Guardado en:
| Autores principales: | , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | https://arxiv.org/abs/2401.14626 |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866911764932722688 |
|---|---|
| author | He, Tao Wu, Tongtong Zhang, Dongyang Duan, Guiduo Qin, Ke Li, Yuan-Fang |
| author_facet | He, Tao Wu, Tongtong Zhang, Dongyang Duan, Guiduo Qin, Ke Li, Yuan-Fang |
| contents | Scene graph generation (SGG) endeavors to predict visual relationships between pairs of objects within an image. Prevailing SGG methods traditionally assume a one-off learning process for SGG. This conventional paradigm may necessitate repetitive training on all previously observed samples whenever new relationships emerge, mitigating the risk of forgetting previously acquired knowledge. This work seeks to address this pitfall inherent in a suite of prior relationship predictions. Motivated by the achievements of in-context learning in pretrained language models, our approach imbues the model with the capability to predict relationships and continuously acquire novel knowledge without succumbing to catastrophic forgetting. To achieve this goal, we introduce a novel and pragmatic framework for scene graph generation, namely Lifelong Scene Graph Generation (LSGG), where tasks, such as predicates, unfold in a streaming fashion. In this framework, the model is constrained to exclusive training on the present task, devoid of access to previously encountered training data, except for a limited number of exemplars, but the model is tasked with inferring all predicates it has encountered thus far. Rigorous experiments demonstrate the superiority of our proposed method over state-of-the-art SGG models in the context of LSGG across a diverse array of metrics. Besides, extensive experiments on the two mainstream benchmark datasets, VG and Open-Image(v6), show the superiority of our proposed model to a number of competitive SGG models in terms of continuous learning and conventional settings. Moreover, comprehensive ablation experiments demonstrate the effectiveness of each component in our model. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2401_14626 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Towards Lifelong Scene Graph Generation with Knowledge-ware In-context Prompt Learning He, Tao Wu, Tongtong Zhang, Dongyang Duan, Guiduo Qin, Ke Li, Yuan-Fang Computer Vision and Pattern Recognition Scene graph generation (SGG) endeavors to predict visual relationships between pairs of objects within an image. Prevailing SGG methods traditionally assume a one-off learning process for SGG. This conventional paradigm may necessitate repetitive training on all previously observed samples whenever new relationships emerge, mitigating the risk of forgetting previously acquired knowledge. This work seeks to address this pitfall inherent in a suite of prior relationship predictions. Motivated by the achievements of in-context learning in pretrained language models, our approach imbues the model with the capability to predict relationships and continuously acquire novel knowledge without succumbing to catastrophic forgetting. To achieve this goal, we introduce a novel and pragmatic framework for scene graph generation, namely Lifelong Scene Graph Generation (LSGG), where tasks, such as predicates, unfold in a streaming fashion. In this framework, the model is constrained to exclusive training on the present task, devoid of access to previously encountered training data, except for a limited number of exemplars, but the model is tasked with inferring all predicates it has encountered thus far. Rigorous experiments demonstrate the superiority of our proposed method over state-of-the-art SGG models in the context of LSGG across a diverse array of metrics. Besides, extensive experiments on the two mainstream benchmark datasets, VG and Open-Image(v6), show the superiority of our proposed model to a number of competitive SGG models in terms of continuous learning and conventional settings. Moreover, comprehensive ablation experiments demonstrate the effectiveness of each component in our model. |
| title | Towards Lifelong Scene Graph Generation with Knowledge-ware In-context Prompt Learning |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2401.14626 |