Search Results for author:
Found 16 papers, 2 papers with code
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
Pinpoint Counterfactuals: Reducing social bias in foundation models via localized counterfactual generation
When applied to the Conceptual Captions dataset for creating gender counterfactuals, our method results in higher visual and semantic fidelity than state-of-the-art alternatives, while maintaining the performance of models trained using only real data on non-human-centric tasks.
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.
Improved transferability of self-supervised learning models through batch normalization finetuning
At a cost of extra training of only 0. 16% model parameters, in case of ResNet-50, we acquire a proxy task that (i) has a stronger correlation with end-to-end finetuned performance, (ii) improves the linear probing performance in the many- and few-shot learning regimes and (iii) in some cases, outperforms both linear probing and end-to-end finetuning, reaching the state-of-the-art performance on a pathology dataset.
Ranked #1 on
Classification
on MHIST
(using extra training data)
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.
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.
Self-Supervised Curricular Deep Learning for Chest X-Ray Image Classification
Deep learning technologies have already demonstrated a high potential to build diagnosis support systems from medical imaging data, such as Chest X-Ray images.
Graph Convolutional Network for Multi-Target Multi-Camera Vehicle Tracking
This letter focuses on the task of Multi-Target Multi-Camera vehicle tracking.
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.
A study on the distribution of social biases in self-supervised learning visual models
We show that there is a correlation between the type of the SSL model and the number of biases that it incorporates.
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.
A Prospective Study on Sequence-Driven Temporal Sampling and Ego-Motion Compensation for Action Recognition in the EPIC-Kitchens Dataset
Action recognition is currently one of the top-challenging research fields in computer vision.
Egocentric Human Segmentation for Mixed Reality
The objective of this work is to segment human body parts from egocentric video using semantic segmentation networks.
Semantic-Aware Scene Recognition
Scene recognition is currently one of the top-challenging research fields in computer vision.
Ranked #1 on
Scene Recognition
on ADE20K
Semantic Driven Multi-Camera Pedestrian Detection
Contrarily to the majority of the methods of the state-of-the-art, the proposed approach is scene-agnostic, not requiring a tailored adaptation to the target scenario\textemdash e. g., via fine-tunning.
