Weakly-supervised HOI Detection via Prior-guided Bi-level Representation Learning
원문 초록
Human object interaction (HOI) detection plays a crucial role in human-centric scene understanding and serves as a fundamental building-block for many vision tasks. One generalizable and scalable strategy for HOI detection is to use weak supervision, learning from image-level annotations only. This is inherently challenging due to ambiguous human-object associations, large search space of detecting HOIs and highly noisy training signal. A promising strategy to address those challenges is to exploit knowledge from large-scale pretrained models (e.g., CLIP), but a direct knowledge distillation strategy~\citep{liao2022gen} does not perform well on the weakly-supervised setting. In contrast, we develop a CLIP-guided HOI representation capable of incorporating the prior knowledge at both image level and HOI instance level, and adopt a self-taught mechanism to prune incorrect human-object associations. Experimental results on HICO-DET and V-COCO show that our method outperforms the previous works by a sizable margin, showing the efficacy of our HOI representation.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
ERNet: Efficient and Reliable Human-Object Interaction Detection
RoHOI: Robustness Benchmark for Human-Object Interaction Detection
Feed-Forward SceneDINO for Unsupervised Semantic Scene Completion
MUVOD: A Novel Multi-view Video Object Segmentation Dataset and A Benchmark for 3D Segmentation
DreamAnywhere: Object-Centric Panoramic 3D Scene Generation
HOIverse: A Synthetic Scene Graph Dataset With Human Object Interactions
토론
이 논문과 연결된 포럼 글이 아직 없습니다.