Search Results for author:
Found 63 papers, 41 papers with code
DitHub: A Modular Framework for Incremental Open-Vocabulary Object Detection
Open-Vocabulary object detectors can recognize a wide range of categories using simple textual prompts.
Is Multiple Object Tracking a Matter of Specialization?
End-to-end transformer-based trackers have achieved remarkable performance on most human-related datasets.
Closed-form merging of parameter-efficient modules for Federated Continual Learning
Model merging has emerged as a crucial technique in Deep Learning, enabling the integration of multiple models into a unified system while preserving performance and scalability.
May the Forgetting Be with You: Alternate Replay for Learning with Noisy Labels
Forgetting presents a significant challenge during incremental training, making it particularly demanding for contemporary AI systems to assimilate new knowledge in streaming data environments.
CLIP with Generative Latent Replay: a Strong Baseline for Incremental Learning
With the emergence of Transformers and Vision-Language Models (VLMs) such as CLIP, fine-tuning large pre-trained models has recently become a prevalent strategy in Continual Learning.
An Attention-based Representation Distillation Baseline for Multi-Label Continual Learning
It relies on a knowledge transfer technique that seeks to align the representations of the student network -- which trains continuously and is subject to forgetting -- with the teacher ones, which is pretrained and kept frozen.
Mask and Compress: Efficient Skeleton-based Action Recognition in Continual Learning
The use of skeletal data allows deep learning models to perform action recognition efficiently and effectively.
Federated Class-Incremental Learning with Hierarchical Generative Prototypes
Federated Learning (FL) aims at unburdening the training of deep models by distributing computation across multiple devices (clients) while safeguarding data privacy.
Trajectory Forecasting through Low-Rank Adaptation of Discrete Latent Codes
Trajectory forecasting is crucial for video surveillance analytics, as it enables the anticipation of future movements for a set of agents, e. g. basketball players engaged in intricate interactions with long-term intentions.
A Second-Order Perspective on Model Compositionality and Incremental Learning
The fine-tuning of deep pre-trained models has revealed compositional properties, with multiple specialized modules that can be arbitrarily composed into a single, multi-task model.
Selective Attention-based Modulation for Continual Learning
We present SAM, a biologically-plausible selective attention-driven modulation approach to enhance classification models in a continual learning setting.
Semantic Residual Prompts for Continual Learning
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).
Self-Labeling the Job Shop Scheduling Problem
Inspired by semi- and self-supervised learning, we show that generative models can be trained by sampling multiple solutions and using the best one according to the problem objective as a pseudo-label.
DistFormer: Enhancing Local and Global Features for Monocular Per-Object Distance Estimation
Existing approaches rely on two scales: local information (i. e., the bounding box proportions) or global information, which encodes the semantics of the scene as well as the spatial relations with neighboring objects.
TrackFlow: Multi-Object Tracking with Normalizing Flows
The field of multi-object tracking has recently seen a renewed interest in the good old schema of tracking-by-detection, as its simplicity and strong priors spare it from the complex design and painful babysitting of tracking-by-attention approaches.
On the Effectiveness of Equivariant Regularization for Robust Online Continual Learning
Humans can learn incrementally, whereas neural networks forget previously acquired information catastrophically.
Neuro-Symbolic Continual Learning: Knowledge, Reasoning Shortcuts and Concept Rehearsal
We introduce Neuro-Symbolic Continual Learning, where a model has to solve a sequence of neuro-symbolic tasks, that is, it has to map sub-symbolic inputs to high-level concepts and compute predictions by reasoning consistently with prior knowledge.
Input Perturbation Reduces Exposure Bias in Diffusion Models
Denoising Diffusion Probabilistic Models have shown an impressive generation quality, although their long sampling chain leads to high computational costs.
Ranked #1 on
Image Generation
on FFHQ 128 x 128
Latent Spectral Regularization for Continual Learning
While biological intelligence grows organically as new knowledge is gathered throughout life, Artificial Neural Networks forget catastrophically whenever they face a changing training data distribution.
On the Effectiveness of Lipschitz-Driven Rehearsal in Continual Learning
By means of extensive experiments, we show that applying LiDER delivers a stable performance gain to several state-of-the-art rehearsal CL methods across multiple datasets, both in the presence and absence of pre-training.
Spotting Virus from Satellites: Modeling the Circulation of West Nile Virus Through Graph Neural Networks
In this paper, we seek to predict WNV circulation by feeding Deep Neural Networks (DNNs) with satellite images, which have been extensively shown to hold environmental and climatic features.
Consistency-based Self-supervised Learning for Temporal Anomaly Localization
This work tackles Weakly Supervised Anomaly detection, in which a predictor is allowed to learn not only from normal examples but also from a few labeled anomalies made available during training.
Ranked #14 on
Anomaly Detection In Surveillance Videos
on XD-Violence
Anomaly Detection In Surveillance Videos
Anomaly Localization
+4
Learning the Quality of Machine Permutations in Job Shop Scheduling
Finally, we empirically demonstrate the value of predicting the quality of machine permutations by enhancing the performance of a simple Tabu Search algorithm inspired by the works in the literature.
Effects of Auxiliary Knowledge on Continual Learning
In this paper we propose a new, simple, CL algorithm that focuses on solving the current task in a way that might facilitate the learning of the next ones.
Transfer without Forgetting
This work investigates the entanglement between Continual Learning (CL) and Transfer Learning (TL).
SeeFar: Vehicle Speed Estimation and Flow Analysis from a Moving UAV
In this paper, we introduce SeeFar to achieve vehicle speed estimation and traffic flow analysis based on YOLOv5 and DeepSORT from a moving drone.
Goal-driven Self-Attentive Recurrent Networks for Trajectory Prediction
Human trajectory forecasting is a key component of autonomous vehicles, social-aware robots and advanced video-surveillance applications.
How many Observations are Enough? Knowledge Distillation for Trajectory Forecasting
To this end, we conceive a novel distillation strategy that allows a knowledge transfer from a teacher network to a student one, the latter fed with fewer observations (just two ones).
Class-Incremental Continual Learning into the eXtended DER-verse
The staple of human intelligence is the capability of acquiring knowledge in a continuous fashion.
MOTSynth: How Can Synthetic Data Help Pedestrian Detection and Tracking?
Deep learning-based methods for video pedestrian detection and tracking require large volumes of training data to achieve good performance.
Continual Semi-Supervised Learning through Contrastive Interpolation Consistency
This work explores Continual Semi-Supervised Learning (CSSL): here, only a small fraction of labeled input examples are shown to the learner.
Avalanche: an End-to-End Library for Continual Learning
Learning continually from non-stationary data streams is a long-standing goal and a challenging problem in machine learning.
RMS-Net: Regression and Masking for Soccer Event Spotting
The recently proposed action spotting task consists in finding the exact timestamp in which an event occurs.
Ranked #1 on
Action Spotting
on SoccerNet
Generalising via Meta-Examples for Continual Learning in the Wild
Future deep learning systems call for techniques that can deal with the evolving nature of temporal data and scarcity of annotations when new problems occur.
Rethinking Experience Replay: a Bag of Tricks for Continual Learning
In Continual Learning, a Neural Network is trained on a stream of data whose distribution shifts over time.
Few-Shot Unsupervised Continual Learning through Meta-Examples
In real-world applications, data do not reflect the ones commonly used for neural networks training, since they are usually few, unlabeled and can be available as a stream.
Inter-Homines: Distance-Based Risk Estimation for Human Safety
In this document, we report our proposal for modeling the risk of possible contagiousity in a given area monitored by RGB cameras where people freely move and interact.
Robust Re-Identification by Multiple Views Knowledge Distillation
To achieve robustness in Re-Identification, standard methods leverage tracking information in a Video-To-Video fashion.
Ranked #2 on
Vehicle Re-Identification
on VeRi
Future Urban Scenes Generation Through Vehicles Synthesis
In this work we propose a deep learning pipeline to predict the visual future appearance of an urban scene.
The color out of space: learning self-supervised representations for Earth Observation imagery
We conduct experiments on land cover classification (BigEarthNet) and West Nile Virus detection, showing that colorization is a solid pretext task for training a feature extractor.
DAG-Net: Double Attentive Graph Neural Network for Trajectory Forecasting
Understanding human motion behaviour is a critical task for several possible applications like self-driving cars or social robots, and in general for all those settings where an autonomous agent has to navigate inside a human-centric environment.
Ranked #1 on
Trajectory Prediction
on STATS SportVu NBA [ATK]
AC-VRNN: Attentive Conditional-VRNN for Multi-Future Trajectory Prediction
Anticipating human motion in crowded scenarios is essential for developing intelligent transportation systems, social-aware robots and advanced video surveillance applications.
Dark Experience for General Continual Learning: a Strong, Simple Baseline
Continual Learning has inspired a plethora of approaches and evaluation settings; however, the majority of them overlooks the properties of a practical scenario, where the data stream cannot be shaped as a sequence of tasks and offline training is not viable.
Ranked #12 on
Continual Learning
on ASC (19 tasks)
Compressed Volumetric Heatmaps for Multi-Person 3D Pose Estimation
At the core of the proposed method lies our Volumetric Heatmap Autoencoder, a fully-convolutional network tasked with the compression of ground-truth heatmaps into a dense intermediate representation.
Ranked #6 on
3D Human Pose Estimation
on Panoptic
(using extra training data)
Conditional Channel Gated Networks for Task-Aware Continual Learning
Therefore, we additionally introduce a task classifier that predicts the task label of each example, to deal with settings in which a task oracle is not available.
Ranked #3 on
Continual Learning
on ImageNet-50 (5 tasks)
Video action detection by learning graph-based spatio-temporal interactions
Action Detection is a complex task that aims to detect and classify human actions in video clips.
Spotting insects from satellites: modeling the presence of Culicoides imicola through Deep CNNs
Nowadays, Vector-Borne Diseases (VBDs) raise a severe threat for public health, accounting for a considerable amount of human illnesses.
Warp and Learn: Novel Views Generation for Vehicles and Other Objects
An Image Completion Network (ICN) is then trained to generate a realistic image starting from this geometric guidance.
A Deep Learning based approach to VM behavior identification in cloud systems
The experiments compare our proposal with state-of-the-art solutions available in literature, demonstrating that our proposal achieve better performance.
Classifying Signals on Irregular Domains via Convolutional Cluster Pooling
We present a novel and hierarchical approach for supervised classification of signals spanning over a fixed graph, reflecting shared properties of the dataset.
Multi-views Embedding for Cattle Re-identification
People re-identification task has seen enormous improvements in the latest years, mainly due to the development of better image features extraction from deep Convolutional Neural Networks (CNN) and the availability of large datasets.
Can Adversarial Networks Hallucinate Occluded People With a Plausible Aspect?
When you see a person in a crowd, occluded by other persons, you miss visual information that can be used to recognize, re-identify or simply classify him or her.
Domain Translation with Conditional GANs: from Depth to RGB Face-to-Face
Can faces acquired by low-cost depth sensors be useful to catch some characteristic details of the face?
Latent Space Autoregression for Novelty Detection
Novelty detection is commonly referred to as the discrimination of observations that do not conform to a learned model of regularity.
Learning to Detect and Track Visible and Occluded Body Joints in a Virtual World
Multi-People Tracking in an open-world setting requires a special effort in precise detection.
Face-from-Depth for Head Pose Estimation on Depth Images
Therefore, we propose a complete framework for the estimation of the head and shoulder pose based on depth images only.
Generative Adversarial Models for People Attribute Recognition in Surveillance
In this paper we propose a deep architecture for detecting people attributes (e. g. gender, race, clothing ...) in surveillance contexts.
Learning to Map Vehicles into Bird's Eye View
Awareness of the road scene is an essential component for both autonomous vehicles and Advances Driver Assistance Systems and is gaining importance both for the academia and car companies.
TransFlow: Unsupervised Motion Flow by Joint Geometric and Pixel-level Estimation
We address unsupervised optical flow estimation for ego-centric motion.
Predicting the Driver's Focus of Attention: the DR(eye)VE Project
In this work we aim to predict the driver's focus of attention.
Learning Where to Attend Like a Human Driver
Despite the advent of autonomous cars, it's likely - at least in the near future - that human attention will still maintain a central role as a guarantee in terms of legal responsibility during the driving task.
Learning to Divide and Conquer for Online Multi-Target Tracking
Online Multiple Target Tracking (MTT) is often addressed within the tracking-by-detection paradigm.
Socially Constrained Structural Learning for Groups Detection in Crowd
Modern crowd theories agree that collective behavior is the result of the underlying interactions among small groups of individuals.
