2 papers
cs.CV2024
Revisiting Relevance Feedback for CLIP-based Interactive Image Retrieval
Ryoya Nara, Yu-Chieh Lin, Yuji Nozawa +4
Many image retrieval studies use metric learning to train an image encoder. However, metric learning cannot handle differences in users' preferences, and requires data to train an…
cs.CV2024
Adversarial Doodles: Interpretable and Human-drawable Attacks Provide Describable Insights
Ryoya Nara, Yusuke Matsui
DNN-based image classifiers are susceptible to adversarial attacks. Most previous adversarial attacks do not have clear patterns, making it difficult to interpret attacks' results…