Deep fair models for complex data: Graphs labeling and explainable face recognition

Explainable AI (XAI) is an active research area to interpret a neural network’s decision by ensuring transparency and trust in the task-specified learned models. Recently, perturbation-based model analysis has shown better interpretation, but backpropagation techniques are still prevailing because of their computational efficiency. In this work, we combine both approaches as a hybrid visual explanation algorithm and propose an efficient interpretation method for convolutional neural networks. Our method adaptively selects the most critical features that mainly contribute towards a prediction to probe the model by finding the activated features. Experimental results show that the proposed method can reduce the execution time up to 30% while enhancing competitive interpretability without compromising the quality of explanation generated.

Ada-Sise: Adaptive Semantic Input Sampling for Efficient Explanation of Convolutional Neural Networks

The evolution of Deep Learning (DL), a subset of machine learning, has made their use very 6 effective in many artificial intelligence (AI) fields. In parallel Virtual Reality is going wide in 7 many applications thanks to the proliferation of cameras in mobile devices and improved 8 processing eﬀiciency. Data visualization in deep learning is a fundamental element for which it 9 can benefit from the advantages offered by the visualization of the VR for the development of 10 the models. In addition, the researchers can widely use the editing of images and videos in the 11 machine learning process to design a convolutional network suitable for image recognition. In 12 this study, we want to demonstrate the usefulness of this approach in collecting data within 13 virtual reality to train and optimize a convolutional neural network used to recognize human 14 activities (HAR).

Neural Network Design using a Virtual Reality Platform 1

Survey of explainable artificial intelligence techniques for biomedical imaging with deep neural networks

The explanation for deep neural networks has drawn extensive attention in the deep learning community over the past few years. In this work, we study the visual saliency, a.k.a. visual explanation, to interpret convolutional neural networks. Compared to iteration based saliency methods, single backward pass based saliency methods benefit from faster speed, and they are widely used in downstream visual tasks. Thus, we focus on single backward pass based methods. However, existing methods in this category struggle to successfully produce fine-grained saliency maps concentrating on specific target classes. That said, producing faithful saliency maps satisfying both target-selectiveness and fine-grainedness using a single backward pass is a challenging problem in the field. To mitigate this problem, we revisit the gradient flow inside the network, and find that the entangled semantics and original weights may disturb the propagation of target-relevant saliency. Inspired by those observations, we propose a novel visual saliency method, termed Target-Selective Gradient Backprop (TSGB), which leverages rectification operations to effectively emphasize target classes and further efficiently propagate the saliency to the image space, thereby generating target-selective and fine-grained saliency maps. The proposed TSGB consists of two components, namely, TSGB-Conv and TSGB-FC, which rectify the gradients for convolutional layers and fully-connected layers, respectively. Extensive qualitative and quantitative experiments on the ImageNet and Pascal VOC datasets show that the proposed method achieves more accurate and reliable results than the other competitive methods. Code is available at https://github.com/123fxdx/CNNvisualizationTSGB. 

TSGB: Target-Selective Gradient Backprop for Probing CNN Visual Saliency

Visualizing the features captured by Convolutional Neural Networks (CNNs) is one of the conventional approaches to interpret the predictions made by these models in numerous image recognition applications. Grad-CAM is a popular solution that provides such a visualization by combining the activation maps obtained from the model. However, the average gradient-based terms deployed in this method underestimates the contribution of the representations discovered by the model to its predictions. Addressing this problem, we introduce a solution to tackle this issue by computing the path integral of the gradient-based terms in Grad-CAM. We conduct a thorough analysis to demonstrate the improvement achieved by our method in measuring the importance of the extracted representations for the CNN’s predictions, which yields to our method’s administration in object localization and model interpretation.

Integrated Grad-Cam: Sensitivity-Aware Visual Explanation of Deep Convolutional Networks Via Integrated Gradient-Based Scoring

As an emerging field in Machine Learning, Explainable AI (XAI) has been offering remarkable performance in interpreting the decisions made by Convolutional Neural Networks (CNNs). To achieve visual explanations for CNNs, methods based on class activation mapping and randomized input sampling have gained great popularity. However, the attribution methods based on these techniques provide lower resolution and blurry explanation maps that limit their explanation power. To circumvent this issue, visualization based on various layers is sought. In this work, we collect visualization maps from multiple layers of the model based on an attribution-based input sampling technique and aggregate them to reach a fine-grained and complete explanation. We also propose a layer selection strategy that applies to the whole family of CNN-based models, based on which our extraction framework is applied to visualize the last layers of each convolutional block of the model. Moreover, we perform an empirical analysis of the efficacy of derived lower-level information to enhance the represented attributions. Comprehensive experiments conducted on shallow and deep models trained on natural and industrial datasets, using both ground-truth and model-truth based evaluation metrics validate our proposed algorithm by meeting or outperforming the state-of-the-art methods in terms of explanation ability and visual quality, demonstrating that our method shows stability regardless of the size of objects or instances to be explained.

Explaining Convolutional Neural Networks through Attribution-Based Input Sampling and Block-Wise Feature Aggregation

Recently, there has been a significant growth in the development of rechargeable battery-powered devices such as electric vehicles, leading to an urgent need for reliable and safe batteries. The remaining useful life (RUL) is a critical health indicator of battery, which is defined as the remaining number of charge and recharge cycles before the state-of-health falls below a user-specified threshold under certain operating settings. Substantially, the RUL can be estimated by adaptive stochastic processes or advanced machine learning techniques. However, the existing approaches either assume over-simplified degradation pattern in accordance with physics laws leading to poor generalizability or act as a black box offering no interpretation. To address these limitations, in this article, we develop a pattern-driven degradation process by integrating a recursive Gaussian distribution with its mean learnt from a gated recurrent unit (GRU) driven degradation pattern to capture degradation fluctuation into the model. Due to the non-Markovian state transitions, a joint-learning sampling-based expectation maximization algorithm was developed to estimate model parameters based on historical observations. Finally, numerical studies using real battery data showed that the proposed method achieves over 3% and 40% higher accuracy in RUL prediction than the GRU and adaptive Wiener process, respectively.

A Pattern-Driven Stochastic Degradation Model for the Prediction of Remaining Useful Life of Rechargeable Batteries

We propose a new transfer learning algorithm between tasks with different dynamics. The proposed algorithm solves an Imitation from Observation problem (IfO) to ground the source environment to the target task before learning an optimal policy in the grounded environment. The learned policy is deployed in the target task without additional training. A particular feature of our algorithm is the employment of multiple rollout policies during training with a goal to ground the environment more globally; hence, it is named as Multi-Policy Grounding (MPG). The quality of final policy is further enhanced via ensemble policy learning. We demonstrate the superiority of the proposed algorithm analytically and numerically. Numerical studies show that the proposed multi-policy approach allows comparable grounding with single policy approach with a fraction of target samples, hence the algorithm is able to maintain the quality of obtained policy even as the number of interactions with the target environment becomes extremely small.

Yeonjeong Jeong

Papers

Integrated Grad-Cam: Sensitivity-Aware Visual Explanation of Deep Convolutional Networks Via Integrated Gradient-Based Scoring

Explaining Convolutional Neural Networks through Attribution-Based Input Sampling and Block-Wise Feature Aggregation

Ada-Sise: Adaptive Semantic Input Sampling for Efficient Explanation of Convolutional Neural Networks

A Pattern-Driven Stochastic Degradation Model for the Prediction of Remaining Useful Life of Rechargeable Batteries

Multi-policy Grounding and Ensemble Policy Learning for Transfer Learning with Dynamics Mismatch