a bi-directional LSTM block and a convolutional decoder output a new, locally manipulated mask. We report quantitative and qualitative results on the CelebMask-HQ dataset, which show our model can both faithfully reconstruct and modify a segmentation mask at the class level. Also, we show our model can be put before a SIS generator, opening the way to a fully automatic generation control of both shape and texture. Code available at https://github.com/TFonta/Semantic-VAE.

Leonardo Rossi, Akbar Karimi, Andrea Prati

Nowadays, Semi-Supervised Object Detection (SSOD) is a hot topic, since, while it is rather easy to collect images for creating a new dataset, labeling them is still an expensive and time-consuming task. One of the successful methods to take advantage of raw images on a Semi-Supervised Learning (SSL) setting is the Mean Teacher technique, where the operations of pseudo-labeling by the Teacher and the Knowledge Transfer from the Student to the Teacher take place simultaneously. However, the pseudo-labeling by thresholding is not the best solution since the confidence value is not strictly related to the prediction uncertainty, not permitting to safely filter predictions. In this paper, we introduce an additional classification task for bounding box localization to improve the filtering of the predicted bounding boxes and obtain higher quality on Student training. Furthermore, we empirically prove that bounding box regression on the unsupervised part can equally contribute to the training as much as category classification. Our experiments show that our IL-net (Improving Localization net) increases SSOD performance by 1.14% AP on COCO dataset in limited-annotation regime. The code is available at https://github.com/IMPLabUniPr/unbiased-teacher/tree/ilnet

Filippo Botti, Alex Ergasti, Leonardo Rossi et al.

The goal of style transfer is, given a content image and a style source, generating a new image preserving the content but with the artistic representation of the style source. Most of the state-of-the-art architectures use transformers or diffusion-based models to perform this task, despite the heavy computational burden that they require. In particular, transformers use self- and cross-attention layers which have large memory footprint, while diffusion models require high inference time. To overcome the above, this paper explores a novel design of Mamba, an emergent State-Space Model (SSM), called Mamba-ST, to perform style transfer. To do so, we adapt Mamba linear equation to simulate the behavior of cross-attention layers, which are able to combine two separate embeddings into a single output, but drastically reducing memory usage and time complexity. We modified the Mamba's inner equations so to accept inputs from, and combine, two separate data streams. To the best of our knowledge, this is the first attempt to adapt the equations of SSMs to a vision task like style transfer without requiring any other module like cross-attention or custom normalization layers. An extensive set of experiments demonstrates the superiority and efficiency of our method in performing style transfer compared to transformers and diffusion models. Results show improved quality in terms of both ArtFID and FID metrics. Code is available at https://github.com/FilippoBotti/MambaST.

Leonardo Rossi, Marco Valenti, Sara Elisabetta Legler et al.

The Instance Segmentation task, an extension of the well-known Object Detection task, is of great help in many areas, such as precision agriculture: being able to automatically identify plant organs and the possible diseases associated with them, allows to effectively scale and automate crop monitoring and its diseases control. To address the problem related to early disease detection and diagnosis on vines plants, a new dataset has been created with the goal of advancing the state-of-the-art of diseases recognition via instance segmentation approaches. This was achieved by gathering images of leaves and clusters of grapes affected by diseases in their natural context. The dataset contains photos of 10 object types which include leaves and grapes with and without symptoms of the eight more common grape diseases, with a total of 17,706 labeled instances in 1,092 images. Multiple statistical measures are proposed in order to offer a complete view on the characteristics of the dataset. Preliminary results for the object detection and instance segmentation tasks reached by the models Mask R-CNN and R^3-CNN are provided as baseline, demonstrating that the procedure is able to reach promising results about the objective of automatic diseases' symptoms recognition.

Alex Ergasti, Tomaso Fontanini, Claudio Ferrari et al.

Text-based person search (TBPS) is a problem that gained significant interest within the research community. The task is that of retrieving one or more images of a specific individual based on a textual description. The multi-modal nature of the task requires learning representations that bridge text and image data within a shared latent space. Existing TBPS systems face two major challenges. One is defined as inter-identity noise that is due to the inherent vagueness and imprecision of text descriptions and it indicates how descriptions of visual attributes can be generally associated to different people; the other is the intra-identity variations, which are all those nuisances e.g. pose, illumination, that can alter the visual appearance of the same textual attributes for a given subject. To address these issues, this paper presents a novel TBPS architecture named MARS (Mae-Attribute-Relation-Sensitive), which enhances current state-of-the-art models by introducing two key components: a Visual Reconstruction Loss and an Attribute Loss. The former employs a Masked AutoEncoder trained to reconstruct randomly masked image patches with the aid of the textual description. In doing so the model is encouraged to learn more expressive representations and textual-visual relations in the latent space. The Attribute Loss, instead, balances the contribution of different types of attributes, defined as adjective-noun chunks of text. This loss ensures that every attribute is taken into consideration in the person retrieval process. Extensive experiments on three commonly used datasets, namely CUHK-PEDES, ICFG-PEDES, and RSTPReid, report performance improvements, with significant gains in the mean Average Precision (mAP) metric w.r.t. the current state of the art.

Leonardo Rossi, Akbar Karimi, Andrea Prati

Current state-of-the-art two-stage models on instance segmentation task suffer from several types of imbalances. In this paper, we address the Intersection over the Union (IoU) distribution imbalance of positive input Regions of Interest (RoIs) during the training of the second stage. Our Self-Balanced R-CNN (SBR-CNN), an evolved version of the Hybrid Task Cascade (HTC) model, brings brand new loop mechanisms of bounding box and mask refinements. With an improved Generic RoI Extraction (GRoIE), we also address the feature-level imbalance at the Feature Pyramid Network (FPN) level, originated by a non-uniform integration between low- and high-level features from the backbone layers. In addition, the redesign of the architecture heads toward a fully convolutional approach with FCC further reduces the number of parameters and obtains more clues to the connection between the task to solve and the layers used. Moreover, our SBR-CNN model shows the same or even better improvements if adopted in conjunction with other state-of-the-art models. In fact, with a lightweight ResNet-50 as backbone, evaluated on COCO minival 2017 dataset, our model reaches 45.3% and 41.5% AP for object detection and instance segmentation, with 12 epochs and without extra tricks. The code is available at https://github.com/IMPLabUniPr/mmdetection/tree/sbr_cnn

Leonardo Rossi, Vittorio Bernuzzi, Tomaso Fontanini et al.

Due to the limitations of current optical and sensor technologies and the high cost of updating them, the spectral and spatial resolution of satellites may not always meet desired requirements. For these reasons, Remote-Sensing Single-Image Super-Resolution (RS-SISR) techniques have gained significant interest. In this paper, we propose Swin2-MoSE model, an enhanced version of Swin2SR. Our model introduces MoE-SM, an enhanced Mixture-of-Experts (MoE) to replace the Feed-Forward inside all Transformer block. MoE-SM is designed with Smart-Merger, and new layer for merging the output of individual experts, and with a new way to split the work between experts, defining a new per-example strategy instead of the commonly used per-token one. Furthermore, we analyze how positional encodings interact with each other, demonstrating that per-channel bias and per-head bias can positively cooperate. Finally, we propose to use a combination of Normalized-Cross-Correlation (NCC) and Structural Similarity Index Measure (SSIM) losses, to avoid typical MSE loss limitations. Experimental results demonstrate that Swin2-MoSE outperforms any Swin derived models by up to 0.377 - 0.958 dB (PSNR) on task of 2x, 3x and 4x resolution-upscaling (Sen2Venus and OLI2MSI datasets). It also outperforms SOTA models by a good margin, proving to be competitive and with excellent potential, especially for complex tasks. Additionally, an analysis of computational costs is also performed. Finally, we show the efficacy of Swin2-MoSE, applying it to a semantic segmentation task (SeasoNet dataset). Code and pretrained are available on https://github.com/IMPLabUniPr/swin2-mose/tree/official_code

Alex Ergasti, Giuseppe Gabriele Tarollo, Filippo Botti et al.

Joint audio-video (AV) generation is still a significant challenge in generative AI, primarily due to three critical requirements: quality of the generated samples, seamless multimodal synchronization and temporal coherence, with audio tracks that match the visual data and vice versa, and limitless video duration. In this paper, we present $^R$-FLAV, a novel transformer-based architecture that addresses all the key challenges of AV generation. We explore three distinct cross modality interaction modules, with our lightweight temporal fusion module emerging as the most effective and computationally efficient approach for aligning audio and visual modalities. Our experimental results demonstrate that $^R$-FLAV outperforms existing state-of-the-art models in multimodal AV generation tasks. Our code and checkpoints are available at https://github.com/ErgastiAlex/R-FLAV.

Akbar Karimi, Leonardo Rossi, Andrea Prati

This paper proposes AEDA (An Easier Data Augmentation) technique to help improve the performance on text classification tasks. AEDA includes only random insertion of punctuation marks into the original text. This is an easier technique to implement for data augmentation than EDA method (Wei and Zou, 2019) with which we compare our results. In addition, it keeps the order of the words while changing their positions in the sentence leading to a better generalized performance. Furthermore, the deletion operation in EDA can cause loss of information which, in turn, misleads the network, whereas AEDA preserves all the input information. Following the baseline, we perform experiments on five different datasets for text classification. We show that using the AEDA-augmented data for training, the models show superior performance compared to using the EDA-augmented data in all five datasets. The source code is available for further study and reproduction of the results.

Leonardo Rossi, Akbar Karimi, Andrea Prati

Within the field of instance segmentation, most of the state-of-the-art deep learning networks rely nowadays on cascade architectures, where multiple object detectors are trained sequentially, re-sampling the ground truth at each step. This offers a solution to the problem of exponentially vanishing positive samples. However, it also translates into an increase in network complexity in terms of the number of parameters. To address this issue, we propose Recursively Refined R-CNN (R^3-CNN) which avoids duplicates by introducing a loop mechanism instead. At the same time, it achieves a quality boost using a recursive re-sampling technique, where a specific IoU quality is utilized in each recursion to eventually equally cover the positive spectrum. Our experiments highlight the specific encoding of the loop mechanism in the weights, requiring its usage at inference time. The R^3-CNN architecture is able to surpass the recently proposed HTC model, while reducing the number of parameters significantly. Experiments on COCO minival 2017 dataset show performance boost independently from the utilized baseline model. The code is available online at https://github.com/IMPLabUniPr/mmdetection/tree/r3_cnn.

Akbar Karimi, Leonardo Rossi, Andrea Prati

With the ever-increasing availability of digital information, toxic content is also on the rise. Therefore, the detection of this type of language is of paramount importance. We tackle this problem utilizing a combination of a state-of-the-art pre-trained language model (CharacterBERT) and a traditional bag-of-words technique. Since the content is full of toxic words that have not been written according to their dictionary spelling, attendance to individual characters is crucial. Therefore, we use CharacterBERT to extract features based on the word characters. It consists of a CharacterCNN module that learns character embeddings from the context. These are, then, fed into the well-known BERT architecture. The bag-of-words method, on the other hand, further improves upon that by making sure that some frequently used toxic words get labeled accordingly. With a 4 percent difference from the first team, our system ranked 36th in the competition. The code is available for further re-search and reproduction of the results.

Akbar Karimi, Leonardo Rossi, Andrea Prati

Aspect-Based Sentiment Analysis (ABSA) studies the consumer opinion on the market products. It involves examining the type of sentiments as well as sentiment targets expressed in product reviews. Analyzing the language used in a review is a difficult task that requires a deep understanding of the language. In recent years, deep language models, such as BERT \cite{devlin2019bert}, have shown great progress in this regard. In this work, we propose two simple modules called Parallel Aggregation and Hierarchical Aggregation to be utilized on top of BERT for two main ABSA tasks namely Aspect Extraction (AE) and Aspect Sentiment Classification (ASC) in order to improve the model's performance. We show that applying the proposed models eliminates the need for further training of the BERT model. The source code is available on the Web for further research and reproduction of the results.

Leonardo Rossi, Akbar Karimi, Andrea Prati

Given the wide diffusion of deep neural network architectures for computer vision tasks, several new applications are nowadays more and more feasible. Among them, a particular attention has been recently given to instance segmentation, by exploiting the results achievable by two-stage networks (such as Mask R-CNN or Faster R-CNN), derived from R-CNN. In these complex architectures, a crucial role is played by the Region of Interest (RoI) extraction layer, devoted to extracting a coherent subset of features from a single Feature Pyramid Network (FPN) layer attached on top of a backbone. This paper is motivated by the need to overcome the limitations of existing RoI extractors which select only one (the best) layer from FPN. Our intuition is that all the layers of FPN retain useful information. Therefore, the proposed layer (called Generic RoI Extractor - GRoIE) introduces non-local building blocks and attention mechanisms to boost the performance. A comprehensive ablation study at component level is conducted to find the best set of algorithms and parameters for the GRoIE layer. Moreover, GRoIE can be integrated seamlessly with every two-stage architecture for both object detection and instance segmentation tasks. Therefore, the improvements brought about by the use of GRoIE in different state-of-the-art architectures are also evaluated. The proposed layer leads up to gain a 1.1% AP improvement on bounding box detection and 1.7% AP improvement on instance segmentation. The code is publicly available on GitHub repository at https://github.com/IMPLabUniPr/mmdetection/tree/groie_dev

Giuseppe Tarollo, Tomaso Fontanini, Claudio Ferrari et al.

Nowadays, deep learning models have reached incredible performance in the task of image generation. Plenty of literature works address the task of face generation and editing, with human and automatic systems that struggle to distinguish what's real from generated. Whereas most systems reached excellent visual generation quality, they still face difficulties in preserving the identity of the starting input subject. Among all the explored techniques, Semantic Image Synthesis (SIS) methods, whose goal is to generate an image conditioned on a semantic segmentation mask, are the most promising, even though preserving the perceived identity of the input subject is not their main concern. Therefore, in this paper, we investigate the problem of identity preservation in face image generation and present an SIS architecture that exploits a cross-attention mechanism to merge identity, style, and semantic features to generate faces whose identities are as similar as possible to the input ones. Experimental results reveal that the proposed method is not only suitable for preserving the identity but is also effective in the face recognition adversarial attack, i.e. hiding a second identity in the generated faces.

Alex Ergasti, Filippo Botti, Tomaso Fontanini et al.

Diffusion models have become the most popular approach for high-quality image generation, but their high computational cost still remains a significant challenge. To address this problem, we propose U-Shape Mamba (USM), a novel diffusion model that leverages Mamba-based layers within a U-Net-like hierarchical structure. By progressively reducing sequence length in the encoder and restoring it in the decoder through Mamba blocks, USM significantly lowers computational overhead while maintaining strong generative capabilities. Experimental results against Zigma, which is currently the most efficient Mamba-based diffusion model, demonstrate that USM achieves one-third the GFlops, requires less memory and is faster, while outperforming Zigma in image quality. Frechet Inception Distance (FID) is improved by 15.3, 0.84 and 2.7 points on AFHQ, CelebAHQ and COCO datasets, respectively. These findings highlight USM as a highly efficient and scalable solution for diffusion-based generative models, making high-quality image synthesis more accessible to the research community while reducing computational costs.

Vittorio Bernuzzi, Leonardo Rossi, Tomaso Fontanini et al.

Self-supervised learning (SSL) has recently emerged as a key strategy for building foundation models in remote sensing, where the scarcity of annotated data limits the applicability of fully supervised approaches. In this work, we introduce WaveMAE, a masked autoencoding framework tailored for multispectral satellite imagery. Unlike conventional pixel-based reconstruction, WaveMAE leverages a multi-level Discrete Wavelet Transform (DWT) to disentangle frequency components and guide the encoder toward learning scale-aware high-frequency representations. We further propose a Geo-conditioned Positional Encoding (GPE), which incorporates geographical priors via Spherical Harmonics, encouraging embeddings that respect both semantic and geospatial structure. To ensure fairness in evaluation, all methods are pretrained on the same dataset (fMoW-S2) and systematically evaluated on the diverse downstream tasks of the PANGAEA benchmark, spanning semantic segmentation, regression, change detection, and multilabel classification. Extensive experiments demonstrate that WaveMAE achieves consistent improvements over prior state-of-the-art approaches, with substantial gains on segmentation and regression benchmarks. The effectiveness of WaveMAE pretraining is further demonstrated by showing that even a lightweight variant, containing only 26.4% of the parameters, achieves state-of-the-art performance. Our results establish WaveMAE as a strong and geographically informed foundation model for multispectral remote sensing imagery.

Filippo Botti, Alex Ergasti, Tomaso Fontanini et al.

Diffusion Models have become very popular for Semantic Image Synthesis (SIS) of human faces. Nevertheless, their training and inference is computationally expensive and their computational requirements are high due to the quadratic complexity of attention layers. In this paper, we propose a novel architecture called SISMA, based on the recently proposed Mamba. SISMA generates high quality samples by controlling their shape using a semantic mask at a reduced computational demand. We validated our approach through comprehensive experiments with CelebAMask-HQ, revealing that our architecture not only achieves a better FID score yet also operates at three times the speed of state-of-the-art architectures. This indicates that the proposed design is a viable, lightweight substitute to transformer-based models.

Alex Ergasti, Claudio Ferrari, Tomaso Fontanini et al.

Semantic Image Synthesis (SIS) is among the most popular and effective techniques in the field of face generation and editing, thanks to its good generation quality and the versatility is brings along. Recent works attempted to go beyond the standard GAN-based framework, and started to explore Diffusion Models (DMs) for this task as these stand out with respect to GANs in terms of both quality and diversity. On the other hand, DMs lack in fine-grained controllability and reproducibility. To address that, in this paper we propose a SIS framework based on a novel Latent Diffusion Model architecture for human face generation and editing that is both able to reproduce and manipulate a real reference image and generate diversity-driven results. The proposed system utilizes both SPADE normalization and cross-attention layers to merge shape and style information and, by doing so, allows for a precise control over each of the semantic parts of the human face. This was not possible with previous methods in the state of the art. Finally, we performed an extensive set of experiments to prove that our model surpasses current state of the art, both qualitatively and quantitatively.

Runze Li, Tomaso Fontanini, Luca Donati et al.

Gradient-based attention modeling has been used widely as a way to visualize and understand convolutional neural networks. However, exploiting these visual explanations during the training of generative adversarial networks (GANs) is an unexplored area in computer vision research. Indeed, we argue that this kind of information can be used to influence GANs training in a positive way. For this reason, in this paper, it is shown how gradient based attentions can be used as knowledge to be conveyed in a teacher-student paradigm for multi-domain image-to-image translation tasks in order to improve the results of the student architecture. Further, it is demonstrated how "pseudo"-attentions can also be employed during training when teacher and student networks are trained on different domains which share some similarities. The approach is validated on multi-domain facial attributes transfer and human expression synthesis showing both qualitative and quantitative results.

Akbar Karimi, Leonardo Rossi, Andrea Prati

Aspect-Based Sentiment Analysis (ABSA) deals with the extraction of sentiments and their targets. Collecting labeled data for this task in order to help neural networks generalize better can be laborious and time-consuming. As an alternative, similar data to the real-world examples can be produced artificially through an adversarial process which is carried out in the embedding space. Although these examples are not real sentences, they have been shown to act as a regularization method which can make neural networks more robust. In this work, we apply adversarial training, which was put forward by Goodfellow et al. (2014), to the post-trained BERT (BERT-PT) language model proposed by Xu et al. (2019) on the two major tasks of Aspect Extraction and Aspect Sentiment Classification in sentiment analysis. After improving the results of post-trained BERT by an ablation study, we propose a novel architecture called BERT Adversarial Training (BAT) to utilize adversarial training in ABSA. The proposed model outperforms post-trained BERT in both tasks. To the best of our knowledge, this is the first study on the application of adversarial training in ABSA.

Tomaso Fontanini, Eleonora Iotti, Luca Donati et al.

Image synthesis is currently one of the most addressed image processing topic in computer vision and deep learning fields of study. Researchers have tackled this problem focusing their efforts on its several challenging problems, e.g. image quality and size, domain and pose changing, architecture of the networks, and so on. Above all, producing images belonging to different domains by using a single architecture is a very relevant goal for image generation. In fact, a single multi-domain network would allow greater flexibility and robustness in the image synthesis task than other approaches. This paper proposes a novel architecture and a training algorithm, which are able to produce multi-domain outputs using a single network. A small portion of a dataset is intentionally used, and there are no hard-coded labels (or classes). This is achieved by combining a conditional Generative Adversarial Network (cGAN) for image generation and a Meta-Learning algorithm for domain switch, and we called our approach MetalGAN. The approach has proved to be appropriate for solving the multi-domain problem and it is validated on facial attribute transfer, using CelebA dataset.

Tomaso Fontanini, Eleonora Iotti, Andrea Prati

In recent years, the majority of works on deep-learning-based image colorization have focused on how to make a good use of the enormous datasets currently available. What about when the data at disposal are scarce? The main objective of this work is to prove that a network can be trained and can provide excellent colorization results even without a large quantity of data. The adopted approach is a mixed one, which uses an adversarial method for the actual colorization, and a meta-learning technique to enhance the generator model. Also, a clusterization a-priori of the training dataset ensures a task-oriented division useful for meta-learning, and at the same time reduces the per-step number of images. This paper describes in detail the method and its main motivations, and a discussion of results and future developments is provided.

Federico Magliani, Laura Sani, Stefano Cagnoni et al.

Several computer vision and artificial intelligence projects are nowadays exploiting the manifold data distribution using, e.g., the diffusion process. This approach has produced dramatic improvements on the final performance thanks to the application of such algorithms to the kNN graph. Unfortunately, this recent technique needs a manual configuration of several parameters, thus it is not straightforward to find the best configuration for each dataset. Moreover, the brute-force approach is computationally very demanding when used to optimally set the parameters of the diffusion approach. We propose to use genetic algorithms to find the optimal setting of all the diffusion parameters with respect to retrieval performance for each different dataset. Our approach is faster than others used as references (brute-force, random-search and PSO). A comparison with these methods has been made on three public image datasets: Oxford5k, Paris6k and Oxford105k.

Federico Magliani, Kevin McGuinness, Eva Mohedano et al.

The application of the diffusion in many computer vision and artificial intelligence projects has been shown to give excellent improvements in performance. One of the main bottlenecks of this technique is the quadratic growth of the kNN graph size due to the high-quantity of new connections between nodes in the graph, resulting in long computation times. Several strategies have been proposed to address this, but none are effective and efficient. Our novel technique, based on LSH projections, obtains the same performance as the exact kNN graph after diffusion, but in less time (approximately 18 times faster on a dataset of a hundred thousand images). The proposed method was validated and compared with other state-of-the-art on several public image datasets, including Oxford5k, Paris6k, and Oxford105k.

Federico Magliani, Tomaso Fontanini, Andrea Prati

The recent advances brought by deep learning allowed to improve the performance in image retrieval tasks. Through the many convolutional layers, available in a Convolutional Neural Network (CNN), it is possible to obtain a hierarchy of features from the evaluated image. At every step, the patches extracted are smaller than the previous levels and more representative. Following this idea, this paper introduces a new detector applied on the feature maps extracted from pre-trained CNN. Specifically, this approach lets to increase the number of features in order to increase the performance of the aggregation algorithms like the most famous and used VLAD embedding. The proposed approach is tested on different public datasets: Holidays, Oxford5k, Paris6k and UKB.

Federico Magliani, Andrea Prati

The landmark recognition problem is far from being solved, but with the use of features extracted from intermediate layers of Convolutional Neural Networks (CNNs), excellent results have been obtained. In this work, we propose some improvements on the creation of R-MAC descriptors in order to make the newly-proposed R-MAC+ descriptors more representative than the previous ones. However, the main contribution of this paper is a novel retrieval technique, that exploits the fine representativeness of the MAC descriptors of the database images. Using this descriptors called "db regions" during the retrieval stage, the performance is greatly improved. The proposed method is tested on different public datasets: Oxford5k, Paris6k and Holidays. It outperforms the state-of-the- art results on Holidays and reached excellent results on Oxford5k and Paris6k, overcame only by approaches based on fine-tuning strategies.

Federico Magliani, Tomaso Fontanini, Andrea Prati

The problem of landmark recognition has achieved excellent results in small-scale datasets. When dealing with large-scale retrieval, issues that were irrelevant with small amount of data, quickly become fundamental for an efficient retrieval phase. In particular, computational time needs to be kept as low as possible, whilst the retrieval accuracy has to be preserved as much as possible. In this paper we propose a novel multi-index hashing method called Bag of Indexes (BoI) for Approximate Nearest Neighbors (ANN) search. It allows to drastically reduce the query time and outperforms the accuracy results compared to the state-of-the-art methods for large-scale landmark recognition. It has been demonstrated that this family of algorithms can be applied on different embedding techniques like VLAD and R-MAC obtaining excellent results in very short times on different public datasets: Holidays+Flickr1M, Oxford105k and Paris106k.

Luca Donati, Simone Cesano, Andrea Prati

Vectorizing hand-drawn sketches is a challenging task, which is of paramount importance for creating CAD vectorized versions for the fashion and creative workflows. This paper proposes a complete framework that automatically transforms noisy and complex hand-drawn sketches with different stroke types in a precise, reliable and highly-simplified vectorized model. The proposed framework includes a novel line extraction algorithm based on a multi-resolution application of Pearson's cross correlation and a new unbiased thinning algorithm that can get rid of scribbles and variable-width strokes to obtain clean 1-pixel lines. Other contributions include variants of pruning, merging and edge linking procedures to post-process the obtained paths. Finally, a modification of the original Schneider's vectorization algorithm is designed to obtain fewer control points in the resulting Bezier splines. All the proposed steps of the framework have been extensively tested and compared with state-of-the-art algorithms, showing (both qualitatively and quantitatively) its outperformance.

Yonatan Tariku Tesfaye, Eyasu Zemene, Andrea Prati et al.

In this paper, a unified three-layer hierarchical approach for solving tracking problems in multiple non-overlapping cameras is proposed. Given a video and a set of detections (obtained by any person detector), we first solve within-camera tracking employing the first two layers of our framework and, then, in the third layer, we solve across-camera tracking by merging tracks of the same person in all cameras in a simultaneous fashion. To best serve our purpose, a constrained dominant sets clustering (CDSC) technique, a parametrized version of standard quadratic optimization, is employed to solve both tracking tasks. The tracking problem is caste as finding constrained dominant sets from a graph. In addition to having a unified framework that simultaneously solves within- and across-camera tracking, the third layer helps link broken tracks of the same person occurring during within-camera tracking. In this work, we propose a fast algorithm, based on dynamics from evolutionary game theory, which is efficient and salable to large-scale real-world applications.

Federico Magliani, Navid Mahmoudian Bidgoli, Andrea Prati

The current state of the research in landmark recognition highlights the good accuracy which can be achieved by embedding techniques, such as Fisher vector and VLAD. All these techniques do not exploit spatial information, i.e. consider all the features and the corresponding descriptors without embedding their location in the image. This paper presents a new variant of the well-known VLAD (Vector of Locally Aggregated Descriptors) embedding technique which accounts, at a certain degree, for the location of features. The driving motivation comes from the observation that, usually, the most interesting part of an image (e.g., the landmark to be recognized) is almost at the center of the image, while the features at the borders are irrelevant features which do no depend on the landmark. The proposed variant, called locVLAD (location-aware VLAD), computes the mean of the two global descriptors: the VLAD executed on the entire original image, and the one computed on a cropped image which removes a certain percentage of the image borders. This simple variant shows an accuracy greater than the existing state-of-the-art approach. Experiments are conducted on two public datasets (ZuBuD and Holidays) which are used both for training and testing. Morever a more balanced version of ZuBuD is proposed.

Eyasu Zemene, Yonatan Tariku, Haroon Idrees et al.

This paper presents a new approach for the challenging problem of geo-locating an image using image matching in a structured database of city-wide reference images with known GPS coordinates. We cast the geo-localization as a clustering problem on local image features. Akin to existing approaches on the problem, our framework builds on low-level features which allow partial matching between images. For each local feature in the query image, we find its approximate nearest neighbors in the reference set. Next, we cluster the features from reference images using Dominant Set clustering, which affords several advantages over existing approaches. First, it permits variable number of nodes in the cluster which we use to dynamically select the number of nearest neighbors (typically coming from multiple reference images) for each query feature based on its discrimination value. Second, as we also quantify in our experiments, this approach is several orders of magnitude faster than existing approaches. Thus, we obtain multiple clusters (different local maximizers) and obtain a robust final solution to the problem using multiple weak solutions through constrained Dominant Set clustering on global image features, where we enforce the constraint that the query image must be included in the cluster. This second level of clustering also bypasses heuristic approaches to voting and selecting the reference image that matches to the query. We evaluated the proposed framework on an existing dataset of 102k street view images as well as a new dataset of 300k images, and show that it outperforms the state-of-the-art by 20% and 7%, respectively, on the two datasets.