GPT4SGG: Synthesizing Scene Graphs from Holistic and Region-specific Narratives

• URL: http://arxiv.org/abs/2312.04314v2
• Date: Sun, 2 Jun 2024 11:32:19 GMT
• Title: GPT4SGG: Synthesizing Scene Graphs from Holistic and Region-specific Narratives
• Authors: Zuyao Chen, Jinlin Wu, Zhen Lei, Zhaoxiang Zhang, Changwen Chen,
• Abstract summary: We propose a novel framework named textitGPT4SGG to obtain more accurate and comprehensive scene graph signals. We show textitGPT4SGG significantly improves the performance of SGG models trained on image-caption data.
• Score: 69.36723767339001
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Training Scene Graph Generation (SGG) models with natural language captions has become increasingly popular due to the abundant, cost-effective, and open-world generalization supervision signals that natural language offers. However, such unstructured caption data and its processing pose significant challenges in learning accurate and comprehensive scene graphs. The challenges can be summarized as three aspects: 1) traditional scene graph parsers based on linguistic representation often fail to extract meaningful relationship triplets from caption data. 2) grounding unlocalized objects of parsed triplets will meet ambiguity issues in visual-language alignment. 3) caption data typically are sparse and exhibit bias to partial observations of image content. Aiming to address these problems, we propose a divide-and-conquer strategy with a novel framework named \textit{GPT4SGG}, to obtain more accurate and comprehensive scene graph signals. This framework decomposes a complex scene into a bunch of simple regions, resulting in a set of region-specific narratives. With these region-specific narratives (partial observations) and a holistic narrative (global observation) for an image, a large language model (LLM) performs the relationship reasoning to synthesize an accurate and comprehensive scene graph. Experimental results demonstrate \textit{GPT4SGG} significantly improves the performance of SGG models trained on image-caption data, in which the ambiguity issue and long-tail bias have been well-handled with more accurate and comprehensive scene graphs.

Related papers

• SG-Adapter: Enhancing Text-to-Image Generation with Scene Graph Guidance [46.77060502803466]
  We introduce the Scene Graph Adapter(SG-Adapter), leveraging the structured representation of scene graphs to rectify inaccuracies in the original text embeddings. The SG-Adapter's explicit and non-fully connected graph representation greatly improves the fully connected, transformer-based text representations.
  arXiv  Detail & Related papers  (2024-05-24T08:00:46Z)
• Lang3DSG: Language-based contrastive pre-training for 3D Scene Graph prediction [16.643252717745348]
  We present the first language-based pre-training approach for 3D scene graphs. We leverage the language encoder of CLIP, a popular vision-language model, to distill its knowledge into our graph-based network. Our method achieves state-of-the-art results on the main semantic 3D scene graph benchmark.
  arXiv  Detail & Related papers  (2023-10-25T09:26:16Z)
• LLM4SGG: Large Language Models for Weakly Supervised Scene Graph Generation [27.97296273461145]
  Weakly-Supervised Scene Graph Generation (WSSGG) research has recently emerged as an alternative to the fully-supervised approach. We propose a new approach, i.e., Large Language Model for weakly-supervised SGG (LLM4SGG) We show significant improvements in both Recall@K and mean Recall@K compared to the state-of-the-art WSSGG methods.
  arXiv  Detail & Related papers  (2023-10-16T13:49:46Z)
• FACTUAL: A Benchmark for Faithful and Consistent Textual Scene Graph Parsing [66.70054075041487]
  Existing scene graphs that convert image captions into scene graphs often suffer from two types of errors. First, the generated scene graphs fail to capture the true semantics of the captions or the corresponding images, resulting in a lack of faithfulness. Second, the generated scene graphs have high inconsistency, with the same semantics represented by different annotations.
  arXiv  Detail & Related papers  (2023-05-27T15:38:31Z)
• CommonScenes: Generating Commonsense 3D Indoor Scenes with Scene Graph Diffusion [83.30168660888913]
  We present CommonScenes, a fully generative model that converts scene graphs into corresponding controllable 3D scenes. Our pipeline consists of two branches, one predicting the overall scene layout via a variational auto-encoder and the other generating compatible shapes. The generated scenes can be manipulated by editing the input scene graph and sampling the noise in the diffusion model.
  arXiv  Detail & Related papers  (2023-05-25T17:39:13Z)
• Semantic Compositional Learning for Low-shot Scene Graph Generation [122.51930904132685]
  Many scene graph generation (SGG) models solely use the limited annotated relation triples for training. We propose a novel semantic compositional learning strategy that makes it possible to construct additional, realistic relation triples. For three recent SGG models, adding our strategy improves their performance by close to 50%, and all of them substantially exceed the current state-of-the-art.
  arXiv  Detail & Related papers  (2021-08-19T10:13:55Z)
• Linguistic Structures as Weak Supervision for Visual Scene Graph Generation [39.918783911894245]
  We show how linguistic structures in captions can benefit scene graph generation. Our method captures the information provided in captions about relations between individual triplets, and context for subjects and objects. Given the large and diverse sources of multimodal data on the web, linguistic supervision is more scalable than crowdsourced triplets.
  arXiv  Detail & Related papers  (2021-05-28T17:20:27Z)
• Generative Compositional Augmentations for Scene Graph Prediction [27.535630110794855]
  Inferring objects and their relationships from an image in the form of a scene graph is useful in many applications at the intersection of vision and language. We consider a challenging problem of compositional generalization that emerges in this task due to a long tail data distribution. We propose and empirically study a model based on conditional generative adversarial networks (GANs) that allows us to generate visual features of perturbed scene graphs.
  arXiv  Detail & Related papers  (2020-07-11T12:11:53Z)
• Structure-Augmented Text Representation Learning for Efficient Knowledge Graph Completion [53.31911669146451]
  Human-curated knowledge graphs provide critical supportive information to various natural language processing tasks. These graphs are usually incomplete, urging auto-completion of them. graph embedding approaches, e.g., TransE, learn structured knowledge via representing graph elements into dense embeddings. textual encoding approaches, e.g., KG-BERT, resort to graph triple's text and triple-level contextualized representations.
  arXiv  Detail & Related papers  (2020-04-30T13:50:34Z)
• Fine-grained Video-Text Retrieval with Hierarchical Graph Reasoning [72.52804406378023]
  Cross-modal retrieval between videos and texts has attracted growing attentions due to the rapid emergence of videos on the web. To improve fine-grained video-text retrieval, we propose a Hierarchical Graph Reasoning model, which decomposes video-text matching into global-to-local levels.
  arXiv  Detail & Related papers  (2020-03-01T03:44:19Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.