Picture for Juan C. SanMiguel

Juan C. SanMiguel

VLMs meet UDA: Boosting Transferability of Open Vocabulary Segmentation with Unsupervised Domain Adaptation

Add code
Dec 12, 2024
Viaarxiv icon

Test-Time Adaptation for Keypoint-Based Spacecraft Pose Estimation Based on Predicted-View Synthesis

Add code
Oct 05, 2024
Viaarxiv icon

Layer-wise Model Merging for Unsupervised Domain Adaptation in Segmentation Tasks

Add code
Sep 24, 2024
Viaarxiv icon

Gradient-based Class Weighting for Unsupervised Domain Adaptation in Dense Prediction Visual Tasks

Add code
Jul 01, 2024
Viaarxiv icon

Open-Vocabulary Attention Maps with Token Optimization for Semantic Segmentation in Diffusion Models

Add code
Mar 21, 2024
Viaarxiv icon

The Robust Semantic Segmentation UNCV2023 Challenge Results

Add code
Sep 27, 2023
Viaarxiv icon

Soft labelling for semantic segmentation: Bringing coherence to label down-sampling

Add code
Mar 08, 2023
Viaarxiv icon

Detection-aware multi-object tracking evaluation

Add code
Dec 16, 2022
Viaarxiv icon

Impact of a DCT-driven Loss in Attention-based Knowledge-Distillation for Scene Recognition

Add code
May 04, 2022
Figure 1 for Impact of a DCT-driven Loss in Attention-based Knowledge-Distillation for Scene Recognition
Figure 2 for Impact of a DCT-driven Loss in Attention-based Knowledge-Distillation for Scene Recognition
Figure 3 for Impact of a DCT-driven Loss in Attention-based Knowledge-Distillation for Scene Recognition
Figure 4 for Impact of a DCT-driven Loss in Attention-based Knowledge-Distillation for Scene Recognition
Viaarxiv icon

Graph Neural Networks for Cross-Camera Data Association

Add code
Jan 17, 2022
Figure 1 for Graph Neural Networks for Cross-Camera Data Association
Figure 2 for Graph Neural Networks for Cross-Camera Data Association
Figure 3 for Graph Neural Networks for Cross-Camera Data Association
Figure 4 for Graph Neural Networks for Cross-Camera Data Association
Viaarxiv icon