Enver Sangineto

Mang Ning, Enver Sangineto, Angelo Porrello et al.

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

Aleksandr Ermolov, Enver Sangineto, Nicu Sebe

Environments in Reinforcement Learning are usually only partially observable. To address this problem, a possible solution is to provide the agent with information about the past. However, providing complete observations of numerous steps can be excessive. Inspired by human memory, we propose to represent history with only important changes in the environment and, in our approach, to obtain automatically this representation using self-supervision. Our method (TempAl) aligns temporally-close frames, revealing a general, slowly varying state of the environment. This procedure is based on contrastive loss, which pulls embeddings of nearby observations to each other while pushing away other samples from the batch. It can be interpreted as a metric that captures the temporal relations of observations. We propose to combine both common instantaneous and our history representation and we evaluate TempAl on all available Atari games from the Arcade Learning Environment. TempAl surpasses the instantaneous-only baseline in 35 environments out of 49. The source code of the method and of all the experiments is available at https://github.com/htdt/tempal.

Jichao Zhang, Jingjing Chen, Hao Tang et al.

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 and high-resolution CelebHQGaze. 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 arts. Code is available at https://github.com/zhangqianhui/GazeAnimationV2

Zipeng Xu, Enver Sangineto, Nicu Sebe

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.

Zipeng Xu, Songlong Xing, Enver Sangineto et al.

Owing to the power of vision-language foundation models, e.g., CLIP, the area of image synthesis has seen recent important advances. Particularly, for style transfer, CLIP enables transferring more general and abstract styles without collecting the style images in advance, as the style can be efficiently described with natural language, and the result is optimized by minimizing the CLIP similarity between the text description and the stylized image. However, directly using CLIP to guide style transfer leads to undesirable artifacts (mainly written words and unrelated visual entities) spread over the image. In this paper, we propose SpectralCLIP, which is based on a spectral representation of the CLIP embedding sequence, where most of the common artifacts occupy specific frequencies. By masking the band including these frequencies, we can condition the generation process to adhere to the target style properties (e.g., color, texture, paint stroke, etc.) while excluding the generation of larger-scale structures corresponding to the artifacts. Experimental results show that SpectralCLIP prevents the generation of artifacts effectively in quantitative and qualitative terms, without impairing the stylisation quality. We also apply SpectralCLIP to text-conditioned image generation and show that it prevents written words in the generated images. Our code is available at https://github.com/zipengxuc/SpectralCLIP.

Elia Peruzzo, Enver Sangineto, Yahui Liu et al.

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.

Wenhui Tan, Fiorenzo Parascandolo, Enver Sangineto et al.

Large Reasoning Models (LRMs) have recently achieved strong mathematical and code reasoning performance through Reinforcement Learning (RL) post-training. However, we show that modern reasoning post-training induces an unintended exploration collapse: temperature-based sampling no longer increases pass@$n$ accuracy. Empirically, the final-layer posterior of post-trained LRMs exhibit sharply reduced entropy, while the entropy of intermediate layers remains relatively high. Motivated by this entropy asymmetry, we propose Latent Exploration Decoding (LED), a depth-conditioned decoding strategy. LED aggregates intermediate posteriors via cumulative sum and selects depth configurations with maximal entropy as exploration candidates. Without additional training or parameters, LED consistently improves pass@1 and pass@16 accuracy by 0.61 and 1.03 percentage points across multiple reasoning benchmarks and models. Project page: https://GitHub.com/Xiaomi-Research/LED.

Simone Luetto, Fabrizio Garuti, Enver Sangineto et al.

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. Specifically 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 items, makes this adaptation difficult. In this paper we propose a Transformer architecture to represent heterogeneous time-dependent tabular data, in which numerical features are represented using a set of frequency functions and the whole network is uniformly trained with a unique loss function.

Yahui Liu, Enver Sangineto, Yajing Chen et al.

Multi-domain image-to-image (I2I) translations can transform a source image according to the style of a target domain. One important, desired characteristic of these transformations, is their graduality, which corresponds to a smooth change between the source and the target image when their respective latent-space representations are linearly interpolated. However, state-of-the-art methods usually perform poorly when evaluated using inter-domain interpolations, often producing abrupt changes in the appearance or non-realistic intermediate images. In this paper, we argue that one of the main reasons behind this problem is the lack of sufficient inter-domain training data and we propose two different regularization methods to alleviate this issue: a new shrinkage loss, which compacts the latent space, and a Mixup data-augmentation strategy, which flattens the style representations between domains. We also propose a new metric to quantitatively evaluate the degree of the interpolation smoothness, an aspect which is not sufficiently covered by the existing I2I translation metrics. Using both our proposed metric and standard evaluation protocols, we show that our regularization techniques can improve the state-of-the-art multi-domain I2I translations by a large margin. Our code will be made publicly available upon the acceptance of this article.

Fiorenzo Parascandolo, Wenhui Tan, Enver Sangineto et al.

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.

Martin Menabue, Emanuele Frascaroli, Matteo Boschini et al.

Prompt-tuning methods for Continual Learning (CL) freeze a large pre-trained model and train a few parameter vectors termed prompts. Most of these methods organize these vectors in a pool of key-value pairs and use the input image as query to retrieve the prompts (values). However, as keys are learned while tasks progress, the prompting selection strategy is itself subject to catastrophic forgetting, an issue often overlooked by existing approaches. For instance, prompts introduced to accommodate new tasks might end up interfering with previously learned prompts. To make the selection strategy more stable, we leverage a foundation model (CLIP) to select our prompts within a two-level adaptation mechanism. Specifically, the first level leverages a standard textual prompt pool for the CLIP textual encoder, leading to stable class prototypes. The second level, instead, uses these prototypes along with the query image as keys to index a second pool. The retrieved prompts serve to adapt a pre-trained ViT, granting plasticity. In doing so, we also propose a novel residual mechanism to transfer CLIP semantics to the ViT layers. Through extensive analysis on established CL benchmarks, we show that our method significantly outperforms both state-of-the-art CL approaches and the zero-shot CLIP test. Notably, our findings hold true even for datasets with a substantial domain gap w.r.t. the pre-training knowledge of the backbone model, as showcased by experiments on satellite imagery and medical datasets. The codebase is available at https://github.com/aimagelab/mammoth.

Jichao Zhang, Enver Sangineto, Hao Tang et al.

Generative Neural Radiance Field (GNeRF) models, which extract implicit 3D representations from 2D images, have recently been shown to produce realistic images representing rigid/semi-rigid objects, such as human faces or cars. However, they usually struggle to generate high-quality images representing non-rigid objects, such as the human body, which is of a great interest for many computer graphics applications. This paper proposes a 3D-aware Semantic-Guided Generative Model (3D-SGAN) for human image synthesis, which combines a GNeRF with a texture generator. The former learns an implicit 3D representation of the human body and outputs a set of 2D semantic segmentation masks. The latter transforms these semantic masks into a real image, adding a realistic texture to the human appearance. Without requiring additional 3D information, our model can learn 3D human representations with a photo-realistic, controllable generation. Our experiments on the DeepFashion dataset show that 3D-SGAN significantly outperforms the most recent baselines. The code is available at https://github.com/zhangqianhui/3DSGAN

Yahui Liu, Enver Sangineto, Wei Bi et al.

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.

Jichao Zhang, Aliaksandr Siarohin, Hao Tang et al.

Controllable person image generation aims to produce realistic human images with desirable attributes such as a given pose, cloth textures, or hairstyles. However, the large spatial misalignment between source and target images makes the standard image-to-image translation architectures unsuitable for this task. Most state-of-the-art methods focus on alignment for global pose-transfer tasks. However, they fail to deal with region-specific texture-transfer tasks, especially for person images with complex textures. To solve this problem, we propose a novel Spatially-Adaptive Warped Normalization (SAWN) which integrates a learned flow-field to warp modulation parameters. It allows us to efficiently align person spatially-adaptive styles with pose features. Moreover, we propose a novel Self-Training Part Replacement (STPR) strategy to refine the model for the texture-transfer task, which improves the quality of the generated clothes and the preservation ability of non-target regions. Our experimental results on the widely used DeepFashion dataset demonstrate a significant improvement of the proposed method over the state-of-the-art methods on pose-transfer and texture-transfer tasks. The code is available at https://github.com/zhangqianhui/Sawn.

Jichao Zhang, Jingjing Chen, Hao Tang et al.

In this paper we address the problem of unsupervised gaze correction in the wild, presenting a solution that works without the need for precise annotations of the gaze angle and the head pose. We have created a new dataset called CelebAGaze, which consists of two domains X, Y, where the eyes are either staring at the camera or somewhere else. Our method consists of three novel modules: the Gaze Correction module (GCM), the Gaze Animation module (GAM), and the Pretrained Autoencoder module (PAM). Specifically, GCM and GAM separately train a dual in-painting network using data from the domain $X$ for gaze correction and data from the domain $Y$ for gaze animation. Additionally, a Synthesis-As-Training method is proposed when training GAM to encourage the features encoded from the eye region to be correlated with the angle information, resulting in a gaze animation which can be achieved by interpolation in the latent space. To further preserve the identity information~(e.g., eye shape, iris color), we propose the PAM with an Autoencoder, which is based on Self-Supervised mirror learning where the bottleneck features are angle-invariant and which works as an extra input to the dual in-painting models. Extensive experiments validate the effectiveness of the proposed method for gaze correction and gaze animation in the wild and demonstrate the superiority of our approach in producing more compelling results than state-of-the-art baselines. Our code, the pretrained models and the supplementary material are available at: https://github.com/zhangqianhui/GazeAnimation.

Aleksandr Ermolov, Aliaksandr Siarohin, Enver Sangineto et al.

Most of the current self-supervised representation learning (SSL) methods are based on the contrastive loss and the instance-discrimination task, where augmented versions of the same image instance ("positives") are contrasted with instances extracted from other images ("negatives"). For the learning to be effective, many negatives should be compared with a positive pair, which is computationally demanding. In this paper, we propose a different direction and a new loss function for SSL, which is based on the whitening of the latent-space features. The whitening operation has a "scattering" effect on the batch samples, avoiding degenerate solutions where all the sample representations collapse to a single point. Our solution does not require asymmetric networks and it is conceptually simple. Moreover, since negatives are not needed, we can extract multiple positive pairs from the same image instance. The source code of the method and of all the experiments is available at: https://github.com/htdt/self-supervised.

Jingjing Chen, Jichao Zhang, Enver Sangineto et al.

Gaze redirection aims at manipulating the gaze of a given face image with respect to a desired direction (i.e., a reference angle) and it can be applied to many real life scenarios, such as video-conferencing or taking group photos. However, previous work on this topic mainly suffers of two limitations: (1) Low-quality image generation and (2) Low redirection precision. In this paper, we propose to alleviate these problems by means of a novel gaze redirection framework which exploits both a numerical and a pictorial direction guidance, jointly with a coarse-to-fine learning strategy. Specifically, the coarse branch learns the spatial transformation which warps input image according to desired gaze. On the other hand, the fine-grained branch consists of a generator network with conditional residual image learning and a multi-task discriminator. This second branch reduces the gap between the previously warped image and the ground-truth image and recovers finer texture details. Moreover, we propose a numerical and pictorial guidance module~(NPG) which uses a pictorial gazemap description and numerical angles as an extra guide to further improve the precision of gaze redirection. Extensive experiments on a benchmark dataset show that the proposed method outperforms the state-of-the-art approaches in terms of both image quality and redirection precision. The code is available at https://github.com/jingjingchen777/CFGR

Fabrizio Garuti, Enver Sangineto, Simone Luetto et al.

Tabular data generation has recently attracted a growing interest due to its different application scenarios. However, generating time series of tabular data, where each element of the series depends on the others, remains a largely unexplored domain. This gap is probably due to the difficulty of jointly solving different problems, the main of which are the heterogeneity of tabular data (a problem common to non-time-dependent approaches) and the variable length of a time series. In this paper, we propose a Diffusion Transformers (DiTs) based approach for tabular data series generation. Inspired by the recent success of DiTs in image and video generation, we extend this framework to deal with heterogeneous data and variable-length sequences. Using extensive experiments on six datasets, we show that the proposed approach outperforms previous work by a large margin.

Fiorenzo Parascandolo, Nicholas Moratelli, Enver Sangineto et al.

Recent work has empirically shown that Vision-Language Models (VLMs) struggle to fully understand the compositional properties of the human language, usually modeling an image caption as a "bag of words". As a result, they perform poorly on compositional tasks, which require a deeper understanding of the different entities of a sentence (subject, verb, etc.) jointly with their mutual relationships in order to be solved. In this paper, we model the dependency relations among textual and visual tokens using a Causal Graphical Model (CGM), built using a dependency parser, and we train a decoder conditioned by the VLM visual encoder. Differently from standard autoregressive or parallel predictions, our decoder's generative process is partially-ordered following the CGM structure. This structure encourages the decoder to learn only the main causal dependencies in a sentence discarding spurious correlations. Using extensive experiments on five compositional benchmarks, we show that our method significantly outperforms all the state-of-the-art compositional approaches by a large margin, and it also improves over methods trained using much larger datasets.

Mattia Bernardi, Chiara Cappellino, Matteo Mosconi et al.

Although recent Open-Vocabulary Object Detection architectures, such as Grounding DINO, demonstrate strong zero-shot capabilities, their performance degrades significantly under domain shifts. Moreover, many domains of practical interest, such as nighttime or foggy scenes, lack large annotated datasets, preventing direct fine-tuning. In this paper, we introduce Aligned Basis Relocation for Adaptation(ABRA), a method that transfers class-specific detection knowledge from a labeled source domain to a target domain where no training images containing these classes are accessible. ABRA formulates this adaptation as a geometric transport problem in the weight space of a pretrained detector, aligning source and target domain experts to transport class-specific knowledge. Extensive experiments across challenging domain shifts demonstrate that ABRA successfully teleports class-level specialization under multiple adverse conditions. Our code will be made public upon acceptance.

Chengxi Min, Wei Wang, Yahui Liu et al.

Mixture-of-Experts (MoE) models have emerged as a promising direction for scaling vision architectures efficiently. Among them, Soft MoE improves training stability by assigning each token to all experts via continuous dispatch weights. However, current designs overlook the semantic structure which is implicitly encoded in these weights, resulting in suboptimal expert routing. In this paper, we discover that dispatch weights in Soft MoE inherently exhibit segmentation-like patterns but are not explicitly aligned with semantic regions. Motivated by this observation, we propose a foreground-guided enhancement strategy. Specifically, we introduce a spatially aware auxiliary loss that encourages expert activation to align with semantic foreground regions. To further reinforce this supervision, we integrate a lightweight LayerScale mechanism that improves information flow and stabilizes optimization in skip connections. Our method necessitates only minor architectural adjustments and can be seamlessly integrated into prevailing Soft MoE frameworks. Comprehensive experiments on ImageNet-1K and multiple smaller-scale classification benchmarks not only showcase consistent performance enhancements but also reveal more interpretable expert routing mechanisms.

Nicola Dall'Asen, Willi Menapace, Elia Peruzzo et al.

The process of painting fosters creativity and rational planning. However, existing generative AI mostly focuses on producing visually pleasant artworks, without emphasizing the painting process. We introduce a novel task, Collaborative Neural Painting (CNP), to facilitate collaborative art painting generation between humans and machines. Given any number of user-input brushstrokes as the context or just the desired object class, CNP should produce a sequence of strokes supporting the completion of a coherent painting. Importantly, the process can be gradual and iterative, so allowing users' modifications at any phase until the completion. Moreover, we propose to solve this task using a painting representation based on a sequence of parametrized strokes, which makes it easy both editing and composition operations. These parametrized strokes are processed by a Transformer-based architecture with a novel attention mechanism to model the relationship between the input strokes and the strokes to complete. We also propose a new masking scheme to reflect the interactive nature of CNP and adopt diffusion models as the basic learning process for its effectiveness and diversity in the generative field. Finally, to develop and validate methods on the novel task, we introduce a new dataset of painted objects and an evaluation protocol to benchmark CNP both quantitatively and qualitatively. We demonstrate the effectiveness of our approach and the potential of the CNP task as a promising avenue for future research.

Enrico Fini, Enver Sangineto, Stéphane Lathuilière et al.

In this paper, we study the problem of Novel Class Discovery (NCD). NCD aims at inferring novel object categories in an unlabeled set by leveraging from prior knowledge of a labeled set containing different, but related classes. Existing approaches tackle this problem by considering multiple objective functions, usually involving specialized loss terms for the labeled and the unlabeled samples respectively, and often requiring auxiliary regularization terms. In this paper, we depart from this traditional scheme and introduce a UNified Objective function (UNO) for discovering novel classes, with the explicit purpose of favoring synergy between supervised and unsupervised learning. Using a multi-view self-labeling strategy, we generate pseudo-labels that can be treated homogeneously with ground truth labels. This leads to a single classification objective operating on both known and unknown classes. Despite its simplicity, UNO outperforms the state of the art by a significant margin on several benchmarks (~+10% on CIFAR-100 and +8% on ImageNet). The project page is available at: https://ncd-uno.github.io.

Yahui Liu, Enver Sangineto, Yajing Chen et al.

Image-to-Image (I2I) multi-domain translation models are usually evaluated also using the quality of their semantic interpolation results. However, state-of-the-art models frequently show abrupt changes in the image appearance during interpolation, and usually perform poorly in interpolations across domains. In this paper, we propose a new training protocol based on three specific losses which help a translation network to learn a smooth and disentangled latent style space in which: 1) Both intra- and inter-domain interpolations correspond to gradual changes in the generated images and 2) The content of the source image is better preserved during the translation. Moreover, we propose a novel evaluation metric to properly measure the smoothness of latent style space of I2I translation models. The proposed method can be plugged into existing translation approaches, and our extensive experiments on different datasets show that it can significantly boost the quality of the generated images and the graduality of the interpolations.

Enrico Fini, Stéphane Lathuilière, Enver Sangineto et al.

Continual Learning (CL) aims to develop agents emulating the human ability to sequentially learn new tasks while being able to retain knowledge obtained from past experiences. In this paper, we introduce the novel problem of Memory-Constrained Online Continual Learning (MC-OCL) which imposes strict constraints on the memory overhead that a possible algorithm can use to avoid catastrophic forgetting. As most, if not all, previous CL methods violate these constraints, we propose an algorithmic solution to MC-OCL: Batch-level Distillation (BLD), a regularization-based CL approach, which effectively balances stability and plasticity in order to learn from data streams, while preserving the ability to solve old tasks through distillation. Our extensive experimental evaluation, conducted on three publicly available benchmarks, empirically demonstrates that our approach successfully addresses the MC-OCL problem and achieves comparable accuracy to prior distillation methods requiring higher memory overhead.

Subhankar Roy, Aliaksandr Siarohin, Enver Sangineto et al.

Most domain adaptation methods consider the problem of transferring knowledge to the target domain from a single source dataset. However, in practical applications, we typically have access to multiple sources. In this paper we propose the first approach for Multi-Source Domain Adaptation (MSDA) based on Generative Adversarial Networks. Our method is inspired by the observation that the appearance of a given image depends on three factors: the domain, the style (characterized in terms of low-level features variations) and the content. For this reason we propose to project the image features onto a space where only the dependence from the content is kept, and then re-project this invariant representation onto the pixel space using the target domain and style. In this way, new labeled images can be generated which are used to train a final target classifier. We test our approach using common MSDA benchmarks, showing that it outperforms state-of-the-art methods.

Stéphane Lathuilière, Enver Sangineto, Aliaksandr Siarohin et al.

We present a generalization of the person-image generation task, in which a human image is generated conditioned on a target pose and a set X of source appearance images. In this way, we can exploit multiple, possibly complementary images of the same person which are usually available at training and at testing time. The solution we propose is mainly based on a local attention mechanism which selects relevant information from different source image regions, avoiding the necessity to build specific generators for each specific cardinality of X. The empirical evaluation of our method shows the practical interest of addressing the person-image generation problem in a multi-source setting.

Aliaksandr Siarohin, Stéphane Lathuilière, Enver Sangineto et al.

In this paper, we address the problem of generating person images conditioned on both pose and appearance information. Specifically, given an image xa of a person and a target pose P(xb), extracted from a different image xb, we synthesize a new image of that person in pose P(xb), while preserving the visual details in xa. In order to deal with pixel-to-pixel misalignments caused by the pose differences between P(xa) and P(xb), we introduce deformable skip connections in the generator of our Generative Adversarial Network. Moreover, a nearest-neighbour loss is proposed instead of the common L1 and L2 losses in order to match the details of the generated image with the target image. Quantitative and qualitative results, using common datasets and protocols recently proposed for this task, show that our approach is competitive with respect to the state of the art. Moreover, we conduct an extensive evaluation using off-the-shell person re-identification (Re-ID) systems trained with person-generation based augmented data, which is one of the main important applications for this task. Our experiments show that our Deformable GANs can significantly boost the Re-ID accuracy and are even better than data-augmentation methods specifically trained using Re-ID losses.

Subhankar Roy, Enver Sangineto, Begüm Demir et al.

Hashing methods have been recently found very effective in retrieval of remote sensing (RS) images due to their computational efficiency and fast search speed. The traditional hashing methods in RS usually exploit hand-crafted features to learn hash functions to obtain binary codes, which can be insufficient to optimally represent the information content of RS images. To overcome this problem, in this paper we introduce a metric-learning based hashing network, which learns: 1) a semantic-based metric space for effective feature representation; and 2) compact binary hash codes for fast archive search. Our network considers an interplay of multiple loss functions that allows to jointly learn a metric based semantic space facilitating similar images to be clustered together in that target space and at the same time producing compact final activations that lose negligible information when binarized. Experiments carried out on two benchmark RS archives point out that the proposed network significantly improves the retrieval performance under the same retrieval time when compared to the state-of-the-art hashing methods in RS.

Subhankar Roy, Aliaksandr Siarohin, Enver Sangineto et al.

A classifier trained on a dataset seldom works on other datasets obtained under different conditions due to domain shift. This problem is commonly addressed by domain adaptation methods. In this work we introduce a novel deep learning framework which unifies different paradigms in unsupervised domain adaptation. Specifically, we propose domain alignment layers which implement feature whitening for the purpose of matching source and target feature distributions. Additionally, we leverage the unlabeled target data by proposing the Min-Entropy Consensus loss, which regularizes training while avoiding the adoption of many user-defined hyper-parameters. We report results on publicly available datasets, considering both digit classification and object recognition tasks. We show that, in most of our experiments, our approach improves upon previous methods, setting new state-of-the-art performances.

Aliaksandr Siarohin, Enver Sangineto, Nicu Sebe

Batch Normalization (BN) is a common technique used to speed-up and stabilize training. On the other hand, the learnable parameters of BN are commonly used in conditional Generative Adversarial Networks (cGANs) for representing class-specific information using conditional Batch Normalization (cBN). In this paper we propose to generalize both BN and cBN using a Whitening and Coloring based batch normalization. We show that our conditional Coloring can represent categorical conditioning information which largely helps the cGAN qualitative results. Moreover, we show that full-feature whitening is important in a general GAN scenario in which the training process is known to be highly unstable. We test our approach on different datasets and using different GAN networks and training protocols, showing a consistent improvement in all the tested frameworks. Our CIFAR-10 conditioned results are higher than all previous works on this dataset.

Aliaksandr Siarohin, Enver Sangineto, Stephane Lathuiliere et al.

In this paper we address the problem of generating person images conditioned on a given pose. Specifically, given an image of a person and a target pose, we synthesize a new image of that person in the novel pose. In order to deal with pixel-to-pixel misalignments caused by the pose differences, we introduce deformable skip connections in the generator of our Generative Adversarial Network. Moreover, a nearest-neighbour loss is proposed instead of the common L1 and L2 losses in order to match the details of the generated image with the target image. We test our approach using photos of persons in different poses and we compare our method with previous work in this area showing state-of-the-art results in two benchmarks. Our method can be applied to the wider field of deformable object generation, provided that the pose of the articulated object can be extracted using a keypoint detector.

Mahdyar Ravanbakhsh, Moin Nabi, Enver Sangineto et al.

In this paper we address the abnormality detection problem in crowded scenes. We propose to use Generative Adversarial Nets (GANs), which are trained using normal frames and corresponding optical-flow images in order to learn an internal representation of the scene normality. Since our GANs are trained with only normal data, they are not able to generate abnormal events. At testing time the real data are compared with both the appearance and the motion representations reconstructed by our GANs and abnormal areas are detected by computing local differences. Experimental results on challenging abnormality detection datasets show the superiority of the proposed method compared to the state of the art in both frame-level and pixel-level abnormality detection tasks.

Mahdyar Ravanbakhsh, Enver Sangineto, Moin Nabi et al.

Abnormal crowd behaviour detection attracts a large interest due to its importance in video surveillance scenarios. However, the ambiguity and the lack of sufficient abnormal ground truth data makes end-to-end training of large deep networks hard in this domain. In this paper we propose to use Generative Adversarial Nets (GANs), which are trained to generate only the normal distribution of the data. During the adversarial GAN training, a discriminator (D) is used as a supervisor for the generator network (G) and vice versa. At testing time we use D to solve our discriminative task (abnormality detection), where D has been trained without the need of manually-annotated abnormal data. Moreover, in order to prevent G learn a trivial identity function, we use a cross-channel approach, forcing G to transform raw-pixel data in motion information and vice versa. The quantitative results on standard benchmarks show that our method outperforms previous state-of-the-art methods in both the frame-level and the pixel-level evaluation.

Ravi Shekhar, Sandro Pezzelle, Yauhen Klimovich et al.

In this paper, we aim to understand whether current language and vision (LaVi) models truly grasp the interaction between the two modalities. To this end, we propose an extension of the MSCOCO dataset, FOIL-COCO, which associates images with both correct and "foil" captions, that is, descriptions of the image that are highly similar to the original ones, but contain one single mistake ("foil word"). We show that current LaVi models fall into the traps of this data and perform badly on three tasks: a) caption classification (correct vs. foil); b) foil word detection; c) foil word correction. Humans, in contrast, have near-perfect performance on those tasks. We demonstrate that merely utilising language cues is not enough to model FOIL-COCO and that it challenges the state-of-the-art by requiring a fine-grained understanding of the relation between text and image.

Mahdyar Ravanbakhsh, Moin Nabi, Hossein Mousavi et al.

Most of the crowd abnormal event detection methods rely on complex hand-crafted features to represent the crowd motion and appearance. Convolutional Neural Networks (CNN) have shown to be a powerful tool with excellent representational capacities, which can leverage the need for hand-crafted features. In this paper, we show that keeping track of the changes in the CNN feature across time can facilitate capturing the local abnormality. We specifically propose a novel measure-based method which allows measuring the local abnormality in a video by combining semantic information (inherited from existing CNN models) with low-level Optical-Flow. One of the advantage of this method is that it can be used without the fine-tuning costs. The proposed method is validated on challenging abnormality detection datasets and the results show the superiority of our method compared to the state-of-the-art methods.

Enver Sangineto, Moin Nabi, Dubravko Culibrk et al.

In a weakly-supervised scenario object detectors need to be trained using image-level annotation alone. Since bounding-box-level ground truth is not available, most of the solutions proposed so far are based on an iterative, Multiple Instance Learning framework in which the current classifier is used to select the highest-confidence boxes in each image, which are treated as pseudo-ground truth in the next training iteration. However, the errors of an immature classifier can make the process drift, usually introducing many of false positives in the training dataset. To alleviate this problem, we propose in this paper a training protocol based on the self-paced learning paradigm. The main idea is to iteratively select a subset of images and boxes that are the most reliable, and use them for training. While in the past few years similar strategies have been adopted for SVMs and other classifiers, we are the first showing that a self-paced approach can be used with deep-network-based classifiers in an end-to-end training pipeline. The method we propose is built on the fully-supervised Fast-RCNN architecture and can be applied to similar architectures which represent the input image as a bag of boxes. We show state-of-the-art results on Pascal VOC 2007, Pascal VOC 2010 and ILSVRC 2013. On ILSVRC 2013 our results based on a low-capacity AlexNet network outperform even those weakly-supervised approaches which are based on much higher-capacity networks.