Analyzing Visual Aircraft Representations with Sparse Autoencoders 文章

ArXiv CS.CV2026-06-16NEWSen作者: Deepshik Sharma

详细信息

来源站点
ArXiv CS.CV
作者
Deepshik Sharma
文章类型
NEWS
语言
en
发布日期
2026-06-16

摘要

arXiv:2606.15468v1 Announce Type: new Abstract: Vision models can achieve strong performance on classification tasks, but the internal representations supporting their predictions are often difficult to interpret. This work investigates whether sparse autoencoders can decompose intermediate representations of a vision model into interpretable features. We train a ConvNeXt classifier on the FGVC-Aircraft dataset, extract spatial activations from its final feature stage, and train a sparse autoencoder on these activations. The learned sparse features are analyzed using top-activating image patches, activation strength, and class selectivity. Qualitative visual inspection reveals that several features correspond to recognizable aircraft structures and visual patterns.