Relevant bibliographies by topics / Class Activation Maps(CAM)

Contents

  1. Journal articles
  2. Dissertations / Theses
  3. Book chapters
  4. Conference papers

Academic literature on the topic 'Class Activation Maps(CAM)'

Author: Grafiati
Published: 7 June 2025
Last updated: 2 August 2025

Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles

Select a source type:

Consult the lists of relevant articles, books, theses, conference reports, and other scholarly sources on the topic 'Class Activation Maps(CAM).'

Next to every source in the list of references, there is an 'Add to bibliography' button. Press on it, and we will generate automatically the bibliographic reference to the chosen work in the citation style you need: APA, MLA, Harvard, Chicago, Vancouver, etc.

You can also download the full text of the academic publication as pdf and read online its abstract whenever available in the metadata.

Journal articles on the topic "Class Activation Maps(CAM)"

1

Debasis Chaudhuri, Akash Samanta, Aniket Kumar Singh, and Manish Pratap Singh. "Pixel Ablation-CAM: A New Paradigm in CNN Interpretability for Feature Map Visual Explanations." Defence Science Journal 75, no. 2 (2025): 188–98. https://doi.org/10.14429/dsj.20444.

Full text
Abstract:
Many cutting-edge computer vision systems now rely heavily on convolutional neural networks, or CNNs. However, conventional interpretation techniques frequently concentrate on 2D feature maps, ignoring the intricate contributions of individual pixels. This work aims to produce “visual explanations” that improve the explainability and transparency of decisions made by various CNN-based algorithms. We provide Pixel Ablation-CAM, a new method that builds on the ideas of Ablation-CAM by using pixel-wise ablation, which enables a finer-grained comprehension of model choices. With this method, activ
APA, Harvard, Vancouver, ISO, and other styles
2

k, k., k. k, and k. k. "Integration of Multi-scale CAM and Attention for Weakly Supervised Defects Localization on Surface Defective Apple." Korean Institute of Smart Media 12, no. 9 (2023): 45–59. http://dx.doi.org/10.30693/smj.2023.12.9.45.

Full text
Abstract:
Weakly supervised object localization (WSOL) is a task of localizing an object in an image using only image-level labels. Previous studies have followed the conventional class activation mapping (CAM) pipeline. However, we reveal the current CAM approach suffers from problems which cause original CAM could not capture the complete defects features. This work utilizes a convolutional neural network (CNN) pretrained on image-level labels to generate class activation maps in a multi-scale manner to highlight discriminative regions. Additionally, a vision transformer (ViT) pretrained was treated t
APA, Harvard, Vancouver, ISO, and other styles
3

Kusunose, Shoya, Yuki Shinomiya, Takashi Ushiwaka, Nagamasa Maeda, and Yukinobu Hoshino. "Enhancement of the Individual Selectness Using Local Spatial Weighting for Immune Cells." Journal of Advanced Computational Intelligence and Intelligent Informatics 26, no. 2 (2022): 178–87. http://dx.doi.org/10.20965/jaciii.2022.p0178.

Full text
Abstract:
This paper focuses on the analysis of the activity of immune cells for supporting medical workers. Recognition frequency space selects a region including neighboring multiple cells as a single cell is one of the major issues in activity analysis of immune cells. This study focuses on the locality of immune cell features and uses a high-velocity weighting method for the analysis while the Gaussian distribution is used in the literature. The analysis was conducted for a few well-known methods such as final feature maps, class activation mapping (CAM), gradient weighted class activation mapping (
APA, Harvard, Vancouver, ISO, and other styles
4

Kaczmarek, Emily, Olivier X. Miguel, Alexa C. Bowie, et al. "CAManim: Animating end-to-end network activation maps." PLOS ONE 19, no. 6 (2024): e0296985. http://dx.doi.org/10.1371/journal.pone.0296985.

Full text
Abstract:
Deep neural networks have been widely adopted in numerous domains due to their high performance and accessibility to developers and application-specific end-users. Fundamental to image-based applications is the development of Convolutional Neural Networks (CNNs), which possess the ability to automatically extract features from data. However, comprehending these complex models and their learned representations, which typically comprise millions of parameters and numerous layers, remains a challenge for both developers and end-users. This challenge arises due to the absence of interpretable and
APA, Harvard, Vancouver, ISO, and other styles
5

Fu, Jia, Guotai Wang, Tao Lu, et al. "UM-CAM: Uncertainty-weighted multi-resolution class activation maps for weakly-supervised segmentation." Pattern Recognition 160 (April 2025): 111204. http://dx.doi.org/10.1016/j.patcog.2024.111204.

Full text
APA, Harvard, Vancouver, ISO, and other styles
6

Yang, Zhiwei, Yucong Meng, Kexue Fu, Shuo Wang, and Zhijian Song. "MoRe: Class Patch Attention Needs Regularization for Weakly Supervised Semantic Segmentation." Proceedings of the AAAI Conference on Artificial Intelligence 39, no. 9 (2025): 9400–9408. https://doi.org/10.1609/aaai.v39i9.33018.

Full text
Abstract:
Weakly Supervised Semantic Segmentation (WSSS) with image-level labels typically uses Class Activation Maps (CAM) to achieve dense predictions. Recently, Vision Transformer (ViT) has provided an alternative to generate localization maps from class-patch attention. However, due to insufficient constraints on modeling such attention, we observe that the Localization Attention Maps (LAM) often struggle with the artifact issue, i.e., patch regions with minimal semantic relevance are falsely activated by class tokens. In this work, we propose MoRe to address this issue and further explore the poten
APA, Harvard, Vancouver, ISO, and other styles
7

Luo, Wenfeng, and Meng Yang. "Learning Saliency-Free Model with Generic Features for Weakly-Supervised Semantic Segmentation." Proceedings of the AAAI Conference on Artificial Intelligence 34, no. 07 (2020): 11717–24. http://dx.doi.org/10.1609/aaai.v34i07.6842.

Full text
Abstract:
Current weakly-supervised semantic segmentation methods often estimate initial supervision from class activation maps (CAM), which produce sparse discriminative object seeds and rely on image saliency to provide background cues when only class labels are used. To eliminate the demand of extra data for training saliency detector, we propose to discover class pattern inherent in the lower layer convolution features, which are scarcely explored as in previous CAM methods. Specifically, we first project the convolution features into a low-dimension space and then decide on a decision boundary to g
APA, Harvard, Vancouver, ISO, and other styles
8

Loaiza-Arias, Marcos, Andrés Marino Álvarez-Meza, David Cárdenas-Peña, Álvaro Ángel Orozco-Gutierrez, and German Castellanos-Dominguez. "Multimodal Explainability Using Class Activation Maps and Canonical Correlation for MI-EEG Deep Learning Classification." Applied Sciences 14, no. 23 (2024): 11208. https://doi.org/10.3390/app142311208.

Full text
Abstract:
Brain–computer interfaces (BCIs) are essential in advancing medical diagnosis and treatment by providing non-invasive tools to assess neurological states. Among these, motor imagery (MI), in which patients mentally simulate motor tasks without physical movement, has proven to be an effective paradigm for diagnosing and monitoring neurological conditions. Electroencephalography (EEG) is widely used for MI data collection due to its high temporal resolution, cost-effectiveness, and portability. However, EEG signals can be noisy from a number of sources, including physiological artifacts and elec
APA, Harvard, Vancouver, ISO, and other styles
9

Fahim, Masud An Nur Islam, Nazmus Saqib, Shafkat Khan Siam, and Ho Yub Jung. "Rethinking Gradient Weight’s Influence over Saliency Map Estimation." Sensors 22, no. 17 (2022): 6516. http://dx.doi.org/10.3390/s22176516.

Full text
Abstract:
Class activation map (CAM) helps to formulate saliency maps that aid in interpreting the deep neural network’s prediction. Gradient-based methods are generally faster than other branches of vision interpretability and independent of human guidance. The performance of CAM-like studies depends on the governing model’s layer response and the influences of the gradients. Typical gradient-oriented CAM studies rely on weighted aggregation for saliency map estimation by projecting the gradient maps into single-weight values, which may lead to an over-generalized saliency map. To address this issue, w
APA, Harvard, Vancouver, ISO, and other styles
10

Si, Nianwen, Wenlin Zhang, Dan Qu, Xiangyang Luo, Heyu Chang, and Tong Niu. "Spatial-Channel Attention-Based Class Activation Mapping for Interpreting CNN-Based Image Classification Models." Security and Communication Networks 2021 (May 31, 2021): 1–13. http://dx.doi.org/10.1155/2021/6682293.

Full text
Abstract:
Convolutional neural network (CNN) has been applied widely in various fields. However, it is always hindered by the unexplainable characteristics. Users cannot know why a CNN-based model produces certain recognition results, which is a vulnerability of CNN from the security perspective. To alleviate this problem, in this study, the three existing feature visualization methods of CNN are analyzed in detail firstly, and a unified visualization framework for interpreting the recognition results of CNN is presented. Here, class activation weight (CAW) is considered as the most important factor in
APA, Harvard, Vancouver, ISO, and other styles
More sources

Dissertations / Theses on the topic "Class Activation Maps(CAM)"

1

Buratti, Luca. "Visualisation of Convolutional Neural Networks." Master's thesis, Alma Mater Studiorum - Università di Bologna, 2018.

Find full text
Abstract:
Le Reti Neurali, e in particolare le Reti Neurali Convoluzionali, hanno recentemente dimostrato risultati straordinari in vari campi. Purtroppo, comunque, non vi è ancora una chiara comprensione del perchè queste architetture funzionino così bene e soprattutto è difficile spiegare il comportamento nel caso di fallimenti. Questa mancanza di chiarezza è quello che separa questi modelli dall’essere applicati in scenari concreti e critici della vita reale, come la sanità o le auto a guida autonoma. Per questa ragione, durante gli ultimi anni sono stati portati avanti diversi studi in modo tale d
APA, Harvard, Vancouver, ISO, and other styles
2

Baasch, Gaby. "Identification of thermal building properties using gray box and deep learning methods." Thesis, 2020. http://hdl.handle.net/1828/12585.

Full text
Abstract:
Enterprising technologies and policies that focus on energy reduction in buildings are paramount to achieving global carbon emissions targets. Energy retrofits, building stock modelling, heating, ventilation, and air conditioning (HVAC) upgrades and demand side management all present high leverage opportunities in this regard. Advances in computing, data science and machine learning can be leveraged to enhance these methods and thus to expedite energy reduction in buildings but challenges such as lack of data, limited model generalizability and reliability and un-reproducible studies have resu
APA, Harvard, Vancouver, ISO, and other styles

Book chapters on the topic "Class Activation Maps(CAM)"

1

Fu, Jia, Tao Lu, Shaoting Zhang, and Guotai Wang. "UM-CAM: Uncertainty-weighted Multi-resolution Class Activation Maps for Weakly-supervised Fetal Brain Segmentation." In Lecture Notes in Computer Science. Springer Nature Switzerland, 2023. http://dx.doi.org/10.1007/978-3-031-43990-2_30.

Full text
APA, Harvard, Vancouver, ISO, and other styles
2

Ojok, Amos, Honey Abdurahman, Rose Nakibuule, Sunniva Roligheten, and Ggaliwango Marvin. "Interpretable Class Activation Maps for Vision-Based Deforestation Detection." In Lecture Notes in Networks and Systems. Springer Nature Singapore, 2025. https://doi.org/10.1007/978-981-96-2700-4_44.

Full text
APA, Harvard, Vancouver, ISO, and other styles
3

Thota, Gokaramaiah, K. Nagaraju, and Sathya Babu Korra. "SVD-Grad-CAM: Singular Value Decomposition filtered Gradient Weighted Class Activation Map." In Lecture Notes in Computer Science. Springer Nature Switzerland, 2024. https://doi.org/10.1007/978-3-031-78198-8_7.

Full text
APA, Harvard, Vancouver, ISO, and other styles
4

Joshua, Eali Stephen Neal, Midhun Chakkravarthy, and Debnath Bhattacharyya. "Lung Cancer Detection Using Improvised Grad-Cam++ With 3D CNN Class Activation." In Smart Technologies in Data Science and Communication. Springer Singapore, 2021. http://dx.doi.org/10.1007/978-981-16-1773-7_5.

Full text
APA, Harvard, Vancouver, ISO, and other styles
5

Didry, Yoanne, Xavier Mestdagh, and Thomas Tamisier. "Visualizing Features on Classified Fauna Images Using Class Activation Maps." In Lecture Notes in Computer Science. Springer International Publishing, 2020. http://dx.doi.org/10.1007/978-3-030-60816-3_38.

Full text
APA, Harvard, Vancouver, ISO, and other styles
6

Dai, Wenzhang, and Le Sun. "Weakly Supervised Waste Classification with Adaptive Loss and Enhanced Class Activation Maps." In Lecture Notes in Computer Science. Springer Nature Singapore, 2025. https://doi.org/10.1007/978-981-96-4566-4_24.

Full text
APA, Harvard, Vancouver, ISO, and other styles
7

Cherepanov, Igor, David Sessler, Alex Ulmer, Hendrik Lücke-Tieke, and Jörn Kohlhammer. "Towards the Visualization of Aggregated Class Activation Maps to Analyse the Global Contribution of Class Features." In Communications in Computer and Information Science. Springer Nature Switzerland, 2023. http://dx.doi.org/10.1007/978-3-031-44067-0_1.

Full text
APA, Harvard, Vancouver, ISO, and other styles
8

Borgli, Hanna, Håkon Kvale Stensland, and Pål Halvorsen. "Better Image Segmentation with Classification: Guiding Zero-Shot Models Using Class Activation Maps." In Lecture Notes in Computer Science. Springer Nature Singapore, 2025. https://doi.org/10.1007/978-981-96-2074-6_10.

Full text
APA, Harvard, Vancouver, ISO, and other styles
9

Ellis, Joel J., Thomas G. Valencia, Hong Zeng, L. Don Roberts, Rebecca A. Deaton, and Stephen R. Grant. "CaM kinase IIδC phosphorylation of 14–3-3β in vascular smooth muscle cells: Activation of class II HDAC repression." In Cardiac Cell Biology. Springer US, 2003. http://dx.doi.org/10.1007/978-1-4757-4712-6_20.

Full text
APA, Harvard, Vancouver, ISO, and other styles
10

Małka, Anna, Izabela Laskowicz, and Dariusz Grabowski. "The Accuracy of Landslide Susceptibility Mapping in Young Glacial River Valleys." In Progress in Landslide Research and Technology. Springer Nature Switzerland, 2025. https://doi.org/10.1007/978-3-031-72736-8_13.

Full text
Abstract:
AbstractMany aspects affect the accuracy of the geographical information system- and statistically-based susceptibility maps. These aspects can be divided into four categories related to: (α) study area, (β) scale, (γ) input data, and (δ) methods, used for susceptibility calculation, landslide representation and map visualisation. Most of these aspects have an impact on the others and each of them is very complex. Due to the complexity of this issue, the article is limited to two aspects, i.e. scale and one of the crucial causal factors, namely geology. The selection of the research area is a
APA, Harvard, Vancouver, ISO, and other styles

Conference papers on the topic "Class Activation Maps(CAM)"

1

yang, shuwen, Hangcheng Dong, Bingguo Liu, Guodong Liu, and Xingyu Chen. "LayerScore-CAM: hierarchical score-weighted class activation maps for defect segmentation." In Seventeenth International Conference on Digital Image Processing (ICDIP 2025), edited by Xudong Jiang, Jindong Tian, Ting-Chung Poon, and Zhaohui Wang. SPIE, 2025. https://doi.org/10.1117/12.3073222.

Full text
APA, Harvard, Vancouver, ISO, and other styles
2

Li, Xuewei, Yujie Diao, Mei Yu, Chenhan Wang, Jie Gao, and Ruiguo Yu. "Area Intervention for Enhancing Class Activation Maps in Weakly Supervised Semantic Segmentation." In 2024 IEEE International Conference on Multimedia and Expo (ICME). IEEE, 2024. http://dx.doi.org/10.1109/icme57554.2024.10687454.

Full text
APA, Harvard, Vancouver, ISO, and other styles
3

Machida, Kentaro, Soma Asuka, Tomomi Osaka, Fumikazu Watanabe, and Hironori Nakajo. "Matthiola incana classification using CNN and class activation maps for model understanding." In 2024 Twelfth International Symposium on Computing and Networking Workshops (CANDARW). IEEE, 2024. https://doi.org/10.1109/candarw64572.2024.00029.

Full text
APA, Harvard, Vancouver, ISO, and other styles
4

Zanghieri, Marcello, Pierangelo M. Rapa, Mattia Orlandi, et al. "Wearable High-Density sEMG Processing with Class Activation Maps with an Embedded Temporal Convolutional Network." In 2024 IEEE Biomedical Circuits and Systems Conference (BioCAS). IEEE, 2024. https://doi.org/10.1109/biocas61083.2024.10798295.

Full text
APA, Harvard, Vancouver, ISO, and other styles
5

Ahammed, Fahad, Omar Faruq Shikdar, B. M. Shahria Alam, Sabrina Jahan, Golam Kibria, and Nawab Yousuf Ali. "Classifying Nutritional Deficiencies in Coffee Leaf Using Transfer Learning and Gradient-Weighted Class Activation Mapping (Grad-CAM) Visualization." In 2025 International Conference on Computing and Communication Technologies (ICCCT). IEEE, 2025. https://doi.org/10.1109/iccct63501.2025.11019090.

Full text
APA, Harvard, Vancouver, ISO, and other styles
6

Shikdar, Omar Faruq, Ruba Sazeda, Sujana Islam, Ashraful Islam, Tanzia Haque, and Arifa Sultana Mily. "Detecting Polycystic Ovary Syndrome with Convolutional Neural Networks: Enhancements through Adversarial Training and Gradient-Weighted Class Activation Mapping (Grad-CAM)." In 2024 IEEE 3rd International Conference on Robotics, Automation, Artificial-Intelligence and Internet-of-Things (RAAICON). IEEE, 2024. https://doi.org/10.1109/raaicon64172.2024.10928518.

Full text
APA, Harvard, Vancouver, ISO, and other styles
7

Patro, Badri, Mayank Lunayach, Shivansh Patel, and Vinay Namboodiri. "U-CAM: Visual Explanation Using Uncertainty Based Class Activation Maps." In 2019 IEEE/CVF International Conference on Computer Vision (ICCV). IEEE, 2019. http://dx.doi.org/10.1109/iccv.2019.00754.

Full text
APA, Harvard, Vancouver, ISO, and other styles
8

Belharbi, Soufiane, Aydin Sarraf, Marco Pedersoli, Ismail Ben Ayed, Luke McCaffrey, and Eric Granger. "F-CAM: Full Resolution Class Activation Maps via Guided Parametric Upscaling." In 2022 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV). IEEE, 2022. http://dx.doi.org/10.1109/wacv51458.2022.00378.

Full text
APA, Harvard, Vancouver, ISO, and other styles
9

Lee, Sangkyun, and Sungmin Han. "Libra-CAM: An Activation-Based Attribution Based on the Linear Approximation of Deep Neural Nets and Threshold Calibration." In Thirty-First International Joint Conference on Artificial Intelligence {IJCAI-22}. International Joint Conferences on Artificial Intelligence Organization, 2022. http://dx.doi.org/10.24963/ijcai.2022/442.

Full text
Abstract:
Universal application of AI has increased the need to explain why an AI model makes a specific decision in a human-understandable form. Among many related works, the class activation map (CAM)-based methods have been successful recently, creating input attribution based on the weighted sum of activation maps in convolutional neural networks. However, existing methods use channel-wise importance weights with specific architectural assumptions, relying on arbitrarily chosen attribution threshold values in their quality assessment: we think these can degrade the quality of attribution. In this pa
APA, Harvard, Vancouver, ISO, and other styles
10

Vasu, Bhavan, Faiz Ur Rahman, and Andreas Savakis. "Aerial-CAM: Salient Structures and Textures in Network Class Activation Maps of Aerial Imagery." In 2018 IEEE 13th Image, Video, and Multidimensional Signal Processing Workshop (IVMSP). IEEE, 2018. http://dx.doi.org/10.1109/ivmspw.2018.8448567.

Full text
APA, Harvard, Vancouver, ISO, and other styles
You might also be interested in the extended bibliographies on the topic 'Class Activation Maps(CAM)' for particular source types:
Journal articles
We offer discounts on all premium plans for authors whose works are included in thematic literature selections. Contact us to get a unique promo code!

To the bibliography