Paper
LLMs & Texto
Selective Synergistic Learning for Video Object-Centric Learning
Selective Synergistic Learning (SSync) addresses limitations in video object-centric learning by selectively distilling reliable cues through pseudo-labeling and transitive merging…
Hugging Face · Daily Papers
·WonJun Moon, Jae-Pil Heo
·
·▲ 3 upvotes
Este artigo está em destaque na seleção diária de papers do Hugging Face, curada pela comunidade de pesquisa em IA.
Autores: WonJun Moon, Jae-Pil Heo
- 3 upvotes da comunidade
- Temas: video object-centric learning, slot-based frameworks, encoder-decoder architectures, attention maps, object maps, contrastive learning
Resumo
Resumo original (em inglês), extraído do paper:
Selective Synergistic Learning (SSync) addresses limitations in video object-centric learning by selectively distilling reliable cues through pseudo-labeling and transitive merging to improve object decomposition quality and robustness.
