Smooth Deep Saliency
In this work, we investigate methods to reduce the noise in deep saliency maps coming from convolutional downsampling. Those methods make the investigated models more interpretable for gradient-based saliency maps, computed in hidden layers. We evaluate the faithfulness of those methods using insertion and deletion metrics, finding that saliency maps computed in hidden layers perform better compared to both the input layer and GradCAM. We test our approach on different models trained for image classification on ImageNet1K, and models trained for tumor detection on Camelyon16 and in-house real-world digital pathology scans of stained tissue samples. Our results show that the checkerboard noise in the gradient gets reduced, resulting in smoother and therefore easier to interpret saliency maps.
Code (1)
Tasks
image-classificationImage ClassificationSimilar Papers 제목 키워드 기반
ODSmoothGrad: Generating Saliency Maps for Object Detectors
Techniques for generating saliency maps continue to be used for explainability of deep learning models, with efforts primarily applied to the image classification task. Such techniques, however, can also be applied to ob…
Classificationimage-classificationImage ClassificationObjectCo-Saliency Detection via Mask-Guided Fully Convolutional Networks With Multi-Scale Label Smoothing
In image co-saliency detection problem, one critical issue is how to model the concurrent pattern of the co-salient parts, which appears both within each image and across all the relevant images. In this paper, we propos…
Co-Salient Object DetectionSaliency DetectionSuperpixelsSupersaliency: A Novel Pipeline for Predicting Smooth Pursuit-Based Attention Improves Generalizability of Video Saliency
Predicting attention is a popular topic at the intersection of human and computer vision. However, even though most of the available video saliency data sets and models claim to target human observers' fixations, they fa…
PredictionSaliency PredictionSemantic-driven Generation of Hyperlapse from $360^\circ$ Video
We present a system for converting a fully panoramic ($360^\circ$) video into a normal field-of-view (NFOV) hyperlapse for an optimal viewing experience. Our system exploits visual saliency and semantics to non-uniformly…
Video StabilizationTraining for Trustworthy Saliency Maps: Adversarial Training Meets Feature-Map Smoothing
Gradient-based saliency methods such as Vanilla Gradient (VG) and Integrated Gradients (IG) are widely used to explain image classifiers, yet the resulting maps are often noisy and unstable, limiting their usefulness in …