Search Results for author:
Found 4 papers, 0 papers with code
Attention Round for Post-Training Quantization
For ResNet18 and MobileNetV2, the post-training quantization proposed in this paper only require 1, 024 training data and 10 minutes to complete the quantization process, which can achieve quantization performance on par with quantization aware training.
Memory-Based Label-Text Tuning for Few-Shot Class-Incremental Learning
The difficulties are that training on a sequence of limited data from new tasks leads to severe overfitting issues and causes the well-known catastrophic forgetting problem.
Fastidious Attention Network for Navel Orange Segmentation
Deep learning achieves excellent performance in many domains, so we not only apply it to the navel orange semantic segmentation task to solve the two problems of distinguishing defect categories and identifying the stem end and blossom end, but also propose a fastidious attention mechanism to further improve model performance.
FSD: Feature Skyscraper Detector for Stem End and Blossom End of Navel Orange
To accurately and efficiently distinguish the stem end and the blossom end of navel orange from its black spots, we propose a feature skyscraper detector (FSD) with low computational cost, compact architecture and high detection accuracy.
