1

[ BMVC 2023 ] We present a novel superpixel-based positional encoding technique that combines Vision Transformer (ViT) features with superpixels priors to improve the performance of semantic segmentation architectures.

[ ICIAP 2023 ] We propose a novel open-vocabulary semantic segmentation paradigm based on weakly supervised visual prototypes extracted from image-caption pairs and adopt a retrieval-based approach to combine visual and textual features to enhance segmentation performance.

We propose a novel self-supervised pre-training technique for Vision Transformer called MaPeT and a novel image tokenizer called k-CLIP which directly employs discretized CLIP features.

[ IEEE CCNC 2023 ] In this work, we propose a super-resolution technique for traffic matrix estimation. We also expand our design by employing a federated learning model to address scalability and improve performance.

[ ICIAP 2021 | Best Paper Award sponsored by NVIDIA ] We explore the application of a 2D max-pooling operator to improve the efficiency of Transformer-based architecture for classification.

[ CAIP 2021 | Oral ] We test and devise variants of both the Boundary and Active Boundary losses, two recent proposals which deal with the prediction of semantic boundaries.

[ IWANN 2021 | Oral ] We propose two loss functions that improve the semantic segmentation accuracy at the boundary level.

[ CoNEXT 2020 | Best Poster Award ] Inspired by the field of image processing, we propose a super-resolution technique for Internet traffic matrix inference.