Towards Measuring Bias in Image Classification
원문 초록
Convolutional Neural Networks (CNN) have become de fact state-of-the-art for the main computer vision tasks. However, due to the complex underlying structure their decisions are hard to understand which limits their use in some context of the industrial world. A common and hard to detect challenge in machine learning (ML) tasks is data bias. In this work, we present a systematic approach to uncover data bias by means of attribution maps. For this purpose, first an artificial dataset with a known bias is created and used to train intentionally biased CNNs. The networks' decisions are then inspected using attribution maps. Finally, meaningful metrics are used to measure the attribution maps' representativeness with respect to the known bias. The proposed study shows that some attribution map techniques highlight the presence of bias in the data better than others and metrics can support the identification of bias.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
One Prototype Is Enough: Single-Prototype Activation for Interpretable Image Classification
Hyperspectral Image Classification via Transformer-based Spectral-Spatial Attention Decoupling and Adaptive Gating
GeoVision Labeler: Zero-Shot Geospatial Classification with Vision and Language Models
Optimal Weighted Convolution for Classification and Denosing
Adversarial attacks to image classification systems using evolutionary algorithms
Disentangled representations of microscopy images
토론
이 논문과 연결된 포럼 글이 아직 없습니다.