Search Results for author:
Found 30 papers, 9 papers with code
NIGHT -- Non-Line-of-Sight Imaging from Indirect Time of Flight Data
The acquisition of objects outside the Line-of-Sight of cameras is a very intriguing but also extremely challenging research topic.
When Cars meet Drones: Hyperbolic Federated Learning for Source-Free Domain Adaptation in Adverse Weather
In Federated Learning (FL), multiple clients collaboratively train a global model without sharing private data.
A Modular System for Enhanced Robustness of Multimedia Understanding Networks via Deep Parametric Estimation
To this end, we design a small, modular, and efficient (just 2GFLOPs to process a Full HD image) system to enhance input data for robust downstream multimedia understanding with minimal computational cost.
ALERT-Transformer: Bridging Asynchronous and Synchronous Machine Learning for Real-Time Event-based Spatio-Temporal Data
We propose a novel hybrid pipeline composed of asynchronous sensing and synchronous processing that combines several ideas: (1) an embedding based on PointNet models -- the ALERT module -- that can continuously integrate new and dismiss old events thanks to a leakage mechanism, (2) a flexible readout of the embedded data that allows to feed any downstream model with always up-to-date features at any sampling rate, (3) exploiting the input sparsity in a patch-based approach inspired by Vision Transformer to optimize the efficiency of the method.
Ranked #8 on
Gesture Recognition
on DVS128 Gesture
RECALL+: Adversarial Web-based Replay for Continual Learning in Semantic Segmentation
Catastrophic forgetting of previous knowledge is a critical issue in continual learning typically handled through various regularization strategies.
Exploiting Multiple Priors for Neural 3D Indoor Reconstruction
In this work, we propose a novel neural implicit modeling method that leverages multiple regularization strategies to achieve better reconstructions of large indoor environments, while relying only on images.
SynDrone -- Multi-modal UAV Dataset for Urban Scenarios
The development of computer vision algorithms for Unmanned Aerial Vehicles (UAVs) imagery heavily relies on the availability of annotated high-resolution aerial data.
Continual Road-Scene Semantic Segmentation via Feature-Aligned Symmetric Multi-Modal Network
In this work, we re-frame the task of multimodal semantic segmentation by enforcing a tightly-coupled feature representation and a symmetric information-sharing scheme, which allows our approach to work even when one of the input modalities is missing.
Source-Free Domain Adaptation for RGB-D Semantic Segmentation with Vision Transformers
With the increasing availability of depth sensors, multimodal frameworks that combine color information with depth data are gaining interest.
Asynchronous Federated Continual Learning
We introduce a novel federated learning setting (AFCL) where the continual learning of multiple tasks happens at each client with different orderings and in asynchronous time slots.
DepthFormer: Multimodal Positional Encodings and Cross-Input Attention for Transformer-Based Segmentation Networks
Most approaches for semantic segmentation use only information from color cameras to parse the scenes, yet recent advancements show that using depth data allows to further improve performances.
Learning with Style: Continual Semantic Segmentation Across Tasks and Domains
Then, we address the proposed setup by using style transfer techniques to extend knowledge across domains when learning incremental tasks and a robust distillation framework to effectively recollect task knowledge under incremental domain shift.
Learning Across Domains and Devices: Style-Driven Source-Free Domain Adaptation in Clustered Federated Learning
Federated Learning (FL) has recently emerged as a possible way to tackle the domain shift in real-world Semantic Segmentation (SS) without compromising the private nature of the collected data.
A Low Memory Footprint Quantized Neural Network for Depth Completion of Very Sparse Time-of-Flight Depth Maps
We also achieve low memory footprint for weights and activations by means of mixed precision quantization-at-training techniques.
SELMA: SEmantic Large-scale Multimodal Acquisitions in Variable Weather, Daytime and Viewpoints
Accurate scene understanding from multiple sensors mounted on cars is a key requirement for autonomous driving systems.
End-to-end Learning for Joint Depth and Image Reconstruction from Diffracted Rotation
Monocular depth estimation is still an open challenge due to the ill-posed nature of the problem at hand.
Ranked #1 on
Monocular Depth Estimation
on SUN-RGBD
Continual Coarse-to-Fine Domain Adaptation in Semantic Segmentation
In this paper we introduce the novel task of coarse-to-fine learning of semantic segmentation architectures in presence of domain shift.
Lightweight Deep Learning Architecture for MPI Correction and Transient Reconstruction
Indirect Time-of-Flight cameras (iToF) are low-cost devices that provide depth images at an interactive frame rate.
RECALL: Replay-based Continual Learning in Semantic Segmentation
Replay data are then blended with new samples during the incremental steps.
Road Scenes Segmentation Across Different Domains by Disentangling Latent Representations
Deep learning models obtain impressive accuracy in road scenes understanding, however they need a large quantity of labeled samples for their training.
Latent Space Regularization for Unsupervised Domain Adaptation in Semantic Segmentation
Deep convolutional neural networks for semantic segmentation achieve outstanding accuracy, however they also have a couple of major drawbacks: first, they do not generalize well to distributions slightly different from the one of the training data; second, they require a huge amount of labeled data for their optimization.
Continual Semantic Segmentation via Repulsion-Attraction of Sparse and Disentangled Latent Representations
Second, features sparsification allows to make room in the latent space to accommodate novel classes.
Ranked #3 on
Disjoint 15-5
on PASCAL VOC 2012
Unsupervised Domain Adaptation in Semantic Segmentation via Orthogonal and Clustered Embeddings
Deep learning frameworks allowed for a remarkable advancement in semantic segmentation, but the data hungry nature of convolutional networks has rapidly raised the demand for adaptation techniques able to transfer learned knowledge from label-abundant domains to unlabeled ones.
GMNet: Graph Matching Network for Large Scale Part Semantic Segmentation in the Wild
To tackle part-level ambiguity and localization we propose a novel adjacency graph-based module that aims at matching the relative spatial relationships between ground truth and predicted parts.
Ranked #7 on
Semantic Segmentation
on FMB Dataset
Unsupervised Domain Adaptation in Semantic Segmentation: a Review
The aim of this paper is to give an overview of the recent advancements in the Unsupervised Domain Adaptation (UDA) of deep networks for semantic segmentation.
Unsupervised Domain Adaptation with Multiple Domain Discriminators and Adaptive Self-Training
We introduce a novel UDA framework where a standard supervised loss on labeled synthetic data is supported by an adversarial module and a self-training strategy aiming at aligning the two domain distributions.
Unsupervised Domain Adaptation for Mobile Semantic Segmentation based on Cycle Consistency and Feature Alignment
The supervised training of deep networks for semantic segmentation requires a huge amount of labeled real world data.
Knowledge Distillation for Incremental Learning in Semantic Segmentation
Deep learning architectures have shown remarkable results in scene understanding problems, however they exhibit a critical drop of performances when they are required to learn incrementally new tasks without forgetting old ones.
Adversarial Learning and Self-Teaching Techniques for Domain Adaptation in Semantic Segmentation
A recently proposed workaround is to train deep networks using synthetic data, but the domain shift between real world and synthetic representations limits the performance.
Incremental Learning Techniques for Semantic Segmentation
To tackle this task we propose to distill the knowledge of the previous model to retain the information about previously learned classes, whilst updating the current model to learn the new ones.
Ranked #4 on
Domain 11-1
on Cityscapes
