Training deep networks from zero to hero: avoiding pitfalls and going beyond (2021)
- Authors:
- USP affiliated authors: PONTI, MOACIR ANTONELLI - ICMC ; SANTOS, FERNANDO PEREIRA DOS - ICMC ; RIBEIRO, LEONARDO SAMPAIO FERRAZ - ICMC ; CAVALLARI, GABRIEL BISCARO - ICMC
- Unidade: ICMC
- DOI: 10.1109/SIBGRAPI54419.2021.00011
- Subjects: REDES NEURAIS; APRENDIZADO COMPUTACIONAL; RECONHECIMENTO DE IMAGEM
- Agências de fomento:
- Language: Inglês
- Imprenta:
- Publisher: IEEE
- Publisher place: Los Alamitos
- Date published: 2021
- Source:
- Título: Proceedings
- Conference titles: Conference on Graphics, Patterns and Images - SIBGRAPI
- Este periódico é de assinatura
- Este artigo é de acesso aberto
- URL de acesso aberto
- Cor do Acesso Aberto: green
-
ABNT
PONTI, Moacir Antonelli et al. Training deep networks from zero to hero: avoiding pitfalls and going beyond. 2021, Anais.. Los Alamitos: IEEE, 2021. Disponível em: https://doi.org/10.1109/SIBGRAPI54419.2021.00011. Acesso em: 29 dez. 2025. -
APA
Ponti, M. A., Santos, F. P. dos, Ribeiro, L. S. F., & Cavallari, G. B. (2021). Training deep networks from zero to hero: avoiding pitfalls and going beyond. In Proceedings. Los Alamitos: IEEE. doi:10.1109/SIBGRAPI54419.2021.00011 -
NLM
Ponti MA, Santos FP dos, Ribeiro LSF, Cavallari GB. Training deep networks from zero to hero: avoiding pitfalls and going beyond [Internet]. Proceedings. 2021 ;[citado 2025 dez. 29 ] Available from: https://doi.org/10.1109/SIBGRAPI54419.2021.00011 -
Vancouver
Ponti MA, Santos FP dos, Ribeiro LSF, Cavallari GB. Training deep networks from zero to hero: avoiding pitfalls and going beyond [Internet]. Proceedings. 2021 ;[citado 2025 dez. 29 ] Available from: https://doi.org/10.1109/SIBGRAPI54419.2021.00011 - Sketchformer: transformer-based representation for sketched structure
- Semi-supervised siamese network using self-supervision under scarce annotation improves class separability and robustness to attack
- Scene designer: compositional sketch-based image retrieval with contrastive learning and an auxiliary synthesis task
- Data augmentation guidelines for cross-dataset transfer learning and pseudo labeling
- Scene Designer: a unified model for scene search and synthesis from sketch
- Alignment of local and global features from multiple layers of convolutional neural network for image classification
- Homogeneity index as stopping criterion for anisotropic diffusion filter
- Learning image features with fewer labels using a semi-supervised deep convolutional network
- Features transfer learning for image and video recognition tasks
- Estudo de representações de imagens de múltiplos domínios a partir de aprendizado profundo não supervisionado e semi-supervisionado
Informações sobre o DOI: 10.1109/SIBGRAPI54419.2021.00011 (Fonte: oaDOI API)
Download do texto completo
| Tipo | Nome | Link | |
|---|---|---|---|
 |
3057145.pdf |
How to cite
A citação é gerada automaticamente e pode não estar totalmente de acordo com as normas
