Search Results for author:
Found 47 papers, 20 papers with code
FORESCENE: FOREcasting human activity via latent SCENE graphs diffusion
Forecasting human-environment interactions in daily activities is challenging due to the high variability of human behavior.
MaskPlanner: Learning-Based Object-Centric Motion Generation from 3D Point Clouds
Object-Centric Motion Generation (OCMG) plays a key role in a variety of industrial applications$\unicode{x2014}$such as robotic spray painting and welding$\unicode{x2014}$requiring efficient, scalable, and generalizable algorithms to plan multiple long-horizon trajectories over free-form 3D objects.
Hier-EgoPack: Hierarchical Egocentric Video Understanding with Diverse Task Perspectives
To achieve this, we propose a novel hierarchical architecture for temporal reasoning equipped with a GNN layer specifically designed to tackle the challenges of multi-granularity reasoning effectively.
A Modern Take on Visual Relationship Reasoning for Grasp Planning
Interacting with real-world cluttered scenes pose several challenges to robotic agents that need to understand complex spatial dependencies among the observed objects to determine optimal pick sequences or efficient object retrieval strategies.
Transient Fault Tolerant Semantic Segmentation for Autonomous Driving
Deep learning models are crucial for autonomous vehicle perception, but their reliability is challenged by algorithmic limitations and hardware faults.
Finding Lottery Tickets in Vision Models via Data-driven Spectral Foresight Pruning
Recent advances in neural network pruning have shown how it is possible to reduce the computational costs and memory demands of deep learning models before training.
Segmentation Re-thinking Uncertainty Estimation Metrics for Semantic Segmentation
In the domain of computer vision, semantic segmentation emerges as a fundamental application within machine learning, wherein individual pixels of an image are classified into distinct semantic categories.
PolyDiff: Generating 3D Polygonal Meshes with Diffusion Models
In contrast to methods that use alternate 3D shape representations (e. g. implicit representations), our approach is a discrete denoising diffusion probabilistic model that operates natively on the polygonal mesh data structure.
MeshGPT: Generating Triangle Meshes with Decoder-Only Transformers
We introduce MeshGPT, a new approach for generating triangle meshes that reflects the compactness typical of artist-created meshes, in contrast to dense triangle meshes extracted by iso-surfacing methods from neural fields.
Domain Randomization via Entropy Maximization
Varying dynamics parameters in simulation is a popular Domain Randomization (DR) approach for overcoming the reality gap in Reinforcement Learning (RL).
OpenPatch: a 3D patchwork for Out-Of-Distribution detection
We advance the field by introducing OpenPatch that builds on a large pre-trained model and simply extracts from its intermediate features a set of patch representations that describe each known class.
Large Class Separation is not what you need for Relational Reasoning-based OOD Detection
We focus exactly on such a fine-tuning-free OOD detection setting.
Fairness meets Cross-Domain Learning: a new perspective on Models and Metrics
Deep learning-based recognition systems are deployed at scale for several real-world applications that inevitably involve our social life.
Domain Randomization for Robust, Affordable and Effective Closed-loop Control of Soft Robots
Soft robots are gaining popularity thanks to their intrinsic safety to contacts and adaptability.
PaintNet: Unstructured Multi-Path Learning from 3D Point Clouds for Robotic Spray Painting
Popular industrial robotic problems such as spray painting and welding require (i) conditioning on free-shape 3D objects and (ii) planning of multiple trajectories to solve the task.
3DOS: Towards 3D Open Set Learning -- Benchmarking and Understanding Semantic Novelty Detection on Point Clouds
In recent years there has been significant progress in the field of 3D learning on classification, detection and segmentation problems.
Semantic Novelty Detection via Relational Reasoning
We claim that a tailored representation learning strategy may be the right solution for effective and efficient semantic novelty detection.
Online vs. Offline Adaptive Domain Randomization Benchmark
However, transferring the acquired knowledge to the real world can be challenging due to the reality gap.
Fault-Aware Design and Training to Enhance DNNs Reliability with Zero-Overhead
Deep Neural Networks (DNNs) enable a wide series of technological advancements, ranging from clinical imaging, to predictive industrial maintenance and autonomous driving.
Contrastive Learning for Cross-Domain Open World Recognition
The ability to evolve is fundamental for any valuable autonomous agent whose knowledge cannot remain limited to that injected by the manufacturer.
Distance-based Hyperspherical Classification for Multi-source Open-Set Domain Adaptation
Vision systems trained in closed-world scenarios fail when presented with new environmental conditions, new data distributions, and novel classes at deployment time.
Towards Fairness Certification in Artificial Intelligence
Thanks to the great progress of machine learning in the last years, several Artificial Intelligence (AI) techniques have been increasingly moving from the controlled research laboratory settings to our everyday life.
Denoise and Contrast for Category Agnostic Shape Completion
The combined embedding inherits category-agnostic properties from the chosen pretext tasks.
Multi-Modal RGB-D Scene Recognition Across Domains
Indeed, learning to go from RGB to depth and vice-versa is an unsupervised procedure that can be trained jointly on data of multiple cameras and may help to bridge the gap among the extracted feature distributions.
Rethinking Domain Generalization Baselines
Despite being very powerful in standard learning settings, deep learning models can be extremely brittle when deployed in scenarios different from those on which they were trained.
Ranked #63 on
Domain Generalization
on PACS
On the Effectiveness of Image Rotation for Open Set Domain Adaptation
Open Set Domain Adaptation (OSDA) bridges the domain gap between a labeled source domain and an unlabeled target domain, while also rejecting target classes that are not present in the source.
Self-Supervised Learning Across Domains
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.
Ranked #88 on
Domain Generalization
on PACS
One-Shot Unsupervised Cross-Domain Detection
Despite impressive progress in object detection over the last years, it is still an open challenge to reliably detect objects across visual domains.
Bridging the gap between Natural and Medical Images through Deep Colorization
Deep learning has thrived by training on large-scale datasets.
Joint Supervised and Self-Supervised Learning for 3D Real-World Challenges
Point cloud processing and 3D shape understanding are very challenging tasks for which deep learning techniques have demonstrated great potentials.
Learning to Generalize One Sample at a Time with Self-Supervision
Although deep networks have significantly increased the performance of visual recognition methods, it is still challenging to achieve the robustness across visual domains that is necessary for real-world applications.
Tackling Partial Domain Adaptation with Self-Supervision
Domain adaptation approaches have shown promising results in reducing the marginal distribution difference among visual domains.
Domain Generalization by Solving Jigsaw Puzzles
Human adaptability relies crucially on the ability to learn and merge knowledge both from supervised and unsupervised learning: the parents point out few important concepts, but then the children fill in the gaps on their own.
Ranked #3 on
Domain Generalization
on NICO Animal
Hallucinating Agnostic Images to Generalize Across Domains
The ability to generalize across visual domains is crucial for the robustness of artificial recognition systems.
Adaptive Deep Learning through Visual Domain Localization
We exploit this through the learning of maps that spatially ground the domain and quantify the degree of shift, embedded into an end-to-end deep domain adaptation architecture.
From source to target and back: symmetric bi-directional adaptive GAN
The effectiveness of generative adversarial approaches in producing images according to a specific style or visual domain has recently opened new directions to solve the unsupervised domain adaptation problem.
Ranked #14 on
Domain Adaptation
on SVHN-to-MNIST
Training Deep Networks without Learning Rates Through Coin Betting
Instead, we reduce the optimization process to a game of betting on a coin and propose a learning-rate-free optimal algorithm for this scenario.
Ranked #1 on
Stochastic Optimization
on MNIST
Learning Deep Visual Object Models From Noisy Web Data: How to Make it Work
We contribute to this research thread with two findings: (1) a study correlating a given level of noisily labels to the expected drop in accuracy, for two deep architectures, on two different types of noise, that clearly identifies GoogLeNet as a suitable architecture for learning from Web data; (2) a recipe for the creation of Web datasets with minimal noise and maximum visual variability, based on a visual and natural language processing concept expansion strategy.
Combining Multiple Cues for Visual Madlibs Question Answering
This paper presents an approach for answering fill-in-the-blank multiple choice questions from the Visual Madlibs dataset.
Solving Visual Madlibs with Multiple Cues
This paper focuses on answering fill-in-the-blank style multiple choice questions from the Visual Madlibs dataset.
Learning the Roots of Visual Domain Shift
In this paper we focus on the spatial nature of visual domain shift, attempting to learn where domain adaptation originates in each given image of the source and target set.
Active Transfer Learning with Zero-Shot Priors: Reusing Past Datasets for Future Tasks
How can we reuse existing knowledge, in the form of available datasets, when solving a new and apparently unrelated target task from a set of unlabeled data?
A Deeper Look at Dataset Bias
The presence of a bias in each image data collection has recently attracted a lot of attention in the computer vision community showing the limits in generalization of any learning method trained on a specific dataset.
Joint cross-domain classification and subspace learning for unsupervised adaptation
Domain adaptation aims at adapting the knowledge acquired on a source domain to a new different but related target domain.
Location Recognition Over Large Time Lags
Would it be possible to automatically associate ancient pictures to modern ones and create fancy cultural heritage city maps?
A Testbed for Cross-Dataset Analysis
Since its beginning visual recognition research has tried to capture the huge variability of the visual world in several image collections.
