Ablation-CAM: Visual Explanations for Deep Convolutional Network via Gradient-free Localization

Desai, Saurabh Ravindra; Ramaswamy, Harish G.

doi:10.1109/wacv45572.2020.9093360

Cited by 203 publications

(180 citation statements)

References 7 publications

Supporting

Mentioning

179

Contrasting

Unclassified

Order By: Relevance

“…Each CNN-based method has its own advantages according to problem definitions and data characteristics. In the various such methods, ResNet [10] has been proven to be one of the most representative deep learning networks. Furthermore, following the architecture of this network, modifications to the architecture of the existing CNN-based methods have been made by utilizing the idea of residual blocks to achieve deeper networks and more efficient learning [11].…”

Section: Development Of the Algorithmmentioning

confidence: 99%

Application of deep learning algorithm to detect and visualize vertebral fractures on plain frontal radiographs

et al. 2021

View full text Add to dashboard Cite

Background Identification of vertebral fractures (VFs) is critical for effective secondary fracture prevention owing to their association with the increasing risks of future fractures. Plain abdominal frontal radiographs (PARs) are a common investigation method performed for a variety of clinical indications and provide an ideal platform for the opportunistic identification of VF. This study uses a deep convolutional neural network (DCNN) to identify the feasibility for the screening, detection, and localization of VFs using PARs. Methods A DCNN was pretrained using ImageNet and retrained with 1306 images from the PARs database obtained between August 2015 and December 2018. The accuracy, sensitivity, specificity, and area under the receiver operating characteristic curve (AUC) were evaluated. The visualization algorithm gradient-weighted class activation mapping (Grad-CAM) was used for model interpretation. Results Only 46.6% (204/438) of the VFs were diagnosed in the original PARs reports. The algorithm achieved 73.59% accuracy, 73.81% sensitivity, 73.02% specificity, and an AUC of 0.72 in the VF identification. Conclusion Computer driven solutions integrated with the DCNN have the potential to identify VFs with good accuracy when used opportunistically on PARs taken for a variety of clinical purposes. The proposed model can help clinicians become more efficient and economical in the current clinical pathway of fragile fracture treatment.

show abstract

Section: Development Of the Algorithmmentioning

confidence: 99%

Application of deep learning algorithm to detect and visualize vertebral fractures on plain frontal radiographs

et al. 2021

View full text Add to dashboard Cite

show abstract

“…The contribution weight of the channel is then evaluated by the change on the feature map it has made by masking the input. In addition to these CAM-based methods, a lot of other variations have been proposed recently such as Smooth Grad-CAM++ [10], SS-CAM [11], Layer-CAM [12], and Ablation-CAM [13]. Besides, there are many other CAMbased methods in which the saliency maps are generated for specific tasks (e.g., label-free localization [14], high-quality proposal [15], visualization of deep reinforcement learning [16], localization comparison [17], scaling method comparison [18], and performance evaluation by experts [19,20]).…”

Section: A Cam-based Methodsmentioning

confidence: 99%

“…To measure the performance, we have employed two widely adopted metrics of Average Increase (AI) and Average Drop (AD) [3,10,11,13,33] as follows…”

Section: A Setupmentioning

confidence: 99%

Conceptor Learning for Class Activation Mapping

Qian¹,

Yang²,

Zhang³

et al. 2022

Preprint

View full text Add to dashboard Cite

Class Activation Mapping (CAM) has been widely adopted to generate saliency maps which provides visual explanations for deep neural networks (DNNs). The saliency maps are conventionally generated by fusing the channels of the target feature map using a weighted average scheme. It is a weak model for the inter-channel relation, in the sense that it only models the relation among channels in a contrastive way (i.e., channels that play key roles in the prediction are given higher weights for them to stand out in the fusion). The collaborative relation, which makes the channels work together to provide cross reference, has been ignored. Furthermore, the model has neglected the intra-channel relation thoroughly. In this paper, we address this problem by introducing Conceptor learning into CAM generation. Conceptor leaning has been originally proposed to model the patterns of state changes in recurrent neural networks (RNNs). By relaxing the dependency of Conceptor learning to RNNs, we make Conceptor-CAM not only generalizable to more DNN architectures but also able to learn both the inter-and intra-channel relations for better saliency map generation. Moreover, we have enabled the use of Boolean operations to combine the positive and pseudo-negative evidences, which has made the CAM inference more robust and comprehensive. The effectiveness of Conceptor-CAM has been validated with both formal verifications and experiments on the dataset of the largest scale in literature. The experimental results show that Conceptor-CAM is compatible with and can bring significant improvement to all well recognized CAM-based methods, and has outperformed the state-of-the-art methods by 43.14% ∼ 72.79% (88.39% ∼ 168.15%) on ILSVRC2012 in Average Increase (Drop), 15.42% ∼ 42.55% (47.09% ∼ 372.09%) on VOC, and 17.43% ∼ 31.32% (47.54% ∼ 206.45%) on COCO, respectively.

show abstract

“…to assess which areas are more informative for the estimation of the hazard index. In particular, CAM methods have been recently shown to be successful for interpretability tasks in several fields [44][45][46][47] (19) in our image repository segmentationthose that are common and relevant in driver-perspective scenes (e.g. "car", "road", "sidewalk", "person", "traffic light", etc.…”

Section: Hazard Index Interpretabilitymentioning

confidence: 99%

Explainable, automated urban interventions to improve pedestrian and vehicle safety

Bustos

Rhoads

Solé-Ribalta

et al. 2021

Transportation Research Part C: Emerging Technologies

View full text Add to dashboard Cite

At the moment, urban mobility research and governmental initiatives are mostly focused on motor-related issues, e.g. the problems of congestion and pollution. And yet, we can not disregard the most vulnerable elements in the urban landscape: pedestrians, exposed to higher risks than other road users. Indeed, safe, accessible, and sustainable transport systems in cities are a core target of the UN's 2030 Agenda. Thus, there is an opportunity to apply advanced computational tools to the problem of traffic safety, in regards especially to pedestrians, who have been often overlooked in the past. This paper combines public data sources, large-scale street imagery and computer vision techniques to approach pedestrian and vehicle safety with an automated, relatively simple, and universally-applicable data-processing scheme. The steps involved in this pipeline include the adaptation and training of a Residual Convolutional Neural Network to determine a hazard index for each given urban scene, as well as an interpretability analysis based on image segmentation and class activation mapping on those same images. Combined, the outcome of this computational approach is a fine-grained map of hazard levels across a city, and an heuristic to identify interventions that might simultaneously improve pedestrian and vehicle safety. The proposed frame

show abstract

Ablation-CAM: Visual Explanations for Deep Convolutional Network via Gradient-free Localization

Cited by 203 publications

References 7 publications

Application of deep learning algorithm to detect and visualize vertebral fractures on plain frontal radiographs

Application of deep learning algorithm to detect and visualize vertebral fractures on plain frontal radiographs

Conceptor Learning for Class Activation Mapping

Explainable, automated urban interventions to improve pedestrian and vehicle safety

Contact Info

Product

Resources

About