public sealed class XraiAttribution : IMessage<XraiAttribution>, IEquatable<XraiAttribution>, IDeepCloneable<XraiAttribution>, IBufferMessage, IMessage
Reference documentation and code samples for the Vertex AI v1beta1 API class XraiAttribution.
An explanation method that redistributes Integrated Gradients
attributions to segmented regions, taking advantage of the model's fully
differentiable structure. Refer to this paper for more details:
https://arxiv.org/abs/1906.02825
public BlurBaselineConfig BlurBaselineConfig { get; set; }
Config for XRAI with blur baseline.
When enabled, a linear path from the maximally blurred image to the input
image is created. Using a blurred baseline instead of zero (black image) is
motivated by the BlurIG approach explained here:
https://arxiv.org/abs/2004.03383
public SmoothGradConfig SmoothGradConfig { get; set; }
Config for SmoothGrad approximation of gradients.
When enabled, the gradients are approximated by averaging the gradients
from noisy samples in the vicinity of the inputs. Adding
noise can help improve the computed gradients. Refer to this paper for more
details: https://arxiv.org/pdf/1706.03825.pdf
Required. The number of steps for approximating the path integral.
A good value to start is 50 and gradually increase until the
sum to diff property is met within the desired error range.
Valid range of its value is [1, 100], inclusively.
[[["Easy to understand","easyToUnderstand","thumb-up"],["Solved my problem","solvedMyProblem","thumb-up"],["Other","otherUp","thumb-up"]],[["Missing the information I need","missingTheInformationINeed","thumb-down"],["Too complicated / too many steps","tooComplicatedTooManySteps","thumb-down"],["Out of date","outOfDate","thumb-down"],["Samples / code issue","samplesCodeIssue","thumb-down"],["Other","otherDown","thumb-down"]],["Last updated 2025-08-28 UTC."],[[["\u003cp\u003eThe \u003ccode\u003eXraiAttribution\u003c/code\u003e class in the Vertex AI v1beta1 API provides a method for redistributing Integrated Gradients attributions to segmented regions in image models.\u003c/p\u003e\n"],["\u003cp\u003eThis class implements interfaces such as \u003ccode\u003eIMessage\u003c/code\u003e, \u003ccode\u003eIEquatable\u003c/code\u003e, \u003ccode\u003eIDeepCloneable\u003c/code\u003e, and \u003ccode\u003eIBufferMessage\u003c/code\u003e, enabling it to work within the Google Protocol Buffers framework.\u003c/p\u003e\n"],["\u003cp\u003eIt offers properties like \u003ccode\u003eBlurBaselineConfig\u003c/code\u003e and \u003ccode\u003eSmoothGradConfig\u003c/code\u003e to refine attribution calculations using blur baselines and SmoothGrad approximations respectively.\u003c/p\u003e\n"],["\u003cp\u003eThe \u003ccode\u003eStepCount\u003c/code\u003e property allows configuration of the number of steps for approximating the path integral, which is crucial for the accuracy of attribution calculations with a valid range between 1 and 100.\u003c/p\u003e\n"],["\u003cp\u003eThe method is only supported by image Models.\u003c/p\u003e\n"]]],[],null,["# Vertex AI v1beta1 API - Class XraiAttribution (1.0.0-beta47)\n\nVersion latestkeyboard_arrow_down\n\n- [1.0.0-beta47 (latest)](/dotnet/docs/reference/Google.Cloud.AIPlatform.V1Beta1/latest/Google.Cloud.AIPlatform.V1Beta1.XraiAttribution)\n- [1.0.0-beta46](/dotnet/docs/reference/Google.Cloud.AIPlatform.V1Beta1/1.0.0-beta46/Google.Cloud.AIPlatform.V1Beta1.XraiAttribution) \n\n public sealed class XraiAttribution : IMessage\u003cXraiAttribution\u003e, IEquatable\u003cXraiAttribution\u003e, IDeepCloneable\u003cXraiAttribution\u003e, IBufferMessage, IMessage\n\nReference documentation and code samples for the Vertex AI v1beta1 API class XraiAttribution.\n\nAn explanation method that redistributes Integrated Gradients\nattributions to segmented regions, taking advantage of the model's fully\ndifferentiable structure. Refer to this paper for more details:\n\u003chttps://arxiv.org/abs/1906.02825\u003e\n\nSupported only by image Models. \n\nInheritance\n-----------\n\n[object](https://learn.microsoft.com/dotnet/api/system.object) \\\u003e XraiAttribution \n\nImplements\n----------\n\n[IMessage](https://cloud.google.com/dotnet/docs/reference/Google.Protobuf/latest/Google.Protobuf.IMessage-1.html)[XraiAttribution](/dotnet/docs/reference/Google.Cloud.AIPlatform.V1Beta1/latest/Google.Cloud.AIPlatform.V1Beta1.XraiAttribution), [IEquatable](https://learn.microsoft.com/dotnet/api/system.iequatable-1)[XraiAttribution](/dotnet/docs/reference/Google.Cloud.AIPlatform.V1Beta1/latest/Google.Cloud.AIPlatform.V1Beta1.XraiAttribution), [IDeepCloneable](https://cloud.google.com/dotnet/docs/reference/Google.Protobuf/latest/Google.Protobuf.IDeepCloneable-1.html)[XraiAttribution](/dotnet/docs/reference/Google.Cloud.AIPlatform.V1Beta1/latest/Google.Cloud.AIPlatform.V1Beta1.XraiAttribution), [IBufferMessage](https://cloud.google.com/dotnet/docs/reference/Google.Protobuf/latest/Google.Protobuf.IBufferMessage.html), [IMessage](https://cloud.google.com/dotnet/docs/reference/Google.Protobuf/latest/Google.Protobuf.IMessage.html) \n\nInherited Members\n-----------------\n\n[object.GetHashCode()](https://learn.microsoft.com/dotnet/api/system.object.gethashcode) \n[object.GetType()](https://learn.microsoft.com/dotnet/api/system.object.gettype) \n[object.ToString()](https://learn.microsoft.com/dotnet/api/system.object.tostring)\n\nNamespace\n---------\n\n[Google.Cloud.AIPlatform.V1Beta1](/dotnet/docs/reference/Google.Cloud.AIPlatform.V1Beta1/latest/Google.Cloud.AIPlatform.V1Beta1)\n\nAssembly\n--------\n\nGoogle.Cloud.AIPlatform.V1Beta1.dll\n\nConstructors\n------------\n\n### XraiAttribution()\n\n public XraiAttribution()\n\n### XraiAttribution(XraiAttribution)\n\n public XraiAttribution(XraiAttribution other)\n\nProperties\n----------\n\n### BlurBaselineConfig\n\n public BlurBaselineConfig BlurBaselineConfig { get; set; }\n\nConfig for XRAI with blur baseline.\n\nWhen enabled, a linear path from the maximally blurred image to the input\nimage is created. Using a blurred baseline instead of zero (black image) is\nmotivated by the BlurIG approach explained here:\n\u003chttps://arxiv.org/abs/2004.03383\u003e\n\n### SmoothGradConfig\n\n public SmoothGradConfig SmoothGradConfig { get; set; }\n\nConfig for SmoothGrad approximation of gradients.\n\nWhen enabled, the gradients are approximated by averaging the gradients\nfrom noisy samples in the vicinity of the inputs. Adding\nnoise can help improve the computed gradients. Refer to this paper for more\ndetails: \u003chttps://arxiv.org/pdf/1706.03825.pdf\u003e\n\n### StepCount\n\n public int StepCount { get; set; }\n\nRequired. The number of steps for approximating the path integral.\nA good value to start is 50 and gradually increase until the\nsum to diff property is met within the desired error range.\n\nValid range of its value is \\[1, 100\\], inclusively."]]
