• Generative Multi-Label Zero-Shot Learning

    Akshita Gupta, Sanath Narayan, Salman Khan, Fahad Shahbaz Khan, Ling Shao, Joost van de Weijer Read Full Paper → Multi-label zero-shot learning strives to classify images into multiple unseen categories for which no data is available during training. The test samples can additionally contain seen categories in the generalized variant. Existing approaches rely on learning either shared or label-specific attention […]

  • Class-incremental learning: survey and performance evaluation on image classification

    Marc Masana, Xialei Liu, Bartlomiej Twardowski, Mikel Menta, Andrew D. Bagdanov, Joost van de Weijer Read Full Paper → For future learning systems, incremental learning is desirable because it allows for: efficient resource usage by eliminating the need to retrain from scratch at the arrival of new data; reduced memory usage by preventing or limiting the amount of data required […]

  • Code framework for Class-Incremental Learning

    Check out our new framework for analysis of class-incremental learning (FACIL), which contains implementations of fourteen class-incremental algorithms and several baselines. It allows you to reproduce our results on CIFAR 100 presented in our survey paper.

  • Exploiting Unlabeled Data in CNNs by Self-supervised Learning to Rank

    Xialei Liu, Joost van de Weijer, Andrew D. Bagdanov Read Full Paper → For many applications the collection of labeled data is expensive laborious. Exploitation of unlabeled data during training is thus a long pursued objective of machine learning. Self-supervised learning addresses this by positing an auxiliary task (different, but related to the supervised task) for which […]

  • Stacked Sequential Scale-SpaceTaylor Context

    Carlo Gatta; Francesco Ciompi Read Full Paper → We analyze sequential image labeling methods that sample the posterior label field in order to gather contextual information. We propose an effective method that extracts local Taylor coefficients from the posterior at different scales. Results show that our proposal outperforms state-of-the-art methods on MSRC-21, CAMVID, eTRIMS8 and KAIST2 […]

  • Local Pyramidal Descriptors for Image Recognition

    Lorenzo Seidenari; Giuseppe Serra; Andrew D. Bagdanov; Alberto Del Bimbo Read Full Paper → In this paper, we present a novel method to improve the flexibility of descriptor matching for image recognition by using local multiresolution pyramids in feature space. We propose that image patches be represented at multiple levels of descriptor detail and that these levels be […]