Resumen
During the last years, we have seen significant advances in the object detection task, mainly due to the outperforming results of convolutional neural networks. In this vein, anchor-based models have achieved the best results. However, these models require prior information about the aspect and scales of target objects, needing more hyperparameters to fit. In addition, using anchors to fit bounding boxes seems far from how our visual system does the same visual task. Instead, our visual system uses the interactions of different scene parts to semantically identify objects, called perceptual grouping. An object detection methodology closer to the natural model is anchor-free detection, where models like FCOS or Centernet have shown competitive results, but these have not yet exploited the concept of perceptual grouping. Therefore, to increase the effectiveness of anchor-free models keeping the inference time low, we propose to add non-local attention (NL modules) modules to boost the feature map of the underlying backbone. NL modules implement the perceptual grouping mechanism, allowing receptive fields to cooperate in visual representation learning. We show that non-local modules combined with an FCOS head (NL-FCOS) are practical and efficient. Thus, we establish state-of-the-art performance in clothing detection and handwritten amount recognition problems.
Idioma original | Inglés |
---|---|
Título de la publicación alojada | 2022 26th International Conference on Pattern Recognition, ICPR 2022 |
Editorial | Institute of Electrical and Electronics Engineers Inc. |
Páginas | 4651-4657 |
Número de páginas | 7 |
ISBN (versión digital) | 9781665490627 |
DOI | |
Estado | Publicada - 2022 |
Evento | 26th International Conference on Pattern Recognition, ICPR 2022 - Montreal, Canadá Duración: 21 ago. 2022 → 25 ago. 2022 |
Serie de la publicación
Nombre | Proceedings - International Conference on Pattern Recognition |
---|---|
Volumen | 2022-August |
ISSN (versión impresa) | 1051-4651 |
Conferencia
Conferencia | 26th International Conference on Pattern Recognition, ICPR 2022 |
---|---|
País/Territorio | Canadá |
Ciudad | Montreal |
Período | 21/08/22 → 25/08/22 |
Nota bibliográfica
Publisher Copyright:© 2022 IEEE.