This paper introduces Transferable-guided Attention (TransferAttn) model, a novel ViT for unsupervised domain adaptation (UDA). To improve the transferability of ViT, we propose Domain Transferable-guided Attention Block (DTAB), a new attention mechanism that improves adaptation and domain transferability.

In this work, we leverage the use of an embedded device (Raspberry Pi 4B) and perform aggressive model compression by means of pruning-quantization aware training (PQAT) in addition of hardware acceleration devices to perform real-time image classification of leaf diseases using thermal camera.

In this work, we introduce a new dataset of productive fields based on agriculture machine’s operation combined with Sentinel-2 images collected over a period of time, enabling to training highly accurate prediction models that automatically detect productive crop fields.

In this work, we propose a weakly supervised approach for classification scenarios where only small labeled sets are available. It exploits hypergraph structures based on ranking information to identify and select reliable similarity relations between pairs of labeled-unlabeled data.

In this work, we propose the new problem of low-budget label query, which aims at maximizing the classification performance by selecting a convenient and small set of samples (i.e., low budget) to be manually labeled from an arbitrary big set of unlabeled data.