Towards Visually Explaining Variational Autoencoders

@article{Liu2020TowardsVE,
  title={Towards Visually Explaining Variational Autoencoders},
  author={WenQian Liu and Runze Li and Meng Zheng and Srikrishna Karanam and Ziyan Wu and Bir Bhanu and Richard J. Radke and Octavia I. Camps},
  journal={2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year={2020},
  pages={8639-8648}
}
  • WenQian Liu, Runze Li, +5 authors O. Camps
  • Published 2020
  • Computer Science
  • 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
Recent advances in Convolutional Neural Network (CNN) model interpretability have led to impressive progress in visualizing and understanding model predictions. In particular, gradient-based visual attention methods have driven much recent effort in using visual attention maps as a means for visual explanations. A key problem, however, is these methods are designed for classification and categorization tasks, and their extension to explaining generative models, e.g., variational autoencoders… Expand
Reproducing Visual Explanations of Variational Autoencoders
  • 2021
In this work we perform a replication study of the paper “Towards Visually Explaining Variational Autoencoders". 3 This paper claims to have found a method to provide visual explanations ofExpand
Transferring Knowledge with Attention Distillation for Multi-Domain Image-to-Image Translation
TLDR
It is shown how gradientbased attentions can be used as knowledge to be conveyed in a teacher-student paradigm for multi-domain image-toimage translation tasks in order to improve the results of the student architecture. Expand
Reproducibility report: Towards Visually Explaining Variational Autoencoders
The paper by Liu et al. [7] claims to develop a new technique that is capable of visually explaining Variational Autoen3 coders (VAEs). Additionally, these explanation maps can support simple modelsExpand
Reproducing: Towards Visually Explaining Variational Autoencoders
Reproducing the visual explanation for the basic VAE resulted in figures that are roughly similar to their images. Reproducing the anomaly detection images on the MNIST dataset resulted in imagesExpand
Transfer Learning Gaussian Anomaly Detection by Fine-Tuning Representations
TLDR
A new method to fine-tune learned representations for AD in a transfer learning setting is proposed, based on the linkage between generative and discriminative modeling, which induces a multivariate Gaussian distribution for the normal class, and uses the Mahalanobis distance of normal images to the distribution as training objective. Expand
Where and When: Space-Time Attention for Audio-Visual Explanations
TLDR
A novel space-time attention network is proposed that uncovers the synergistic dynamics of audio and visual data over both space and time and is capable of predicting the audio-visual video events, while justifying its decision by localizing where the relevant visual cues appear, and when the predicted sounds occur in videos. Expand
Combining GANs and AutoEncoders for efficient anomaly detection
  • Fabio Carrara, G. Amato, +4 authors Italy.
  • Computer Science, Mathematics
  • 2020 25th International Conference on Pattern Recognition (ICPR)
  • 2021
TLDR
Experiments show that the proposed CBiGAN improves the performance of BiGAN formulations by a large margin and performs comparably to expensive state-of-the-art iterative methods while reducing the computational cost. Expand
Attention Map-guided Two-stage Anomaly Detection using Hard Augmentation
TLDR
A novel twostage network consisting of an attention network and an anomaly detection GAN based on synthetic anomaly samples generated from hard augmentation outperforms the state-of-the-art anomaly detection and anomaly segmentation methods for widely used datasets. Expand
Reconstruction by inpainting for visual anomaly detection
TLDR
The RIAD approach (RIAD) randomly removes partial image regions and reconstructs the image from partial inpaintings, thus addressing the drawbacks of auto-enocoding methods. Expand
Contrastive Predictive Coding for Anomaly Detection
TLDR
This paper shows that its patch-wise contrastive loss can directly be interpreted as an anomaly score, and how this allows for the creation of anomaly segmentation masks, and achieves promising results for both anomaly detection and segmentation on the challenging MVTec-AD dataset. Expand
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 64 REFERENCES
Self-Attention Generative Adversarial Networks
TLDR
The proposed SAGAN achieves the state-of-the-art results, boosting the best published Inception score from 36.8 to 52.52 and reducing Frechet Inception distance from 27.62 to 18.65 on the challenging ImageNet dataset. Expand
Guided Attention Inference Network
TLDR
This paper makes attention maps a natural and explicit component in the training pipeline such that they are end-to-end trainable and provides self-guidance directly on these maps by exploring supervision from the network itself to improve them towards specific target tasks. Expand
Sharpen Focus: Learning With Attention Separability and Consistency
TLDR
This paper proposes a new framework that makes class-discriminative attention a principled part of the learning process and introduces new learning objectives for attention separability and cross-layer consistency, which result in improved attention discriminability and reduced visual confusion. Expand
Grad-CAM: Visual Explanations from Deep Networks via Gradient-Based Localization
TLDR
This work proposes a technique for producing ‘visual explanations’ for decisions from a large class of Convolutional Neural Network (CNN)-based models, making them more transparent and explainable, and shows that even non-attention based models learn to localize discriminative regions of input image. Expand
Grad-CAM++: Generalized Gradient-Based Visual Explanations for Deep Convolutional Networks
TLDR
This paper proposes Grad-CAM++, which uses a weighted combination of the positive partial derivatives of the last convolutional layer feature maps with respect to a specific class score as weights to generate a visual explanation for the class label under consideration, to provide better visual explanations of CNN model predictions. Expand
beta-VAE: Learning Basic Visual Concepts with a Constrained Variational Framework
Learning an interpretable factorised representation of the independent data generative factors of the world without supervision is an important precursor for the development of artificialExpand
Top-Down Neural Attention by Excitation Backprop
TLDR
A new backpropagation scheme, called Excitation Backprop, is proposed to pass along top-down signals downwards in the network hierarchy via a probabilistic Winner-Take-All process, and the concept of contrastive attention is introduced to make the top- down attention maps more discriminative. Expand
Learning Generative Models with Visual Attention
TLDR
A deep-learning based generative framework using attention that can robustly attend to the face region of novel test subjects and can learn generative models of new faces from a novel dataset of large images where the face locations are not known. Expand
Attention Branch Network: Learning of Attention Mechanism for Visual Explanation
TLDR
Attention Branch Network (ABN) is proposed, which extends a response-based visual explanation model by introducing a branch structure with an attention mechanism and is trainable for visual explanation and image recognition in an end-to-end manner. Expand
Visualizing and Understanding Convolutional Networks
TLDR
A novel visualization technique is introduced that gives insight into the function of intermediate feature layers and the operation of the classifier in large Convolutional Network models, used in a diagnostic role to find model architectures that outperform Krizhevsky et al on the ImageNet classification benchmark. Expand
...
1
2
3
4
5
...