Evaluating the Use of Reconstruction Error for Novelty Localization
The pixelwise reconstruction error of deep autoencoders is often utilized for image novelty detection and localization under the assumption that pixels with high error indicate which parts of the input image are unfamiliar and therefore likely to be novel. This assumed correlation between pixels with high reconstruction error and novel regions of input images has not been verified and may limit the accuracy of these methods. In this paper we utilize saliency maps to evaluate whether this correlation exists. Saliency maps reveal directly how much a change in each input pixel would affect reconstruction loss, while each pixel's reconstruction error may be attributed to many input pixels when layers are fully connected. We compare saliency maps to reconstruction error maps via qualitative visualizations as well as quantitative correspondence between the top K elements of the maps for both novel and normal images. Our results indicate that reconstruction error maps do not closely correlate with the importance of pixels in the input images, making them insufficient for novelty localization.
Code (0)
등록된 구현이 없습니다.
Tasks
Novelty DetectionSimilar Papers 제목 키워드 기반
Beyond the Known: Adversarial Autoencoders in Novelty Detection
In novelty detection, the goal is to decide if a new data point should be categorized as an inlier or an outlier, given a training dataset that primarily captures the inlier distribution. Recent approaches typically use …
DecoderNovelty DetectionOne-class classifierDiscriminative Multi-level Reconstruction under Compact Latent Space for One-Class Novelty Detection
In one-class novelty detection, a model learns solely on the in-class data to single out out-class instances. Autoencoder (AE) variants aim to compactly model the in-class data to reconstruct it exclusively, thus differe…
Novelty DetectionImproving Novelty Detection using the Reconstructions of Nearest Neighbours
We show that using nearest neighbours in the latent space of autoencoders (AE) significantly improves performance of semi-supervised novelty detection in both single and multi-class contexts. Autoencoding methods detect …
Anomaly DetectionData AugmentationNovelty DetectionOAAE: Adversarial Autoencoders for Novelty Detection in Multi-modal Normality Case via Orthogonalized Latent Space
Novelty detection using deep generative models such as autoencoder, generative adversarial networks mostly takes image reconstruction error as novelty score function. However, image data, high dimensional as it is, conta…
Image ReconstructionNovelty DetectionConnective Reconstruction-based Novelty Detection
Detection of out-of-distribution samples is one of the critical tasks for real-world applications of computer vision. The advancement of deep learning has enabled us to analyze real-world data which contain unexplained s…
Novelty Detection