ScholarGate
Asistente

Comparar métodos

Revisa los métodos seleccionados uno junto a otro; las filas que difieren aparecen resaltadas.

DETR (Detection Transformer)×Modelo de Segmentación de Cualquier Cosa×
CampoAprendizaje profundoAprendizaje profundo
FamiliaMachine learningMachine learning
Año de origen20202023
Autor originalNicolas CarionAlexander Kirillov
TipoNeural network architectureNeural network architecture
Fuente seminalCarion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., & Zagoruyko, S. (2020). End-to-end object detection with transformers. In European Conference on Computer Vision (pp. 213-229). Springer, Cham. DOI ↗Kirillov, A., Mintun, E., Darrell, T., & Girshick, R. (2023). Segment Anything. In Proceedings of the IEEE/CVF International Conference on Computer Vision (pp. 4015-4026). DOI ↗
AliasDetection Transformer, DETRSAM, Segment Anything
Relacionados44
ResumenDETR (Detection Transformer) is an end-to-end framework for object detection introduced by Carion et al. in 2020 that reformulates detection as a direct set prediction problem using transformers. Unlike traditional approaches that use hand-crafted post-processing like non-maximum suppression, DETR treats object detection as a sequence-to-sequence problem where the transformer predicts all objects at once.Segment Anything Model (SAM) is a foundation model introduced by Kirillov et al. in 2023 that can segment any object in an image given various forms of prompts. SAM is trained on a massive dataset of diverse images and learns to segment objects based on minimal user input such as points, boxes, or text descriptions.
ScholarGateConjunto de datos
  1. v1
  2. 1 Fuentes
  3. PUBLISHED
  1. v1
  2. 1 Fuentes
  3. PUBLISHED

Ir a la búsqueda Descargar diapositivas

ScholarGateComparar métodos: DETR (Detection Transformer) · Segment Anything Model. Recuperado el 2026-06-17 de https://scholargate.app/es/compare