FCFabio Maria Carlucci

Fabio Maria Carlucci

*This is an algorithmically generated author record based on publicly available information.

Fabio Maria Carlucci has a total of 35 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Manas: multi-agent neural architecture search

    by Vasco Lopes, Fabio Maria Carlucci, Pedro M. Esperança, Marco Singh, Antoine Yang, Victor Gabillon, Hang Xu, Zewei Chen, Jun Wang


  • Open Access

    MANAS: Multi-Agent Neural Architecture Search

    by Vasco Lopes, Fabio Maria Carlucci, Pedro M Esperança, Marco Singh, Victor Gabillon, Antoine Yang, Hang Xu, Zewei Chen, Jun Wang

    The Neural Architecture Search (NAS) problem is typically formulated as a graph search problem where the goal is to learn the optimal operations over edges in order to maximise a graph-level global objective. Due to the large architecture parameter space, efficiency is a key bottleneck preventing NAS from its practical use. In this paper, we address the issue by framing NAS as a multi-agent problem where agents control a subset of the network and coordinate to reach optimal architectures. We provide two distinct lightweight implementations, with reduced memory requirements (1/8th of state-of-the-art), and performances above those of much more computationally expensive methods. Theoretically, we demonstrate vanishing regrets of the form O(sqrt(T)), with T being the total number of rounds. Finally, aware that random search is an, often ignored, effective baseline we perform additional experiments on 3 alternative datasets and 2 network configurations, and achieve favourable results in comparison.

  • Open Access

    Adversarial Branch Architecture Search for Unsupervised Domain Adaptation

    by Luca Robbiano, Muhammad Rameez Ur Rahman, Fabio Galasso, Barbara Caputo, Fabio Maria Carlucci

    Unsupervised Domain Adaptation (UDA) is a key issue in visual recognition, as it allows to bridge different visual domains enabling robust performances in the real world. To date, all proposed approaches rely on human expertise to manually adapt a given UDA method (e.g. DANN) to a specific backbone architecture (e.g. ResNet). This dependency on handcrafted designs limits the applicability of a given approach in time, as old methods need to be constantly adapted to novel backbones. Existing Neural Architecture Search (NAS) approaches cannot be directly applied to mitigate this issue, as they rely on labels that are not available in the UDA setting. Furthermore, most NAS methods search for full architectures, which precludes the use of pre-trained models, essential in a vast range of UDA settings for reaching SOTA results. To the best of our knowledge, no prior work has addressed these aspects in the context of NAS for UDA. Here we tackle both aspects with an Adversarial Branch Architecture Search for UDA (ABAS): i. we address the lack of target labels by a novel data-driven ensemble approach for model selection; and ii. we search for an auxiliary adversarial branch, attached to a pre-trained backbone, which drives the domain alignment. We extensively validate ABAS to improve two modern UDA techniques, DANN and ALDA, on three standard visual recognition datasets (Office31, Office-Home and PACS). In all cases, ABAS robustly finds the adversarial branch architectures and parameters which yield best performances.

  • Self-Supervised Learning Across Domains

    by Silvia Bucci, Antonio D'INnocente, Yujun Liao, Fabio Maria Carlucci, Barbara Caputo, Tatiana Tommasi

    Human adaptability relies crucially on learning and merging knowledge from both supervised and unsupervised tasks: the parents point out few important concepts, but then the children fill in the gaps on their own. This is particularly effective, because supervised learning can never be exhaustive and thus learning autonomously allows to discover invariances and regularities that help to generalize. In this paper we propose to apply a similar approach to the problem of object recognition across domains: our model learns the semantic labels in a supervised fashion, and broadens its understanding of the data by learning from self-supervised signals on the same images. This secondary task helps the network to focus on object shapes, learning concepts like spatial orientation and part correlation, while acting as a regularizer for the classification task over multiple visual domains. Extensive experiments confirm our intuition and show that our multi-task method, combining supervised and self-supervised knowledge, provides competitive results with respect to more complex domain generalization and adaptation solutions. It also proves its potential in the novel and challenging predictive and partial domain adaptation scenarios.


  • MultiDIAL: Domain Alignment Layers for (Multisource) Unsupervised Domain Adaptation

    by Fabio Maria Carlucci, Lorenzo Porzi, Barbara Caputo, Elisa Ricci, Samuel Rota Bulo

    One of the main challenges for developing visual recognition systems working in the wild is to devise computational models immune from the domain shift problem, i.e. accurate when test data are drawn from a (slightly) different data distribution than training samples. In the last decade, several research efforts have been devoted to devise algorithmic solutions for this issue. Recent attempts to mitigate domain shift have resulted into deep learning models for domain adaptation which learn domain-invariant representations by introducing appropriate loss terms, by casting the problem within an adversarial learning framework or by embedding into deep network specific domain normalization layers. This paper describes a novel approach for unsupervised domain adaptation. Similarly to previous works we propose to align the learned representations by embedding them into appropriate network feature normalization layers. Opposite to previous works, our Domain Alignment Layers are designed not only to match the source and target feature distributions but also to automatically learn the degree of feature alignment required at different levels of the deep network. Differently from most previous deep domain adaptation methods, our approach is able to operate in a multi-source setting. Thorough experiments on four publicly available benchmarks confirm the effectiveness of our approach.


  • From Source to Target and Back: Symmetric Bi-Directional Adaptive GAN

    by Paolo Russo, Fabio M. Carlucci, Tatiana Tommasi, Barbara Caputo

    The effectiveness of GANs in producing images according to a specific visual domain has shown potential in unsupervised domain adaptation. Source labeled images have been modified to mimic target samples for training classifiers in the target domain, and inverse mappings from the target to the source domain have also been evaluated, without new image generation. In this paper we aim at getting the best of both worlds by introducing a symmetric mapping among domains. We jointly optimize bi-directional image transformations combining them with target self-labeling. We define a new class consistency loss that aligns the generators in the two directions, imposing to preserve the class identity of an image passing through both domain mappings. A detailed analysis of the reconstructed images, a thorough ablation study and extensive experiments on six different settings confirm the power of our approach.


  • (DE)$^2$CO: Deep Depth Colorization

    by Fabio Maria Carlucci, Paolo Russo, Barbara Caputo

    The ability to classify objects is fundamental for robots. Besides knowledge about their visual appearance, captured by the RGB channel, robots heavily need also depth information to make sense of the world. While the use of deep networks on RGB robot images has benefited from the plethora of results obtained on databases like ImageNet, using convnets on depth images requires mapping them into three-dimensional channels. This transfer learning procedure makes them processable by pretrained deep architectures. Current mappings are based on heuristic assumptions over preprocessing steps and on what depth properties should be most preserved, resulting often in cumbersome data visualizations, and in suboptimal performance in terms of generality and recognition results. Here, we take an alternative route and we attempt instead to learn an optimal colorization mapping for any given pretrained architecture, using as training data a reference RGB-D database. We propose a deep network architecture, exploiting the residual paradigm, that learns how to map depth data to three channel images. A qualitative analysis of the images obtained with this approach clearly indicates that learning the optimal mapping preserves the richness of depth information better than current hand-crafted approaches. Experiments on the Washington, JHUIT-50 and BigBIRD public benchmark databases, using CaffeNet, VGG-16, GoogleNet, and ResNet50 clearly showcase the power of our approach, with gains in performance of up to 16% compared to state of the art competitors on the depth channel only, leading to top performances when dealing with RGB-D data.


  • Just DIAL: DomaIn Alignment Layers for Unsupervised Domain Adaptation

    by Fabio Maria Carlucci, Lorenzo Porzi, Barbara Caputo, Elisa Ricci, Samuel Rota Bulò


  • Deep Depth Domain Adaptation: A Case Study

    by Novi Patricia, Fabio M. Cariucci, Barbara Caputo

    In the era of deep learning, many domain adaptation studies have been done on RGB images but not on depth. One of the reasons is that there are few databases available for researchers to explore domain shift on depth images. The contribution of this paper is to provide a benchmark to the community to study and evaluate deep domain adaptation methods on depth images, and compare the results with those obtained on the corresponding RGB data. We use two variants dataset that follow the settings from the first introduced RGB-D object dataset with 51 categories taken from multiple views. We also explore different colorization methods for depth images such as Colorjet and DE2CO[3]. The experiments are conducted on several deep domain adaptation approaches on RGB and depth images. Our results show that current deep DA methods can work well for RGB images but how to tackle the domain shift problem on depth is still an open question.