Why are Saliency Maps Noisy? Cause of and Solution to Noisy Saliency Maps
Saliency Map, the gradient of the score function with respect to the input, is the most basic technique for interpreting deep neural network decisions. However, saliency maps are often visually noisy. Although several hypotheses were proposed to account for this phenomenon, there are few works that provide rigorous analyses of noisy saliency maps. In this paper, we firstly propose a new hypothesis that noise may occur in saliency maps when irrelevant features pass through ReLU activation functions. Then, we propose Rectified Gradient, a method that alleviates this problem through layer-wise thresholding during backpropagation. Experiments with neural networks trained on CIFAR-10 and ImageNet showed effectiveness of our method and its superiority to other attribution methods.
Code (2)
Methods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Rectified Gradient: Layer-wise Thresholding for Sharp and Coherent Attribution Maps
Saliency map, or the gradient of the score function with respect to the input, is the most basic means of interpreting deep neural network decisions. However, saliency maps are often visually noisy. Although several hypo…
Learning Noise-Aware Encoder-Decoder from Noisy Labels by Alternating Back-Propagation for Saliency Detection
In this paper, we propose a noise-aware encoder-decoder framework to disentangle a clean saliency predictor from noisy training examples, where the noisy labels are generated by unsupervised handcrafted feature-based met…
DecoderSaliency DetectionDeep Unsupervised Saliency Detection: A Multiple Noisy Labeling Perspective
The success of current deep saliency detection methods heavily depends on the availability of large-scale supervision in the form of per-pixel labeling. Such supervision, while labor-intensive and not always possible, te…
BenchmarkingSaliency DetectionSaliency PredictionUnsupervised Saliency DetectionDSAL-GAN: Denoising based Saliency Prediction with Generative Adversarial Networks
Synthesizing high quality saliency maps from noisy images is a challenging problem in computer vision and has many practical applications. Samples generated by existing techniques for saliency detection cannot handle the…
DenoisingGenerative Adversarial Networkobject-detectionObject Detection+5Improving Deep Learning Interpretability by Saliency Guided Training
Saliency methods have been widely used to highlight important input features in model predictions. Most existing methods use backpropagation on a modified gradient function to generate saliency maps. Thus, noisy gradient…
Deep LearningTime SeriesTime Series Analysis