Transforming gradient-based techniques into interpretable methods
- URL: http://arxiv.org/abs/2401.14434v2
- Date: Wed, 15 May 2024 08:52:23 GMT
- Title: Transforming gradient-based techniques into interpretable methods
- Authors: Caroline Mazini Rodrigues, Nicolas Boutry, Laurent Najman,
- Abstract summary: We introduce GAD (Gradient Artificial Distancing) as a supportive framework for gradient-based techniques.
Its primary objective is to accentuate influential regions by establishing distinctions between classes.
Empirical investigations involving occluded images have demonstrated that the identified regions through this methodology indeed play a pivotal role in facilitating class differentiation.
- Score: 3.6763102409647526
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: The explication of Convolutional Neural Networks (CNN) through xAI techniques often poses challenges in interpretation. The inherent complexity of input features, notably pixels extracted from images, engenders complex correlations. Gradient-based methodologies, exemplified by Integrated Gradients (IG), effectively demonstrate the significance of these features. Nevertheless, the conversion of these explanations into images frequently yields considerable noise. Presently, we introduce GAD (Gradient Artificial Distancing) as a supportive framework for gradient-based techniques. Its primary objective is to accentuate influential regions by establishing distinctions between classes. The essence of GAD is to limit the scope of analysis during visualization and, consequently reduce image noise. Empirical investigations involving occluded images have demonstrated that the identified regions through this methodology indeed play a pivotal role in facilitating class differentiation.
Related papers
- Denoising as Adaptation: Noise-Space Domain Adaptation for Image Restoration [64.84134880709625]
We show that it is possible to perform domain adaptation via the noise-space using diffusion models.
In particular, by leveraging the unique property of how the multi-step denoising process is influenced by auxiliary conditional inputs, we obtain meaningful gradients from noise prediction.
To prevent shortcuts during training, we present useful techniques such as channel shuffling and residual-swapping contrastive learning.
arXiv Detail & Related papers (2024-06-26T17:40:30Z) - Unsupervised Domain Transfer with Conditional Invertible Neural Networks [83.90291882730925]
We propose a domain transfer approach based on conditional invertible neural networks (cINNs)
Our method inherently guarantees cycle consistency through its invertible architecture, and network training can efficiently be conducted with maximum likelihood.
Our method enables the generation of realistic spectral data and outperforms the state of the art on two downstream classification tasks.
arXiv Detail & Related papers (2023-03-17T18:00:27Z) - Towards Robust Image-in-Audio Deep Steganography [14.1081872409308]
This paper extends and enhances an existing image-in-audio deep steganography method by focusing on improving its robustness.
The proposed enhancements include modifications to the loss function, utilization of the Short-Time Fourier Transform (STFT), introduction of redundancy in the encoding process for error correction, and buffering of additional information in the pixel subconvolution operation.
arXiv Detail & Related papers (2023-03-09T03:16:04Z) - Joint Learning of Deep Texture and High-Frequency Features for
Computer-Generated Image Detection [24.098604827919203]
We propose a joint learning strategy with deep texture and high-frequency features for CG image detection.
A semantic segmentation map is generated to guide the affine transformation operation.
The combination of the original image and the high-frequency components of the original and rendered images are fed into a multi-branch neural network equipped with attention mechanisms.
arXiv Detail & Related papers (2022-09-07T17:30:40Z) - SR-GNN: Spatial Relation-aware Graph Neural Network for Fine-Grained
Image Categorization [24.286426387100423]
We propose a method that captures subtle changes by aggregating context-aware features from most relevant image-regions.
Our approach is inspired by the recent advancement in self-attention and graph neural networks (GNNs)
It outperforms the state-of-the-art approaches by a significant margin in recognition accuracy.
arXiv Detail & Related papers (2022-09-05T19:43:15Z) - Hierarchical Similarity Learning for Aliasing Suppression Image
Super-Resolution [64.15915577164894]
A hierarchical image super-resolution network (HSRNet) is proposed to suppress the influence of aliasing.
HSRNet achieves better quantitative and visual performance than other works, and remits the aliasing more effectively.
arXiv Detail & Related papers (2022-06-07T14:55:32Z) - Digging Into Self-Supervised Learning of Feature Descriptors [14.47046413243358]
We propose a set of improvements that combined lead to powerful feature descriptors.
We show that increasing the search space from in-pair to in-batch for hard negative mining brings consistent improvement.
We demonstrate that a combination of synthetic homography transformation, color augmentation, and photorealistic image stylization produces useful representations.
arXiv Detail & Related papers (2021-10-10T12:22:44Z) - Contrastive Rendering for Ultrasound Image Segmentation [59.23915581079123]
The lack of sharp boundaries in US images remains an inherent challenge for segmentation.
We propose a novel and effective framework to improve boundary estimation in US images.
Our proposed method outperforms state-of-the-art methods and has the potential to be used in clinical practice.
arXiv Detail & Related papers (2020-10-10T07:14:03Z) - Pathological Retinal Region Segmentation From OCT Images Using Geometric
Relation Based Augmentation [84.7571086566595]
We propose improvements over previous GAN-based medical image synthesis methods by jointly encoding the intrinsic relationship of geometry and shape.
The proposed method outperforms state-of-the-art segmentation methods on the public RETOUCH dataset having images captured from different acquisition procedures.
arXiv Detail & Related papers (2020-03-31T11:50:43Z) - Towards Interpretable Semantic Segmentation via Gradient-weighted Class
Activation Mapping [71.91734471596432]
We propose SEG-GRAD-CAM, a gradient-based method for interpreting semantic segmentation.
Our method is an extension of the widely-used Grad-CAM method, applied locally to produce heatmaps showing the relevance of individual pixels for semantic segmentation.
arXiv Detail & Related papers (2020-02-26T12:32:40Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.