Search Results for author:
Found 4 papers, 2 papers with code
Proxy Anchor-based Unsupervised Learning for Continuous Generalized Category Discovery
Existing methods for novel category discovery are limited by their reliance on labeled datasets and prior knowledge about the number of novel categories and the proportion of novel samples in the batch.
ContextMix: A context-aware data augmentation method for industrial visual inspection systems
With the minimal additional computation cost of image resizing, ContextMix enhances performance compared to existing augmentation techniques.
AI-KD: Adversarial learning and Implicit regularization for self-Knowledge Distillation
Our model not only distills the deterministic and progressive knowledge which are from the pre-trained and previous epoch predictive probabilities but also transfers the knowledge of the deterministic predictive distributions using adversarial learning.
SPADE: Sparse Pillar-based 3D Object Detection Accelerator for Autonomous Driving
3D object detection using point cloud (PC) data is essential for perception pipelines of autonomous driving, where efficient encoding is key to meeting stringent resource and latency requirements.
