3 papers
cs.CV2025
Dynamic Epsilon Scheduling: A Multi-Factor Adaptive Perturbation Budget for Adversarial Training
Alan Mitkiy, James Smith, Myungseo wong +3
Adversarial training is among the most effective strategies for defending deep neural networks against adversarial examples. A key limitation of existing adversarial training appro…
cs.CV2025
Dynamic Modality Scheduling for Multimodal Large Models via Confidence, Uncertainty, and Semantic Consistency
Hiroshi Tanaka, Anika Rao, Hana Satou +2
Multimodal Large Models (MLLMs) have achieved remarkable progress in vision-language understanding and generation tasks. However, existing MLLMs typically rely on static modality f…
cs.CV2025
Guidelines for External Disturbance Factors in the Use of OCR in Real-World Environments
Kenji Iwata, Eiki Ishidera, Toshifumi Yamaai +6
The performance of OCR has improved with the evolution of AI technology. As OCR continues to broaden its range of applications, the increased likelihood of interference introduced…