An effective combination of loss gradients for multi-task learning applied on instance segmentation and depth estimation (2021)
- Authors:
- USP affiliated authors: GRASSI JUNIOR, VALDIR - EESC ; WOLF, DENIS FERNANDO - ICMC ; NAKAMURA, ANGELICA TIEMI MIZUNO - ICMC
- Unidades: EESC; ICMC
- DOI: 10.1016/j.engappai.2021.104205
- Subjects: TOMADA DE DECISÃO; ANÁLISE DE DESEMPENHO; APRENDIZADO COMPUTACIONAL
- Keywords: Multi-task learning; Instance segmentation; Depth estimation
- Agências de fomento:
- Language: Inglês
- Imprenta:
- Source:
- Título do periódico: Engineering Applications of Artificial Intelligence
- ISSN: 0952-1976
- Volume/Número/Paginação/Ano: v. 100, p. 1-10, 2021
- Este periódico é de assinatura
- Este artigo NÃO é de acesso aberto
- Cor do Acesso Aberto: closed
-
ABNT
NAKAMURA, Angelica Tiemi Mizuno e GRASSI JÚNIOR, Valdir e WOLF, Denis Fernando. An effective combination of loss gradients for multi-task learning applied on instance segmentation and depth estimation. Engineering Applications of Artificial Intelligence, v. 100, p. 1-10, 2021Tradução . . Disponível em: https://doi.org/10.1016/j.engappai.2021.104205. Acesso em: 28 mar. 2024. -
APA
Nakamura, A. T. M., Grassi Júnior, V., & Wolf, D. F. (2021). An effective combination of loss gradients for multi-task learning applied on instance segmentation and depth estimation. Engineering Applications of Artificial Intelligence, 100, 1-10. doi:10.1016/j.engappai.2021.104205 -
NLM
Nakamura ATM, Grassi Júnior V, Wolf DF. An effective combination of loss gradients for multi-task learning applied on instance segmentation and depth estimation [Internet]. Engineering Applications of Artificial Intelligence. 2021 ; 100 1-10.[citado 2024 mar. 28 ] Available from: https://doi.org/10.1016/j.engappai.2021.104205 -
Vancouver
Nakamura ATM, Grassi Júnior V, Wolf DF. An effective combination of loss gradients for multi-task learning applied on instance segmentation and depth estimation [Internet]. Engineering Applications of Artificial Intelligence. 2021 ; 100 1-10.[citado 2024 mar. 28 ] Available from: https://doi.org/10.1016/j.engappai.2021.104205 - Leveraging convergence behavior to balance conflicting tasks in multitask learning
- Improving multi-goal and target-driven reinforcement learning with supervised auxiliary task
- Leveraging convergence behavior to balance conflicting tasks in multitask learning
- Identificação do modelo longitudinal de um veículo de grande porte utilizando processos gaussianos
- Autonomous vehicle navigation in semi-structured urban environment
- Detecção de vagas e estacionamento autônomo de veículos
- Obstacle avoidance using stereo-based generic obstacle tracking
- Avaliação e proposta de sistemas de câmeras estéreo para detecção de pedestres em veículos inteligentes
- Decision making for autonomous vehicles at signalized intersection under uncertain traffic signal phase and timing information
- Effective deep reinforcement learning setups for multiple goals on visual navigation
Informações sobre o DOI: 10.1016/j.engappai.2021.104205 (Fonte: oaDOI API)
Download do texto completo
Tipo | Nome | Link | |
---|---|---|---|
3021516.pdf |
How to cite
A citação é gerada automaticamente e pode não estar totalmente de acordo com as normas