Resilience through Scene Context in Visual Referring Expression Generation
Fuente:
arXiv
Salvato in:
| Autori principali: | , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866913477053906944 |
|---|---|
| author | Junker, Simeon Zarrieß, Sina |
| author_facet | Junker, Simeon Zarrieß, Sina |
| contents | Scene context is well known to facilitate humans' perception of visible objects. In this paper, we investigate the role of context in Referring Expression Generation (REG) for objects in images, where existing research has often focused on distractor contexts that exert pressure on the generator. We take a new perspective on scene context in REG and hypothesize that contextual information can be conceived of as a resource that makes REG models more resilient and facilitates the generation of object descriptions, and object types in particular. We train and test Transformer-based REG models with target representations that have been artificially obscured with noise to varying degrees. We evaluate how properties of the models' visual context affect their processing and performance. Our results show that even simple scene contexts make models surprisingly resilient to perturbations, to the extent that they can identify referent types even when visual information about the target is completely missing. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2404_12289 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Resilience through Scene Context in Visual Referring Expression Generation Junker, Simeon Zarrieß, Sina Computation and Language Scene context is well known to facilitate humans' perception of visible objects. In this paper, we investigate the role of context in Referring Expression Generation (REG) for objects in images, where existing research has often focused on distractor contexts that exert pressure on the generator. We take a new perspective on scene context in REG and hypothesize that contextual information can be conceived of as a resource that makes REG models more resilient and facilitates the generation of object descriptions, and object types in particular. We train and test Transformer-based REG models with target representations that have been artificially obscured with noise to varying degrees. We evaluate how properties of the models' visual context affect their processing and performance. Our results show that even simple scene contexts make models surprisingly resilient to perturbations, to the extent that they can identify referent types even when visual information about the target is completely missing. |
| title | Resilience through Scene Context in Visual Referring Expression Generation |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2404.12289 |