VinVLOptions

Options & Configuration · AiDotNet.VisionLanguage.Foundational

Configuration options for VinVL (Visual Features in Vision-Language).

Inheritance: ModelOptions → FoundationalVLMOptions → VinVLOptions

How It Works

VinVL (Zhang et al., CVPR 2021) improves on Oscar by providing better visual features through a stronger object detection backbone (ResNeXt-152 C4), enriching object tags with attributes and achieving state-of-the-art on VQA, captioning, and retrieval benchmarks.

Constructors

Constructor Summary
VinVLOptions() Initializes a new instance with default values.
VinVLOptions(VinVLOptions other) Initializes a new instance by copying from another instance.

Properties

Property Summary
bool UseAttributePredictions { get; set; } Gets or sets whether to include attribute predictions in object tags.
double DetectionThreshold { get; set; } Gets or sets the object detection confidence threshold.
int MaxImageRegions { get; set; } Gets or sets the maximum number of image regions.
int MaxObjectTags { get; set; } Gets or sets the maximum number of object tags with attributes.