Visual Abductive Reasoning
- Publisher:
- Institute of Electrical and Electronics Engineers (IEEE)
- Publication Type:
- Conference Proceeding
- Citation:
- Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2022, 2022-June, pp. 15544-15554
- Issue Date:
- 2022-01-01
Embargoed
| Filename | Description | Size | |||
|---|---|---|---|---|---|
| Visual Abductive Reasoning.pdf | Accepted version | 4.97 MB |
Copyright Clearance Process
- Recently Added
- In Progress
- Open Access
This item is currently unavailable due to the publisher's embargo.
Abductive reasoning seeks the likeliest possible explanation for partial observations. Although abduction is frequently employed in human daily reasoning, it is rarely explored in computer vision literature. In this paper, we propose a new task and dataset, Visual Abductive Reasoning (VAR), for examining abductive reasoning ability of machine intelligence in everyday visual situations. Given an incomplete set of visual events, AI systems are required to not only describe what is observed, but also infer the hypothesis that can best explain the visual premise. Based on our large-scale VAR dataset, we devise a strong baseline model, REASONER (causal-and-cascaded reasoning Transformer). First, to capture the causal structure of the observations, a contextualized directional position embedding strategy is adopted in the encoder, that yields discriminative represen-tations for the premise and hypothesis. Then, multiple de-coders are cascaded to generate and progressively refine the premise and hypothesis sentences. The prediction scores of the sentences are used to guide cross-sentence information flow in the cascaded reasoning procedure. Our VAR bench-marking results show that REASONER surpasses many famous video-language models, while still being far behind human performance. This work is expected to foster future efforts in the reasoning-beyond-observation paradigm.
Please use this identifier to cite or link to this item: