LAMP

Category: Publications

  • Metric Learning for Novelty and Anomaly Detection

    Marc Masana, Idoia Ruiz, Joan Serrat, Joost van de Weijer, Antonio M. Lopez Read Full Paper → When neural networks process images which do not resemble the distribution seen during training, so called out-of-distribution images, they often make wrong predictions, and do so too confidently. The capability to detect out-of-distribution images is therefore crucial for many real-world applications. We […]

  • Transferring GANs: generating images from limited data

    Yaxing Wang, Chenshen Wu, Luis Herranz, Joost van de Weijer, Abel Gonzalez-Garcia, Bogdan Raducanu Read Full Paper → Transferring the knowledge of pretrained networks to new domains by means of finetuning is a widely used practice for applications based on discriminative models. To the best of our knowledge this practice has not been studied within the context of generative deep […]

  • Context Proposals for Saliency Detection

    Aymen Azaza, Joost van de Weijer, Ali Douik, Marc Masana Read Full Paper → One of the fundamental properties of a salient object region is its contrast with the immediate context. The problem is that numerous object regions exist which potentially can all be salient. One way to prevent an exhaustive search over all object regions is by […]

  • Weakly Supervised Domain-Specific Color Naming Based on Attention

    Lu Yu, Yongmei Cheng, Joost van de Weijer Read Full Paper → The majority of existing color naming methods focuses on the eleven basic color terms of the English language. However, in many applications, different sets of color names are used for the accurate description of objects. Labeling data to learn these domain-specific color names is an […]

  • Learning Illuminant Estimation from Object Recognition

    Marco Buzzelli, Joost van de Weijer, Raimondo Schettini Read Full Paper → In this paper we present a deep learning method to estimate the illuminant of an image. Our model is not trained with illuminant annotations, but with the objective of improving performance on an auxiliary task such as object recognition. To the best of our knowledge, […]

  • Binary Patterns Encoded Convolutional Neural Networks for Texture Recognition and Remote Sensing Scene Classification

    Rao Muhammad Anwer, Fahad Shahbaz Khan, Joost van de Weijer, Matthieu Molinier, Jorma Laaksonen Read Full Paper → Designing discriminative powerful texture features robust to realistic imaging conditions is a challenging computer vision problem with many applications, including material recognition and analysis of satellite or aerial imagery. In the past, most texture description approaches were based on dense orderless […]

  • Leveraging Unlabeled Data for Crowd Counting by Learning to Rank

    Xialei Liu, Joost van de Weijer, Andrew D. Bagdanov Read Full Paper → We propose a novel crowd counting approach that leverages abundantly available unlabeled crowd imagery in a learning-to-rank framework. To induce a ranking of cropped images , we use the observation that any sub-image of a crowded scene image is guaranteed to contain the same […]

  • On the Duality Between Retinex and Image Dehazing

    Adrian Galdran, Aitor Alvarez-Gila, Alessandro Bria, Javier Vazquez-Corral, Marcelo Bertalmio Read Full Paper → Image dehazing deals with the removal of undesired loss of visibility in outdoor images due to the presence of fog. Retinex is a color vision model mimicking the ability of the Human Visual System to robustly discount varying illuminations when observing a scene under different […]

  • Objects as context for detecting their semantic parts

    Abel Gonzalez-Garcia, Davide Modolo, Vittorio Ferrari Read Full Paper → We present a semantic part detection approach that effectively leverages object information.We use the object appearance and its class as indicators of what parts to expect. We also model the expected relative location of parts inside the objects based on their appearance. We achieve this with a […]

  • Beyond Eleven Color Names for Image Understanding

    Lu Yu, Lichao Zhang, Joost van de Weijer, Fahad Shahbaz Khan, Yongmei Cheng & C. Alejandro Parraga Read Full Paper → Color description is one of the fundamental problems of image understanding. One of the popular ways to represent colors is by means of color names. Most existing work on color names focuses on only the eleven basic color terms of […]