Search Results - "Spadaro, Gabriele"

  • Showing 1 - 5 results of 5
Refine Results
  1. 1

    Domain Adaptation for Learned Image Compression with Supervised Adapters by Presta, Alberto, Spadaro, Gabriele, Tartaglione, Enzo, Fiandrotti, Attilio, Grangetto, Marco

    Published 23-04-2024
    “…In Learned Image Compression (LIC), a model is trained at encoding and decoding images sampled from a source domain, often outperforming traditional codecs on…”
    Get full text
    Journal Article
  2. 2

    Domain Adaptation for Learned Image Compression with Supervised Adapters by Presta, Alberto, Spadaro, Gabriele, Tartaglione, Enzo, Fiandrotti, Attilio, Grangetto, Marco

    Published in 2024 Data Compression Conference (DCC) (19-03-2024)
    “…In Learned Image Compression (LIC), a model is trained at encoding and decoding images sampled from a source domain, often outperforming traditional codecs on…”
    Get full text
    Conference Proceeding
  3. 3

    GABIC: Graph-based Attention Block for Image Compression by Spadaro, Gabriele, Presta, Alberto, Tartaglione, Enzo, Giraldo, Jhony H, Grangetto, Marco, Fiandrotti, Attilio

    Published 03-10-2024
    “…While standardized codecs like JPEG and HEVC-intra represent the industry standard in image compression, neural Learned Image Compression (LIC) codecs…”
    Get full text
    Journal Article
  4. 4

    WiGNet: Windowed Vision Graph Neural Network by Spadaro, Gabriele, Grangetto, Marco, Fiandrotti, Attilio, Tartaglione, Enzo, Giraldo, Jhony H

    Published 01-10-2024
    “…In recent years, Graph Neural Networks (GNNs) have demonstrated strong adaptability to various real-world challenges, with architectures such as Vision GNN…”
    Get full text
    Journal Article
  5. 5

    Shannon Strikes Again! Entropy-based Pruning in Deep Neural Networks for Transfer Learning under Extreme Memory and Computation Budgets by Spadaro, Gabriele, Renzulli, Riccardo, Bragagnolo, Andrea, Giraldo, Jhony H., Fiandrotti, Attilio, Grangetto, Marco, Tartaglione, Enzo

    “…Deep neural networks have become the de-facto standard across various computer science domains. Nonetheless, effectively training these deep networks remains…”
    Get full text
    Conference Proceeding