Investigating and Explaining the Frequency Bias in Image Classification
CNNs exhibit many behaviors different from humans, one of which is the capability of employing high-frequency components. This paper discusses the frequency bias phenomenon in image classification tasks: the high-frequency components are actually much less exploited than the low- and mid-frequency components. We first investigate the frequency bias phenomenon by presenting two observations on feature discrimination and learning priority. Furthermore, we hypothesize that (i) the spectral density, (ii) class consistency directly affect the frequency bias. Specifically, our investigations verify that the spectral density of datasets mainly affects the learning priority, while the class consistency mainly affects the feature discrimination.
Code (1)
Tasks
Classificationimage-classificationImage ClassificationSimilar Papers 제목 키워드 기반
Beyond Spatial Explanations: Explainable Face Recognition in the Frequency Domain
The need for more transparent face recognition (FR), along with other visual-based decision-making systems has recently attracted more attention in research, society, and industry. The reasons why two face images are mat…
Face RecognitionLinking convolutional kernel size to generalization bias in face analysis CNNs
Training dataset biases are by far the most scrutinized factors when explaining algorithmic biases of neural networks. In contrast, hyperparameters related to the neural network architecture have largely been ignored eve…
Frequency Matters: Explaining Biases of Face Recognition in the Frequency Domain
Face recognition (FR) models are vulnerable to performance variations across demographic groups. The causes for these performance differences are unclear due to the highly complex deep learning-based structure of face re…
Face RecognitionInvestigating Bias in Image Classification using Model Explanations
We evaluated whether model explanations could efficiently detect bias in image classification by highlighting discriminating features, thereby removing the reliance on sensitive attributes for fairness calculations. To t…
Bias DetectionClassificationFairnessGeneral Classification+2Exploring Explainability in Video Action Recognition
Image Classification and Video Action Recognition are perhaps the two most foundational tasks in computer vision. Consequently, explaining the inner workings of trained deep neural networks is of prime importance. While …
Action RecognitionClassificationimage-classificationImage Classification+1