Search Results for author:
Found 14 papers, 4 papers with code
Unsupervised Class Generation to Expand Semantic Segmentation Datasets
To mitigate this cost there has been a surge in the use of synthetically generated data -- usually created using simulators or videogames -- which, in combination with domain adaptation methods, can effectively learn how to segment real data.
Leveraging Contrastive Learning for Semantic Segmentation with Consistent Labels Across Varying Appearances
This paper introduces a novel synthetic dataset that captures urban scenes under a variety of weather conditions, providing pixel-perfect, ground-truth-aligned images to facilitate effective feature alignment across domains.
VLMs meet UDA: Boosting Transferability of Open Vocabulary Segmentation with Unsupervised Domain Adaptation
Segmentation models are typically constrained by the categories defined during training.
Open Vocabulary Semantic Segmentation
Open-Vocabulary Semantic Segmentation
+2
Test-Time Adaptation for Keypoint-Based Spacecraft Pose Estimation Based on Predicted-View Synthesis
Due to the difficulty of replicating the real conditions during training, supervised algorithms for spacecraft pose estimation experience a drop in performance when trained on synthetic data and applied to real operational data.
Layer-wise Model Merging for Unsupervised Domain Adaptation in Segmentation Tasks
In this paper, we leverage the abundance of freely accessible trained models to introduce a cost-free approach to model merging.
Gradient-based Class Weighting for Unsupervised Domain Adaptation in Dense Prediction Visual Tasks
In unsupervised domain adaptation (UDA), where models are trained on source data (e. g., synthetic) and adapted to target data (e. g., real-world) without target annotations, addressing the challenge of significant class imbalance remains an open issue.
Open-Vocabulary Attention Maps with Token Optimization for Semantic Segmentation in Diffusion Models
This approach limits the generation of segmentation masks derived from word tokens not contained in the text prompt.
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.
Soft labelling for semantic segmentation: Bringing coherence to label down-sampling
To that aim, we propose a novel framework for label down-sampling via soft-labeling that better conserves label information after down-sampling.
Ranked #11 on
Semantic Segmentation
on Cityscapes val
Detection-aware multi-object tracking evaluation
How would you fairly evaluate two multi-object tracking algorithms (i. e. trackers), each one employing a different object detector?
Attention-based Knowledge Distillation in Multi-attention Tasks: The Impact of a DCT-driven Loss
Feature-based Knowledge Distillation is a subfield of KD that relies on intermediate network representations, either unaltered or depth-reduced via maximum activation maps, as the source knowledge.
Graph Neural Networks for Cross-Camera Data Association
To avoid the usage of fixed distances, we leverage the connectivity of Graph Neural Networks, previously unused in this scope, using a Message Passing Network to jointly learn features and similarity.
Online Clustering-based Multi-Camera Vehicle Tracking in Scenarios with overlapping FOVs
Multi-Target Multi-Camera (MTMC) vehicle tracking is an essential task of visual traffic monitoring, one of the main research fields of Intelligent Transportation Systems.
On guiding video object segmentation
This guiding process relies on foreground masks from independent algorithms (i. e. state-of-the-art algorithms) to implement an attention mechanism that incorporates the spatial location of foreground and background to compute their separated representations.
