6 papers
Test-Time Adaptation via Dual Distillation for Videos Under Severe Distribution Shifts
André Sacilotti, Samuel Felipe dos Santos, Jurandy Almeida
Deep learning models have achieved state-of-the-art performance in several computer vision tasks. However, they experience severe performance degradation when applied to real-world…
Efficient Spatio-Temporal Vegetation Pixel Classification with Vision Transformers
Alan Gomes, Anderson Gonçalves, Samuel Felipe dos Santos +6
Plant phenology-the study of recurrent life cycle events-is essential for understanding ecosystem dynamics and their responses to climate change impacts. While Unmanned Aerial Vehi…
E-MLNet: Enhanced Mutual Learning for Universal Domain Adaptation with Sample-Specific Weighting
Samuel Felipe dos Santos, Tiago Agostinho de Almeida, Jurandy Almeida
Universal Domain Adaptation (UniDA) seeks to transfer knowledge from a labeled source to an unlabeled target domain without assuming any relationship between their label sets, requ…
Beyond the Known: Enhancing Open Set Domain Adaptation with Unknown Exploration
Lucas Fernando Alvarenga e Silva, Samuel Felipe dos Santos, Nicu Sebe +1
Convolutional neural networks (CNNs) can learn directly from raw data, resulting in exceptional performance across various research areas. However, factors present in non-controlla…
Transferable-guided Attention Is All You Need for Video Domain Adaptation
André Sacilotti, Samuel Felipe dos Santos, Nicu Sebe +1
Unsupervised domain adaptation (UDA) in videos is a challenging task that remains not well explored compared to image-based UDA techniques. Although vision transformers (ViT) achie…
Budget-Aware Pruning: Handling Multiple Domains with Less Parameters
Samuel Felipe dos Santos, Rodrigo Berriel, Thiago Oliveira-Santos +2
Deep learning has achieved state-of-the-art performance on several computer vision tasks and domains. Nevertheless, it still has a high computational cost and demands a significant…