Video Relationship Detection Using Mixture of Experts
Machine comprehension of visual information from images and videos by neural networks faces two primary challenges. Firstly, there exists a computational and inference gap in connecting vision and language, making it difficult to accurately determine which object a given agent acts on and represent...
Uloženo v:
| Vydáno v: | arXiv.org |
|---|---|
| Hlavní autoři: | , , |
| Médium: | Paper |
| Jazyk: | angličtina |
| Vydáno: |
Ithaca
Cornell University Library, arXiv.org
06.03.2024
|
| Témata: | |
| ISSN: | 2331-8422 |
| On-line přístup: | Získat plný text |
| Tagy: |
Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
|
| Shrnutí: | Machine comprehension of visual information from images and videos by neural networks faces two primary challenges. Firstly, there exists a computational and inference gap in connecting vision and language, making it difficult to accurately determine which object a given agent acts on and represent it through language. Secondly, classifiers trained by a single, monolithic neural network often lack stability and generalization. To overcome these challenges, we introduce MoE-VRD, a novel approach to visual relationship detection utilizing a mixture of experts. MoE-VRD identifies language triplets in the form of < subject, predicate, object> tuples to extract relationships from visual processing. Leveraging recent advancements in visual relationship detection, MoE-VRD addresses the requirement for action recognition in establishing relationships between subjects (acting) and objects (being acted upon). In contrast to single monolithic networks, MoE-VRD employs multiple small models as experts, whose outputs are aggregated. Each expert in MoE-VRD specializes in visual relationship learning and object tagging. By utilizing a sparsely-gated mixture of experts, MoE-VRD enables conditional computation and significantly enhances neural network capacity without increasing computational complexity. Our experimental results demonstrate that the conditional computation capabilities and scalability of the mixture-of-experts approach lead to superior performance in visual relationship detection compared to state-of-the-art methods. |
|---|---|
| Bibliografie: | SourceType-Working Papers-1 ObjectType-Working Paper/Pre-Print-1 content type line 50 |
| ISSN: | 2331-8422 |
| DOI: | 10.48550/arxiv.2403.03994 |