Enver Sangineto
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Research Interests
Enver Sangineto has a total of 61 co-authors. Here are the top co-authors by number of shared publications:
- Nicu Sebe
University of Trento, Trento, Italy
14 shared publications - Aliaksandr Siarohin
Snap Inc., USA
4 shared publications - Moin Nabi
SAP AI Research SAP AI Research
4 shared publications Nicu Sebe
University of Trento Italy
3 shared publications- Stéphane Lathuilière
LTCI Télécom-Paris Institut Polytechnique de Paris France
3 shared publications - Angelo Porrello
University of Modena and Reggio Emilia
2 shared publications
Latest Publications
- Open Access
- 19 November 2026
- Published by Elsevier in Pattern Recognition Letters
ABRA: Teleporting Fine-Tuned Knowledge Across Domains for Open-Vocabulary Object Detection
- 19 November 2026
- Published by Elsevier in Pattern Recognition Letters
Open AccessABRA: Teleporting Fine-Tuned Knowledge Across Domains for Open-Vocabulary Object Detection
- Open Access
BFS-PO: Best-First Search for Large Reasoning Models
Large Reasoning Models (LRMs) such as OpenAI o1 and DeepSeek-R1 have shown excellent performance in reasoning tasks using long reasoning chains. However, this has also led to a significant increase of computational costs and the generation of verbose output, a phenomenon known as overthinking. The tendency to overthinking is often exacerbated by Reinforcement Learning (RL) algorithms such as GRPO/DAPO. In this paper, we propose BFS-PO, an RL algorithm which alleviates this problem using a Best-First Search exploration strategy. Specifically, BFS-PO looks for the shortest correct answer using a backtracking mechanism based on maximum entropy nodes. By generating progressively shorter responses during training, BFS-PO learns to produce concise reasoning chains. Using different benchmarks and base LRMs, we show that BFS-PO can simultaneously increase the LRM accuracy and shorten its answers.
Open AccessBFS-PO: Best-First Search for Large Reasoning Models
Large Reasoning Models (LRMs) such as OpenAI o1 and DeepSeek-R1 have shown excellent performance in reasoning tasks using long reasoning chains. However, this has also led to a significant increase of computational costs and the generation of verbose output, a phenomenon known as overthinking. The tendency to overthinking is often exacerbated by Reinforcement Learning (RL) algorithms such as GRPO/DAPO. In this paper, we propose BFS-PO, an RL algorithm which alleviates this problem using a Best-First Search exploration strategy. Specifically, BFS-PO looks for the shortest correct answer using a backtracking mechanism based on maximum entropy nodes. By generating progressively shorter responses during training, BFS-PO learns to produce concise reasoning chains. Using different benchmarks and base LRMs, we show that BFS-PO can simultaneously increase the LRM accuracy and shorten its answers.
- Open Access
- 28 April 2025
- Published by Springer Nature in Machine Learning
- Vol. 114 (6) , 1-27
One transformer for all time series: representing and training with time-dependent heterogeneous tabular data
There is a recent growing interest in applying Deep Learning techniques to tabular data in order to replicate the success of other Artificial Intelligence areas in this structured domain. Particularly interesting is the case in which tabular data have a time dependence, such as, for instance, financial transactions. However, the heterogeneity of the tabular values, in which categorical elements are mixed with numerical features, makes this adaptation difficult. In this paper we propose UniTTab, a Transformer based architecture whose goal is to uniformly represent heterogeneous time-dependent tabular data, in which both numerical and categorical features are described using continuous embedding vectors. Moreover, differently from common approaches, which use a combination of different loss functions for training with both numerical and categorical targets, UniTTab is uniformly trained with a unique Masked Token pretext task. Finally, UniTTab can also represent time series in which the individual row components have a variable internal structure with a variable number of fields, which is a common situation in many application domains, such as in real world transactional data. Using extensive experiments with five datasets of variable size and complexity, we empirically show that UniTTab consistently and significantly improves the prediction accuracy over several downstream tasks and with respect to both Deep Learning and more standard Machine Learning approaches. Our code and our models are available at: https://github.com/fabriziogaruti/UniTTab.
- 28 April 2025
- Published by Springer Nature in Machine Learning
- Vol. 114 (6) , 1-27
Open AccessOne transformer for all time series: representing and training with time-dependent heterogeneous tabular data
There is a recent growing interest in applying Deep Learning techniques to tabular data in order to replicate the success of other Artificial Intelligence areas in this structured domain. Particularly interesting is the case in which tabular data have a time dependence, such as, for instance, financial transactions. However, the heterogeneity of the tabular values, in which categorical elements are mixed with numerical features, makes this adaptation difficult. In this paper we propose UniTTab, a Transformer based architecture whose goal is to uniformly represent heterogeneous time-dependent tabular data, in which both numerical and categorical features are described using continuous embedding vectors. Moreover, differently from common approaches, which use a combination of different loss functions for training with both numerical and categorical targets, UniTTab is uniformly trained with a unique Masked Token pretext task. Finally, UniTTab can also represent time series in which the individual row components have a variable internal structure with a variable number of fields, which is a common situation in many application domains, such as in real world transactional data. Using extensive experiments with five datasets of variable size and complexity, we empirically show that UniTTab consistently and significantly improves the prediction accuracy over several downstream tasks and with respect to both Deep Learning and more standard Machine Learning approaches. Our code and our models are available at: https://github.com/fabriziogaruti/UniTTab.
- 27 January 2025
- Published by Elsevier in Computer Vision and Image Understanding
- Vol. 252
Collaborative Neural Painting
- 27 January 2025
- Published by Elsevier in Computer Vision and Image Understanding
- Vol. 252
Collaborative Neural Painting
- Open Access
StylerDALLE: Language-Guided Style Transfer Using a Vector-Quantized Tokenizer of a Large-Scale Generative Model
Despite the progress made in the style transfer task, most previous work focus on transferring only relatively simple features like color or texture, while missing more abstract concepts such as overall art expression or painter-specific traits. However, these abstract semantics can be captured by models like DALL-E or CLIP, which have been trained using huge datasets of images and textual documents. In this paper, we propose StylerDALLE, a style transfer method that exploits both of these models and uses natural language to describe abstract art styles. Specifically, we formulate the language-guided style transfer task as a non-autoregressive token sequence translation, i.e., from input content image to output stylized image, in the discrete latent space of a large-scale pretrained vector-quantized tokenizer, e.g., the discrete variational auto-encoder (dVAE) of DALL-E. To incorporate style information, we propose a Reinforcement Learning strategy with CLIP-based language supervision that ensures stylization and content preservation simultaneously. Experimental results demonstrate the superiority of our method, which can effectively transfer art styles using language instructions at different granularities. Code is available at https://github.com/zipengxuc/StylerDALLE.
Open AccessStylerDALLE: Language-Guided Style Transfer Using a Vector-Quantized Tokenizer of a Large-Scale Generative Model
Despite the progress made in the style transfer task, most previous work focus on transferring only relatively simple features like color or texture, while missing more abstract concepts such as overall art expression or painter-specific traits. However, these abstract semantics can be captured by models like DALL-E or CLIP, which have been trained using huge datasets of images and textual documents. In this paper, we propose StylerDALLE, a style transfer method that exploits both of these models and uses natural language to describe abstract art styles. Specifically, we formulate the language-guided style transfer task as a non-autoregressive token sequence translation, i.e., from input content image to output stylized image, in the discrete latent space of a large-scale pretrained vector-quantized tokenizer, e.g., the discrete variational auto-encoder (dVAE) of DALL-E. To incorporate style information, we propose a Reinforcement Learning strategy with CLIP-based language supervision that ensures stylization and content preservation simultaneously. Experimental results demonstrate the superiority of our method, which can effectively transfer art styles using language instructions at different granularities. Code is available at https://github.com/zipengxuc/StylerDALLE.
- Open Access
Input Perturbation Reduces Exposure Bias in Diffusion Models
Denoising Diffusion Probabilistic Models have shown an impressive generation quality, although their long sampling chain leads to high computational costs. In this paper, we observe that a long sampling chain also leads to an error accumulation phenomenon, which is similar to the exposure bias problem in autoregressive text generation. Specifically, we note that there is a discrepancy between training and testing, since the former is conditioned on the ground truth samples, while the latter is conditioned on the previously generated results. To alleviate this problem, we propose a very simple but effective training regularization, consisting in perturbing the ground truth samples to simulate the inference time prediction errors. We empirically show that, without affecting the recall and precision, the proposed input perturbation leads to a significant improvement in the sample quality while reducing both the training and the inference times. For instance, on CelebA 64$\times$64, we achieve a new state-of-the-art FID score of 1.27, while saving 37.5% of the training time. The code is publicly available at https://github.com/forever208/DDPM-IP
Open AccessInput Perturbation Reduces Exposure Bias in Diffusion Models
Denoising Diffusion Probabilistic Models have shown an impressive generation quality, although their long sampling chain leads to high computational costs. In this paper, we observe that a long sampling chain also leads to an error accumulation phenomenon, which is similar to the exposure bias problem in autoregressive text generation. Specifically, we note that there is a discrepancy between training and testing, since the former is conditioned on the ground truth samples, while the latter is conditioned on the previously generated results. To alleviate this problem, we propose a very simple but effective training regularization, consisting in perturbing the ground truth samples to simulate the inference time prediction errors. We empirically show that, without affecting the recall and precision, the proposed input perturbation leads to a significant improvement in the sample quality while reducing both the training and the inference times. For instance, on CelebA 64$\times$64, we achieve a new state-of-the-art FID score of 1.27, while saving 37.5% of the training time. The code is publicly available at https://github.com/forever208/DDPM-IP
- Open Access
Spatial Entropy as an Inductive Bias for Vision Transformers
Recent work on Vision Transformers (VTs) showed that introducing a local inductive bias in the VT architecture helps reducing the number of samples necessary for training. However, the architecture modifications lead to a loss of generality of the Transformer backbone, partially contradicting the push towards the development of uniform architectures, shared, e.g., by both the Computer Vision and the Natural Language Processing areas. In this work, we propose a different and complementary direction, in which a local bias is introduced using an auxiliary self-supervised task, performed jointly with standard supervised training. Specifically, we exploit the observation that the attention maps of VTs, when trained with self-supervision, can contain a semantic segmentation structure which does not spontaneously emerge when training is supervised. Thus, we explicitly encourage the emergence of this spatial clustering as a form of training regularization. In more detail, we exploit the assumption that, in a given image, objects usually correspond to few connected regions, and we propose a spatial formulation of the information entropy to quantify this object-based inductive bias. By minimizing the proposed spatial entropy, we include an additional self-supervised signal during training. Using extensive experiments, we show that the proposed regularization leads to equivalent or better results than other VT proposals which include a local bias by changing the basic Transformer architecture, and it can drastically boost the VT final accuracy when using small-medium training sets. The code is available at https://github.com/helia95/SAR.
Open AccessSpatial Entropy as an Inductive Bias for Vision Transformers
Recent work on Vision Transformers (VTs) showed that introducing a local inductive bias in the VT architecture helps reducing the number of samples necessary for training. However, the architecture modifications lead to a loss of generality of the Transformer backbone, partially contradicting the push towards the development of uniform architectures, shared, e.g., by both the Computer Vision and the Natural Language Processing areas. In this work, we propose a different and complementary direction, in which a local bias is introduced using an auxiliary self-supervised task, performed jointly with standard supervised training. Specifically, we exploit the observation that the attention maps of VTs, when trained with self-supervision, can contain a semantic segmentation structure which does not spontaneously emerge when training is supervised. Thus, we explicitly encourage the emergence of this spatial clustering as a form of training regularization. In more detail, we exploit the assumption that, in a given image, objects usually correspond to few connected regions, and we propose a spatial formulation of the information entropy to quantify this object-based inductive bias. By minimizing the proposed spatial entropy, we include an additional self-supervised signal during training. Using extensive experiments, we show that the proposed regularization leads to equivalent or better results than other VT proposals which include a local bias by changing the basic Transformer architecture, and it can drastically boost the VT final accuracy when using small-medium training sets. The code is available at https://github.com/helia95/SAR.
- 27 July 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Image Processing
- Vol. 31 (10577149) , 5272-5286
Unsupervised High-Resolution Portrait Gaze Correction and Animation
This paper proposes a gaze correction and animation method for high-resolution, unconstrained portrait images, which can be trained without the gaze angle and the head pose annotations. Common gaze-correction methods usually require annotating training data with precise gaze, and head pose information. Solving this problem using an unsupervised method remains an open problem, especially for high-resolution face images in the wild, which are not easy to annotate with gaze and head pose labels. To address this issue, we first create two new portrait datasets: CelebGaze ( $256 \times 256$ ) and high-resolution CelebHQGaze ( $512 \times 512$ ). Second, we formulate the gaze correction task as an image inpainting problem, addressed using a Gaze Correction Module (GCM) and a Gaze Animation Module (GAM). Moreover, we propose an unsupervised training strategy, i.e., Synthesis-As-Training, to learn the correlation between the eye region features and the gaze angle. As a result, we can use the learned latent space for gaze animation with semantic interpolation in this space. Moreover, to alleviate both the memory and the computational costs in the training and the inference stage, we propose a Coarse-to-Fine Module (CFM) integrated with GCM and GAM. Extensive experiments validate the effectiveness of our method for both the gaze correction and the gaze animation tasks in both low and high-resolution face datasets in the wild and demonstrate the superiority of our method with respect to the state of the art.
- 27 July 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Image Processing
- Vol. 31 (10577149) , 5272-5286
Unsupervised High-Resolution Portrait Gaze Correction and Animation
This paper proposes a gaze correction and animation method for high-resolution, unconstrained portrait images, which can be trained without the gaze angle and the head pose annotations. Common gaze-correction methods usually require annotating training data with precise gaze, and head pose information. Solving this problem using an unsupervised method remains an open problem, especially for high-resolution face images in the wild, which are not easy to annotate with gaze and head pose labels. To address this issue, we first create two new portrait datasets: CelebGaze ( $256 \times 256$ ) and high-resolution CelebHQGaze ( $512 \times 512$ ). Second, we formulate the gaze correction task as an image inpainting problem, addressed using a Gaze Correction Module (GCM) and a Gaze Animation Module (GAM). Moreover, we propose an unsupervised training strategy, i.e., Synthesis-As-Training, to learn the correlation between the eye region features and the gaze angle. As a result, we can use the learned latent space for gaze animation with semantic interpolation in this space. Moreover, to alleviate both the memory and the computational costs in the training and the inference stage, we propose a Coarse-to-Fine Module (CFM) integrated with GCM and GAM. Extensive experiments validate the effectiveness of our method for both the gaze correction and the gaze animation tasks in both low and high-resolution face datasets in the wild and demonstrate the superiority of our method with respect to the state of the art.
- Open Access
Efficient Training of Visual Transformers with Small Datasets
Visual Transformers (VTs) are emerging as an architectural paradigm alternative to Convolutional networks (CNNs). Differently from CNNs, VTs can capture global relations between image elements and they potentially have a larger representation capacity. However, the lack of the typical convolutional inductive bias makes these models more data-hungry than common CNNs. In fact, some local properties of the visual domain which are embedded in the CNN architectural design, in VTs should be learned from samples. In this paper, we empirically analyse different VTs, comparing their robustness in a small training-set regime, and we show that, despite having a comparable accuracy when trained on ImageNet, their performance on smaller datasets can be largely different. Moreover, we propose a self-supervised task which can extract additional information from images with only a negligible computational overhead. This task encourages the VTs to learn spatial relations within an image and makes the VT training much more robust when training data are scarce. Our task is used jointly with the standard (supervised) training and it does not depend on specific architectural choices, thus it can be easily plugged in the existing VTs. Using an extensive evaluation with different VTs and datasets, we show that our method can improve (sometimes dramatically) the final accuracy of the VTs. Our code is available at: https://github.com/yhlleo/VTs-Drloc.
Open AccessEfficient Training of Visual Transformers with Small Datasets
Visual Transformers (VTs) are emerging as an architectural paradigm alternative to Convolutional networks (CNNs). Differently from CNNs, VTs can capture global relations between image elements and they potentially have a larger representation capacity. However, the lack of the typical convolutional inductive bias makes these models more data-hungry than common CNNs. In fact, some local properties of the visual domain which are embedded in the CNN architectural design, in VTs should be learned from samples. In this paper, we empirically analyse different VTs, comparing their robustness in a small training-set regime, and we show that, despite having a comparable accuracy when trained on ImageNet, their performance on smaller datasets can be largely different. Moreover, we propose a self-supervised task which can extract additional information from images with only a negligible computational overhead. This task encourages the VTs to learn spatial relations within an image and makes the VT training much more robust when training data are scarce. Our task is used jointly with the standard (supervised) training and it does not depend on specific architectural choices, thus it can be easily plugged in the existing VTs. Using an extensive evaluation with different VTs and datasets, we show that our method can improve (sometimes dramatically) the final accuracy of the VTs. Our code is available at: https://github.com/yhlleo/VTs-Drloc.