Search Results for author:
Found 23 papers, 16 papers with code
The Unreasonable Effectiveness of Pre-Trained Features for Camera Pose Refinement
This involves training an implicit scene representation or learning features while optimizing a camera pose-based loss.
JIST: Joint Image and Sequence Training for Sequential Visual Place Recognition
As a mitigation to this problem, we propose a novel Joint Image and Sequence Training protocol (JIST) that leverages large uncurated sets of images through a multi-task learning framework.
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.
EarthLoc: Astronaut Photography Localization by Indexing Earth from Space
Astronaut photography, spanning six decades of human spaceflight, presents a unique Earth observations dataset with immense value for both scientific research and disaster response.
Communication-Efficient Heterogeneous Federated Learning with Generalized Heavy-Ball Momentum
Federated Learning (FL) is the state-of-the-art approach for learning from decentralized data in privacy-constrained scenarios.
The Robust Semantic Segmentation UNCV2023 Challenge Results
This paper outlines the winning solutions employed in addressing the MUAD uncertainty quantification challenge held at ICCV 2023.
Mask2Anomaly: Mask Transformer for Universal Open-set Segmentation
Segmenting unknown or anomalous object instances is a critical task in autonomous driving applications, and it is approached traditionally as a per-pixel classification problem.
EigenPlaces: Training Viewpoint Robust Models for Visual Place Recognition
Visual Place Recognition is a task that aims to predict the place of an image (called query) based solely on its visual features.
Ranked #1 on
Visual Place Recognition
on SF-XL test v1
Unmasking Anomalies in Road-Scene Segmentation
We propose a paradigm change by shifting from a per-pixel classification to a mask classification.
Ranked #1 on
Scene Segmentation
on StreetHazards
(using extra training data)
Divide&Classify: Fine-Grained Classification for City-Wide Visual Place Recognition
Our method, Divide&Classify (D&C), enjoys the fast inference of classification solutions and an accuracy competitive with retrieval methods on the fine-grained, city-wide setting.
Are Local Features All You Need for Cross-Domain Visual Place Recognition?
Despite recent advances, recognizing the same place when the query comes from a significantly different distribution is still a major hurdle for state of the art retrieval methods.
Divide&Classify: Fine-Grained Classification for City-Wide Visual Geo-Localization
In this paper we investigate whether we can effectively approach this task as a classification problem, thus bypassing the need for a similarity search.
Hierarchical Instance Mixing across Domains in Aerial Segmentation
We investigate the task of unsupervised domain adaptation in aerial semantic segmentation and discover that the current state-of-the-art algorithms designed for autonomous driving based on domain mixing do not translate well to the aerial setting.
Learning Sequential Descriptors for Sequence-based Visual Place Recognition
In robotics, Visual Place Recognition is a continuous process that receives as input a video stream to produce a hypothesis of the robot's current position within a map of known places.
Augmentation Invariance and Adaptive Sampling in Semantic Segmentation of Agricultural Aerial Images
We observe that the existing methods used for this task are designed without considering two characteristics of the aerial data: (i) the top-down perspective implies that the model cannot rely on a fixed semantic structure of the scene, because the same scene may be experienced with different rotations of the sensor; (ii) there can be a strong imbalance in the distribution of semantic classes because the relevant objects of the scene may appear at extremely different scales (e. g., a field of crops and a small vehicle).
Deep Visual Geo-localization Benchmark
In this paper, we propose a new open-source benchmarking framework for Visual Geo-localization (VG) that allows to build, train, and test a wide range of commonly used architectures, with the flexibility to change individual components of a geo-localization pipeline.
Rethinking Visual Geo-localization for Large-Scale Applications
Visual Geo-localization (VG) is the task of estimating the position where a given photo was taken by comparing it with a large database of images of known locations.
Ranked #1 on
Visual Place Recognition
on SF-XL test v2
Learning Semantics for Visual Place Recognition through Multi-Scale Attention
In this paper we address the task of visual place recognition (VPR), where the goal is to retrieve the correct GPS coordinates of a given query image against a huge geotagged gallery.
Pixel-by-Pixel Cross-Domain Alignment for Few-Shot Semantic Segmentation
The pixel-wise adversarial training is assisted by a novel sample selection procedure, that handles the imbalance between source and target data, and a knowledge distillation strategy, that avoids overfitting towards the few target images.
Reimagine BiSeNet for Real-Time Domain Adaptation in Semantic Segmentation
To the best of our knowledge, we are the first to present a real-time adversarial approach for assessing the domain adaption problem in semantic segmentation.
Viewpoint Invariant Dense Matching for Visual Geolocalization
Dense local features matching is robust against changes in illumination and occlusions, but not against viewpoint shifts which are a fundamental aspect of geolocalization.
Adaptive-Attentive Geolocalization from few queries: a hybrid approach
We address the task of cross-domain visual place recognition, where the goal is to geolocalize a given query image against a labeled gallery, in the case where the query and the gallery belong to different visual domains.
IDDA: a large-scale multi-domain dataset for autonomous driving
To support work in this direction, this paper contributes a new large scale, synthetic dataset for semantic segmentation with more than 100 different source visual domains.
