Search Results for author:
Found 3 papers, 0 papers with code
PanelNet: Understanding 360 Indoor Environment via Panel Representation
To reduce the negative impact of panoramic distortion, we incorporate a panel geometry embedding network that encodes both the local and global geometric features of a panel.
Dynamic Generative Targeted Attacks With Pattern Injection
Concretely, the former adopts a dynamic convolution kernel and a static convolution kernel for the specific instance and the global dataset, respectively, which can inherit the advantages of both instance-specific and instance-agnostic attacks.
Meta-Attack: Class-Agnostic and Model-Agnostic Physical Adversarial Attack
To tackle these issues, we propose a class-agnostic and model-agnostic physical adversarial attack model (Meta-Attack), which is able to not only generate robust physical adversarial examples by simulating color and shape distortions, but also generalize to attacking novel images and novel DNN models by accessing a few digital and physical images.
