English
Related papers

Related papers: Canonical Saliency Maps: Decoding Deep Face Models

200 papers

Saliency methods can make deep neural network predictions more interpretable by identifying a set of critical features in an input sample, such as pixels that contribute most strongly to a prediction made by an image classifier.…

Machine Learning · Computer Science 2021-06-15 Yang Lu , Wenbo Guo , Xinyu Xing , William Stafford Noble

Deep convolutional neural networks (DCNNs) have become the state-of-the-art computational models of biological object recognition. Their remarkable success has helped vision science break new ground and recent efforts have started to…

Computer Vision and Pattern Recognition · Computer Science 2023-08-22 Leonard E. van Dyck , Walter R. Gruber

Race classification is a long-standing challenge in the field of face image analysis. The investigation of salient facial features is an important task to avoid processing all face parts. Face segmentation strongly benefits several face…

Computer Vision and Pattern Recognition · Computer Science 2021-04-07 Khalil Khan , Jehad Ali , Irfan Uddin , Sahib Khan , Byeong-hee Roh

This paper investigates the role of saliency to improve the classification accuracy of a Convolutional Neural Network (CNN) for the case when scarce training data is available. Our approach consists in adding a saliency branch to an…

Computer Vision and Pattern Recognition · Computer Science 2019-05-07 Carola Figueroa Flores , Abel Gonzalez-García , Joost van de Weijer , Bogdan Raducanu

Saliency methods provide post-hoc model interpretation by attributing input features to the model outputs. Current methods mainly achieve this using a single input sample, thereby failing to answer input-independent inquiries about the…

Computer Vision and Pattern Recognition · Computer Science 2023-04-03 Naveed Akhtar , Mohammad A. A. K. Jalwana

In mission-critical domains such as law enforcement and medical diagnosis, the ability to explain and interpret the outputs of deep learning models is crucial for ensuring user trust and supporting informed decision-making. Despite…

Computer Vision and Pattern Recognition · Computer Science 2024-11-07 Bharat Chandra Yalavarthi , Nalini Ratha

As prior knowledge of objects or object features helps us make relations for similar objects on attentional tasks, pre-trained deep convolutional neural networks (CNNs) can be used to detect salient objects on images regardless of the…

Computer Vision and Pattern Recognition · Computer Science 2017-06-22 Nevrez Imamoglu , Chi Zhang , Wataru Shimoda , Yuming Fang , Boxin Shi

Conventional saliency maps highlight input features to which neural network predictions are highly sensitive. We take a different approach to saliency, in which we identify and analyze the network parameters, rather than inputs, which are…

Computer Vision and Pattern Recognition · Computer Science 2022-10-11 Roman Levin , Manli Shu , Eitan Borgnia , Furong Huang , Micah Goldblum , Tom Goldstein

Saliency computation models aim to imitate the attention mechanism in the human visual system. The application of deep neural networks for saliency prediction has led to a drastic improvement over the last few years. However, deep models…

Computer Vision and Pattern Recognition · Computer Science 2024-03-26 Saman Zabihi , Hamed Rezazadegan Tavakoli , Ali Borji

Deep neural networks, especially convolutional deep neural networks, are state-of-the-art methods to classify, segment or even generate images, movies, or sounds. However, these methods lack of a good semantic understanding of what happens…

Computer Vision and Pattern Recognition · Computer Science 2021-08-27 Jens Bayer , David Münch , Michael Arens

Face recognition algorithms based on deep convolutional neural networks (DCNNs) have made progress on the task of recognizing faces in unconstrained viewing conditions. These networks operate with compact feature-based face representations…

Computer Vision and Pattern Recognition · Computer Science 2020-02-18 Connor J. Parde , Carlos Castillo , Matthew Q. Hill , Y. Ivette Colon , Swami Sankaranarayanan , Jun-Cheng Chen , Alice J. O'Toole

Currently available methods for extracting saliency maps identify parts of the input which are the most important to a specific fixed classifier. We show that this strong dependence on a given classifier hinders their performance. To…

Machine Learning · Computer Science 2020-07-21 Konrad Zolna , Krzysztof J. Geras , Kyunghyun Cho

Backpropagation image saliency aims at explaining model predictions by estimating model-centric importance of individual pixels in the input. However, class-insensitivity of the earlier layers in a network only allows saliency computation…

Computer Vision and Pattern Recognition · Computer Science 2021-06-22 Mohammad A. A. K. Jalwana , Naveed Akhtar , Mohammed Bennamoun , Ajmal Mian

Interpretation of deep learning remains a very challenging problem. Although the Class Activation Map (CAM) is widely used to interpret deep model predictions by highlighting object location, it fails to provide insight into the salient…

Computer Vision and Pattern Recognition · Computer Science 2024-05-30 Yuguang Yang , Runtang Guo , Sheng Wu , Yimi Wang , Juan Zhang , Xuan Gong , Baochang Zhang

3D point-cloud recognition with PointNet and its variants has received remarkable progress. A missing ingredient, however, is the ability to automatically evaluate point-wise importance w.r.t.\! classification performance, which is usually…

Computer Vision and Pattern Recognition · Computer Science 2019-09-16 Tianhang Zheng , Changyou Chen , Junsong Yuan , Bo Li , Kui Ren

Real-world face detection and alignment demand an advanced discriminative model to address challenges by pose, lighting and expression. Illuminated by the deep learning algorithm, some convolutional neural networks based face detection and…

Computer Vision and Pattern Recognition · Computer Science 2017-08-01 Weilin Cong , Sanyuan Zhao , Hui Tian , Jianbing Shen

This paper proposes a novel saliency detection method by developing a deeply-supervised recurrent convolutional neural network (DSRCNN), which performs a full image-to-image saliency prediction. For saliency detection, the local, global,…

Computer Vision and Pattern Recognition · Computer Science 2016-08-19 Youbao Tang , Xiangqian Wu , Wei Bu

Predicting salient regions in natural images requires the detection of objects that are present in a scene. To develop robust representations for this challenging task, high-level visual features at multiple spatial scales must be extracted…

Computer Vision and Pattern Recognition · Computer Science 2024-04-08 Alexander Kroner , Mario Senden , Kurt Driessens , Rainer Goebel

This paper addresses the visualisation of image classification models, learnt using deep Convolutional Networks (ConvNets). We consider two visualisation techniques, based on computing the gradient of the class score with respect to the…

Computer Vision and Pattern Recognition · Computer Science 2014-04-22 Karen Simonyan , Andrea Vedaldi , Andrew Zisserman

Feature maps in deep neural network generally contain different semantics. Existing methods often omit their characteristics that may lead to sub-optimal results. In this paper, we propose a novel end-to-end deep saliency network which…

Computer Vision and Pattern Recognition · Computer Science 2018-08-07 Fengdong Sun , Wenhui Li , Yuanyuan Guan