4 papers
Detect and Suppress: A Mechanistic Defense against Adversarial Patches in VLA Models
Yukiya Horiba, Koshiro Aoki, Shunsuke Yasuki +2
Adversarial patches can disrupt Vision-Language-Action (VLA) models by manipulating visual observations, leading to failures in robot control. However, it remains poorly understood…
The Shape of Events: Edge-Based Inductive Biases via Cross-Domain Distillation
Soshun Kihara, Shunsuke Yasuki, Masato Taki
Convolutional neural networks trained on ImageNet are known to exhibit a strong preference for local high-frequency texture, an inductive bias that translates into fragile robustne…
GeoProg3D: Compositional Visual Reasoning for City-Scale 3D Language Fields
Shunsuke Yasuki, Taiki Miyanishi, Nakamasa Inoue +5
The advancement of 3D language fields has enabled intuitive interactions with 3D scenes via natural language. However, existing approaches are typically limited to small-scale envi…
CAM Back Again: Large Kernel CNNs from a Weakly Supervised Object Localization Perspective
Shunsuke Yasuki, Masato Taki
Recently, convolutional neural networks (CNNs) with large size kernels have attracted much attention in the computer vision field, following the success of the Vision Transformers.…