TY  - CONF
AU  - Javier Rodenas
AU  - Bhalaji Nagarajan
AU  - Marc Bolaños
AU  - Petia Radeva
A2  - MADiMa
PY  - 2022//
TI  - Learning Multi-Subset of Classes for Fine-Grained Food Recognition
BT  - 7th International Workshop on Multimedia Assisted Dietary Management
SP  - 17–26
N2  - Food image recognition is a complex computer vision task, because of the large number of fine-grained food classes. Fine-grained recognition tasks focus on learning subtle discriminative details to distinguish similar classes. In this paper, we introduce a new method to improve the classification of classes that are more difficult to discriminate based on Multi-Subsets learning. Using a pre-trained network, we organize classes in multiple subsets using a clustering technique. Later, we embed these subsets in a multi-head model structure. This structure has three distinguishable parts. First, we use several shared blocks to learn the generalized representation of the data. Second, we use multiple specialized blocks focusing on specific subsets that are difficult to distinguish. Lastly, we use a fully connected layer to weight the different subsets in an end-to-end manner by combining the neuron outputs. We validated our proposed method using two recent state-of-the-art vision transformers on three public food recognition datasets. Our method was successful in learning the confused classes better and we outperformed the state-of-the-art on the three datasets.
UR  - https://dl.acm.org/doi/abs/10.1145/3552484.3555754
N1  - MILAB
ID  - Javier Rodenas2022
ER  -