Using a pre-trained ResNet-50 or Vision Transformer (ViT) to extract the embedding vector for 148_1000.jpg .
Recommendations for automated "cleaning" of datasets based on high-loss samples. 148_1000.jpg
Summary of how individual data point audits can lead to more robust AI models. Using a pre-trained ResNet-50 or Vision Transformer (ViT)
Generating Grad-CAM visualizations to identify which pixels the model focuses on when classifying this specific image. 3. Results & Discussion 148_1000.jpg
Measuring the cross-entropy loss contribution of this single image during a training epoch.