Verification of Generative-Model-Based Visual Transformations
Generative networks are promising models for specifying visual transformations. Unfortunately, certification of generative models is challenging as one needs to capture sufficient non-convexity so to produce precise bounds on the output. Existing verification methods either fail to scale to generative networks or do not capture enough non-convexity. In this work, we present a new verifier, called ApproxLine, that can certify non-trivial properties of generative networks. ApproxLine performs both deterministic and probabilistic abstract interpretation and captures infinite sets of outputs of generative networks. We show that ApproxLine can verify interesting interpolations in the network's latent space.
Code (0)
등록된 구현이 없습니다.
Tasks
modelSimilar Papers 제목 키워드 기반
PROVES: Establishing Image Provenance using Semantic Signatures
Modern AI tools, such as generative adversarial networks, have transformed our ability to create and modify visual data with photorealistic results. However, one of the deleterious side-effects of these advances is the e…
Face VerificationExplainGAN: Model Explanation via Decision Boundary Crossing Transformations
We introduce a new method for interpreting computer vision models: visually perceptible, decision-boundary crossing transformations. Our goal is to answer a simple question: why did a model classify an image as being of …
modelDiscriminate-and-Rectify Encoders: Learning from Image Transformation Sets
The complexity of a learning task is increased by transformations in the input space that preserve class identity. Visual object recognition for example is affected by changes in viewpoint, scale, illumination or planar …
Face VerificationObject RecognitionRetrievalWeakly-supervised LearningVerification of Visual Controllers via Compositional Geometric Transformations
Perception-based neural network controllers are increasingly used in autonomous systems that rely on visual inputs to operate in the real world. Ensuring the safety of such systems under uncertainty is challenging. Exist…
Generative Universal Verifier as Multimodal Meta-Reasoner
We introduce Generative Universal Verifier, a novel concept and plugin designed for next-generation multimodal reasoning in vision-language models and unified multimodal models, providing the fundamental capability of re…
Multimodal ReasoningImage Generation