Search Results for author:
Found 6 papers, 1 papers with code
CAGE: Circumplex Affect Guided Expression Inference
Using a small-scaled MaxViT-based model architecture, we evaluate the impact of discrete expression category labels in training with the continuous valence and arousal labels.
Ranked #1 on
Dominance Estimation
on EMOTIC
Relationship between Model Compression and Adversarial Robustness: A Review of Current Evidence
Increasing the model capacity is a known approach to enhance the adversarial robustness of deep learning networks.
Conditioning Latent-Space Clusters for Real-World Anomaly Classification
Anomalies in the domain of autonomous driving are a major hindrance to the large-scale deployment of autonomous vehicles.
Traffic Light Recognition using Convolutional Neural Networks: A Survey
Real-time traffic light recognition is essential for autonomous driving.
Adversarial Attacks on Traffic Sign Recognition: A Survey
In this work, we survey existing works performing either digital or real-world attacks on traffic sign detection and classification models.
Sparsely-gated Mixture-of-Expert Layers for CNN Interpretability
In this work, we apply sparse MoE layers to CNNs for computer vision tasks and analyze the resulting effect on model interpretability.
