paper-with-me

홈 › Papers

Explaining in Style: Training a GAN to explain a classifier in StyleSpace

2021-04-27 · ICCV 2021 10 · Oran Lang, Yossi Gandelsman, Michal Yarom, Yoav Wald, Gal Elidan, Avinatan Hassidim, William T. Freeman, Phillip Isola, Amir Globerson, Michal Irani, Inbar Mosseri

Image classification models can depend on multiple different semantic attributes of the image. An explanation of the decision of the classifier needs to both discover and visualize these properties. Here we present StylEx, a method for doing this, by training a generative model to specifically explain multiple attributes that underlie classifier decisions. A natural source for such attributes is the StyleSpace of StyleGAN, which is known to generate semantically meaningful dimensions in the image. However, because standard GAN training is not dependent on the classifier, it may not represent these attributes which are important for the classifier decision, and the dimensions of StyleSpace may represent irrelevant attributes. To overcome this, we propose a training procedure for a StyleGAN, which incorporates the classifier model, in order to learn a classifier-specific StyleSpace. Explanatory attributes are then selected from this space. These can be used to visualize the effect of changing multiple attributes per image, thus providing image-specific explanations. We apply StylEx to multiple domains, including animals, leaves, faces and retinal images. For these, we show how an image can be modified in different ways to change its classifier output. Our results show that the method finds attributes that align well with semantic ones, generate meaningful image-specific explanations, and are human-interpretable as measured in user-studies.

📄 PDF Abstract BibTeX arXiv:2104.13369

Code (2)

google/explaining-in-style 공식 구현 tf
camp-explain-ai/style-chexplain pytorch

Tasks

image-classificationImage Classification

Methods 이 논문이 사용한 방법론

Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
Adaptive Instance Normalization 설명 없음
Feedforward Network A Feedforward Network, or a Multilayer Perceptron (MLP), is a neural network with solely densely connected layers. This is the classic neural network architecture of the…
R1 Regularization R_INLINE_MATH_1 Regularization is a regularization technique and gradient penalty for training [generative adversarial…
HuMan(Expedia)||How do I get a human at Expedia? How do I get a human at Expedia? How Do I Get a Human at Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Real-Time Help & Exclusive…
Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…

Similar Papers 제목 키워드 기반

StyleSpace Analysis: Disentangled Controls for StyleGAN Image Generation

2020-11-25 · CVPR 2021 1 · Zongze Wu, Dani Lischinski, Eli Shechtman

We explore and analyze the latent style space of StyleGAN2, a state-of-the-art architecture for image generation, using models pretrained on several different datasets. We first show that StyleSpace, the space of channel…

AttributeImage Generation

SelfExplain: A Self-Explaining Architecture for Neural Text Classifiers

2021-03-23 · EMNLP 2021 11 · Dheeraj Rajagopal, Vidhisha Balachandran, Eduard Hovy, Yulia Tsvetkov

We introduce SelfExplain, a novel self-explaining model that explains a text classifier's predictions using phrase-based concepts. SelfExplain augments existing neural classifiers by adding (1) a globally interpretable l…

text-classificationText Classification

On the Complexity of Global Necessary Reasons to Explain Classification

2025-01-12 · Marco Calautti, Enrico Malizia, Cristian Molinaro

Explainable AI has garnered considerable attention in recent years, as understanding the reasons behind decisions or predictions made by AI systems is crucial for their successful adoption. Explaining classifiers' behavi…

Explaining in Diffusion: Explaining a Classifier with Diffusion Semantics

2025-01-01 · CVPR 2025 1 · Tahira Kazimi, Ritika Allada, Pinar Yanardag

Classifiers are important components in many computer vision tasks, serving as the foundational backbone of a wide variety of models employed across diverse applications. However, understanding the decision-making pr…

Explaining in Diffusion: Explaining a Classifier Through Hierarchical Semantics with Text-to-Image Diffusion Models

2024-12-24 · Tahira Kazimi, Ritika Allada, Pinar Yanardag

Classifiers are important components in many computer vision tasks, serving as the foundational backbone of a wide variety of models employed across diverse applications. However, understanding the decision-making proces…