Fiora Pirri

Simone Rossetti, Nico Samà, Fiora Pirri

Removing supervision in semantic segmentation is still tricky. Current approaches can deal with common categorical patterns yet resort to multi-stage architectures. We design a novel end-to-end model leveraging local-global patch matching to predict categories, good localization, area and shape of objects for semantic segmentation. The local-global matching is, in turn, compelled by optimal transport plans fulfilling area constraints nearing a solution for exact shape prediction. Our model attains state-of-the-art in Weakly Supervised Semantic Segmentation, only image-level labels, with 75% mIoU on PascalVOC2012 val set and 46% on MS-COCO2014 val set. Dropping the image-level labels and clustering self-supervised learned features to yield pseudo-multi-level labels, we obtain an unsupervised model for semantic segmentation. We also attain state-of-the-art on Unsupervised Semantic Segmentation with 43.6% mIoU on PascalVOC2012 val set and 19.4% on MS-COCO2014 val set. The code is available at https://github.com/deepplants/PC2M.

Simone Rossetti, Damiano Zappia, Marta Sanzari et al.

Weakly Supervised Semantic Segmentation (WSSS) research has explored many directions to improve the typical pipeline CNN plus class activation maps (CAM) plus refinements, given the image-class label as the only supervision. Though the gap with the fully supervised methods is reduced, further abating the spread seems unlikely within this framework. On the other hand, WSSS methods based on Vision Transformers (ViT) have not yet explored valid alternatives to CAM. ViT features have been shown to retain a scene layout, and object boundaries in self-supervised learning. To confirm these findings, we prove that the advantages of transformers in self-supervised methods are further strengthened by Global Max Pooling (GMP), which can leverage patch features to negotiate pixel-label probability with class probability. This work proposes a new WSSS method dubbed ViT-PCM (ViT Patch-Class Mapping), not based on CAM. The end-to-end presented network learns with a single optimization process, refined shape and proper localization for segmentation masks. Our model outperforms the state-of-the-art on baseline pseudo-masks (BPM), where we achieve $69.3\%$ mIoU on PascalVOC 2012 $val$ set. We show that our approach has the least set of parameters, though obtaining higher accuracy than all other approaches. In a sentence, quantitative and qualitative results of our method reveal that ViT-PCM is an excellent alternative to CNN-CAM based architectures.

Alessandro Sebastianelli, Artur Nowakowski, Erika Puglisi et al.

Cloud removal is a relevant topic in Remote Sensing as it fosters the usability of high-resolution optical images for Earth monitoring and study. Related techniques have been analyzed for years with a progressively clearer view of the appropriate methods to adopt, from multi-spectral to inpainting methods. Recent applications of deep generative models and sequence-to-sequence-based models have proved their capability to advance the field significantly. Nevertheless, there are still some gaps, mostly related to the amount of cloud coverage, the density and thickness of clouds, and the occurred temporal landscape changes. In this work, we fill some of these gaps by introducing a novel multi-modal method that uses different sources of information, both spatial and temporal, to restore the whole optical scene of interest. The proposed method introduces an innovative deep model, using the outcomes of both temporal-sequence blending and direct translation from Synthetic Aperture Radar (SAR) to optical images to obtain a pixel-wise restoration of the whole scene. The advantage of our approach is demonstrated across a variety of atmospheric conditions tested on a dataset we have generated and made available. Quantitative and qualitative results prove that the proposed method obtains cloud-free images, preserving scene details without resorting to a huge portion of a clean image and coping with landscape changes.

Luigi Freda, Mario Gianni, Fiora Pirri et al.

Teams of UGVs patrolling harsh and complex 3D environments can experience interference and spatial conflicts with one another. Neglecting the occurrence of these events crucially hinders both soundness and reliability of a patrolling process. This work presents a distributed multi-robot patrolling technique, which uses a two-level coordination strategy to minimize and explicitly manage the occurrence of conflicts and interference. The first level guides the agents to single out exclusive target nodes on a topological map. This target selection relies on a shared idleness representation and a coordination mechanism preventing topological conflicts. The second level hosts coordination strategies based on a metric representation of space and is supported by a 3D SLAM system. Here, each robot path planner negotiates spatial conflicts by applying a multi-robot traversability function. Continuous interactions between these two levels ensure coordination and conflicts resolution. Both simulations and real-world experiments are presented to validate the performances of the proposed patrolling strategy in 3D environments. Results show this is a promising solution for managing spatial conflicts and preventing deadlocks.

Lorenzo Mauro, Edoardo Alati, Marta Sanzari et al.

We consider a novel approach to high-level robot task execution for a robot assistive task. In this work we explore the problem of learning to predict the next subtask by introducing a deep model for both sequencing goals and for visually evaluating the state of a task. We show that deep learning for monitoring robot tasks execution very well supports the interconnection between task-level planning and robot operations. These solutions can also cope with the natural non-determinism of the execution monitor. We show that a deep execution monitor leverages robot performance. We measure the improvement taking into account some robot helping tasks performed at a warehouse.

Lorenzo Mauro, Francesco Puja, Simone Grazioso et al.

Visual search of relevant targets in the environment is a crucial robot skill. We propose a preliminary framework for the execution monitor of a robot task, taking care of the robot attitude to visually searching the environment for targets involved in the task. Visual search is also relevant to recover from a failure. The framework exploits deep reinforcement learning to acquire a "common sense" scene structure and it takes advantage of a deep convolutional network to detect objects and relevant relations holding between them. The framework builds on these methods to introduce a vision-based execution monitoring, which uses classical planning as a backbone for task execution. Experiments show that with the proposed vision-based execution monitor the robot can complete simple tasks and can recover from failures in autonomy.

Fiora Pirri, Lorenzo Mauro, Edoardo Alati et al.

Action anticipation and forecasting in videos do not require a hat-trick, as far as there are signs in the context to foresee how actions are going to be deployed. Capturing these signs is hard because the context includes the past. We propose an end-to-end network for action anticipation and forecasting with memory, to both anticipate the current action and foresee the next one. Experiments on action sequence datasets show excellent results indicating that training on histories with a dynamic memory can significantly improve forecasting performance.

Luigi Freda, Mario Gianni, Fiora Pirri

This work presents a methodology to design trajectory tracking feedback control laws, which embed non-parametric statistical models, such as Gaussian Processes (GPs). The aim is to minimize unmodeled dynamics such as undesired slippages. The proposed approach has the benefit of avoiding complex terramechanics analysis to directly estimate from data the robot dynamics on a wide class of trajectories. Experiments in both real and simulated environments prove that the proposed methodology is promising.

Francesco Puja, Simone Grazioso, Antonio Tammaro et al.

Execution monitor of high-level robot actions can be effectively improved by visual monitoring the state of the world in terms of preconditions and postconditions that hold before and after the execution of an action. Furthermore a policy for searching where to look at, either for verifying the relations that specify the pre and postconditions or to refocus in case of a failure, can tremendously improve the robot execution in an uncharted environment. It is now possible to strongly rely on visual perception in order to make the assumption that the environment is observable, by the amazing results of deep learning. In this work we present visual execution monitoring for a robot executing tasks in an uncharted Lab environment. The execution monitor interacts with the environment via a visual stream that uses two DCNN for recognizing the objects the robot has to deal with and manipulate, and a non-parametric Bayes estimation to discover the relations out of the DCNN features. To recover from lack of focus and failures due to missed objects we resort to visual search policies via deep reinforcement learning.

Marta Sanzari, Valsamis Ntouskos, Fiora Pirri

We present a novel framework for the automatic discovery and recognition of motion primitives in videos of human activities. Given the 3D pose of a human in a video, human motion primitives are discovered by optimizing the `motion flux', a quantity which captures the motion variation of a group of skeletal joints. A normalization of the primitives is proposed in order to make them invariant with respect to a subject anatomical variations and data sampling rate. The discovered primitives are unknown and unlabeled and are unsupervisedly collected into classes via a hierarchical non-parametric Bayes mixture model. Once classes are determined and labeled they are further analyzed for establishing models for recognizing discovered primitives. Each primitive model is defined by a set of learned parameters. Given new video data and given the estimated pose of the subject appearing on the video, the motion is segmented into primitives, which are recognized with a probability given according to the parameters of the learned models. Using our framework we build a publicly available dataset of human motion primitives, using sequences taken from well-known motion capture datasets. We expect that our framework, by providing an objective way for discovering and categorizing human motion, will be a useful tool in numerous research fields including video analysis, human inspired motion generation, learning by demonstration, intuitive human-robot interaction, and human behavior analysis.

Valsamis Ntouskos, Fiora Pirri

We introduce a novel model for spatially varying variational data fusion, driven by point-wise confidence values. The proposed model allows for the joint estimation of the data and the confidence values based on the spatial coherence of the data. We discuss the main properties of the introduced model as well as suitable algorithms for estimating the solution of the corresponding biconvex minimization problem and their convergence. The performance of the proposed model is evaluated considering the problem of depth image fusion by using both synthetic and real data from publicly available datasets.