Zobrazeno 1 - 10
of 70
pro vyhledávání: '"Pernici, Federico"'
Visual retrieval systems face significant challenges when updating models with improved representations due to misalignment between the old and new representations. The costly and resource-intensive backfilling process involves recalculating feature
Externí odkaz:
http://arxiv.org/abs/2408.08793
Learning compatible representations enables the interchangeable use of semantic features as models are updated over time. This is particularly relevant in search and retrieval systems where it is crucial to avoid reprocessing of the gallery images wi
Externí odkaz:
http://arxiv.org/abs/2405.02581
Convolutional Neural Networks (CNNs) trained with the Softmax loss are widely used classification models for several vision tasks. Typically, a learnable transformation (i.e. the classifier) is placed at the end of such models returning class scores
Externí odkaz:
http://arxiv.org/abs/2301.06116
In this paper, we propose a method to partially mimic natural intelligence for the problem of lifelong learning representations that are compatible. We take the perspective of a learning agent that is interested in recognizing object instances in an
Externí odkaz:
http://arxiv.org/abs/2211.09032
Publikováno v:
ICIAP 2021
In this paper, we propose a novel training procedure for the continual representation learning problem in which a neural network model is sequentially learned to alleviate catastrophic forgetting in visual search tasks. Our method, called Contrastive
Externí odkaz:
http://arxiv.org/abs/2205.05476
Compatible features enable the direct comparison of old and new learned features allowing to use them interchangeably over time. In visual search systems, this eliminates the need to extract new features from the gallery-set when the representation m
Externí odkaz:
http://arxiv.org/abs/2111.07632
Publikováno v:
ACM Transactions on Multimedia Computing, Communications, and Applications 2021
In this paper we exploit Semi-Supervised Learning (SSL) to increase the amount of training data to improve the performance of Fine-Grained Visual Categorization (FGVC). This problem has not been investigated in the past in spite of prohibitive annota
Externí odkaz:
http://arxiv.org/abs/2110.05848
Publikováno v:
IEEE Transactions on Neural Networks and Learning Systems, 2021
Neural networks are widely used as a model for classification in a large variety of tasks. Typically, a learnable transformation (i.e. the classifier) is placed at the end of such models returning a value for each class used for classification. This
Externí odkaz:
http://arxiv.org/abs/2103.15632
In this paper we present an event aggregation strategy to convert the output of an event camera into frames processable by traditional Computer Vision algorithms. The proposed method first generates sequences of intermediate binary representations, w
Externí odkaz:
http://arxiv.org/abs/2010.08946
In class-incremental learning, a learning agent faces a stream of data with the goal of learning new classes while not forgetting previous ones. Neural networks are known to suffer under this setting, as they forget previously acquired knowledge. To
Externí odkaz:
http://arxiv.org/abs/2010.08657