Sensitivity of sparse codes to image distortions
Sparse coding has been proposed as a theory of visual cortex and as an unsupervised algorithm for learning representations. We show empirically with the MNIST dataset that sparse codes can be very sensitive to image distortions, a behavior that may hinder invariant object recognition. A locally linear analysis suggests that the sensitivity is due to the existence of linear combinations of active dictionary elements with high cancellation. A nearest neighbor classifier is shown to perform worse on sparse codes than original images. For a linear classifier with a sufficiently large number of labeled examples, sparse codes are shown to yield higher accuracy than original images, but no higher than a representation computed by a random feedforward net. Sensitivity to distortions seems to be a basic property of sparse codes, and one should be aware of this property when applying sparse codes to invariant object recognition.
Code (0)
등록된 구현이 없습니다.
Tasks
Object RecognitionSensitivityMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Removing Rain From a Single Image via Discriminative Sparse Coding
Visual distortions on images caused by bad weather conditions can have a negative impact on the performance of many outdoor vision systems. One often seen bad weather is rain which causes significant yet complex local …
Dictionary LearningRain RemovalSpatially Localized Image Degradation Embeddings for Image Quality Assessment
Self-supervised learning (SSL) currently drives state-of-the-art performance in no-reference image quality assessment (NR-IQA). However, standard SSL pipelines uniformly apply synthetic distortions across the entire imag…
No-Reference Image Quality AssessmentSelf-Supervised LearningBenchmarking performance of object detection under image distortions in an uncontrolled environment
The robustness of object detection algorithms plays a prominent role in real-world applications, especially in uncontrolled environments due to distortions during image acquisition. It has been proven that the performanc…
BenchmarkingObjectobject-detectionObject DetectionCPP-Net: Embracing Multi-Scale Feature Fusion into Deep Unfolding CP-PPA Network for Compressive Sensing
In the domain of compressive sensing (CS) deep unfolding networks (DUNs) have garnered attention for their good performance and certain degree of interpretability rooted in CS domain achieved by marrying traditional …
Compressive SensingEigen-Distortions of Hierarchical Representations
We develop a method for comparing hierarchical image representations in terms of their ability to explain perceptual sensitivity in humans. Specifically, we utilize Fisher information to establish a model-derived predict…
Object RecognitionSensitivity