Can We Find Neurons that Cause Unrealistic Images in Deep Generative Networks?
Even though Generative Adversarial Networks (GANs) have shown a remarkable ability to generate high-quality images, GANs do not always guarantee the generation of photorealistic images. Occasionally, they generate images that have defective or unnatural objects, which are referred to as 'artifacts'. Research to investigate why these artifacts emerge and how they can be detected and removed has yet to be sufficiently carried out. To analyze this, we first hypothesize that rarely activated neurons and frequently activated neurons have different purposes and responsibilities for the progress of generating images. In this study, by analyzing the statistics and the roles for those neurons, we empirically show that rarely activated neurons are related to the failure results of making diverse objects and inducing artifacts. In addition, we suggest a correction method, called 'Sequential Ablation', to repair the defective part of the generated images without high computational cost and manual efforts.
Code (1)
Tasks
GAN image forensicsImage GenerationImage ManipulationImage ReconstructionMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Training capsules as a routing-weighted product of expert neurons
Capsules are the multidimensional analogue to scalar neurons in neural networks, and because they are multidimensional, much more complex routing schemes can be used to pass information forward through the network than w…
High-contrast "gaudy" images improve the training of deep neural network models of visual cortex
A key challenge in understanding the sensory transformations of the visual system is to obtain a highly predictive model of responses from visual cortical neurons. Deep neural networks (DNNs) provide a promising candidat…
Active LearningDeleting object selective units in a fully-connected layer of deep convolutional networks improves classification performance
Neurons in the primate visual cortices show a wide range of stimulus selectivity. Some neurons respond to only a small fraction of stimulus images, whereas others respond to many stimulus images in a non-selective manner…
Object RecognitionDiffusion-Stego: Training-free Diffusion Generative Steganography via Message Projection
Generative steganography is the process of hiding secret messages in generated images instead of cover images. Existing studies on generative steganography use GAN or Flow models to obtain high hiding message capacity an…
DenoisingImage GenerationRe-Evaluating LiDAR Scene Flow for Autonomous Driving
Popular benchmarks for self-supervised LiDAR scene flow (stereoKITTI, and FlyingThings3D) have unrealistic rates of dynamic motion, unrealistic correspondences, and unrealistic sampling patterns. As a result, progress on…
Autonomous DrivingMotion CompensationScene Flow Estimation