The Best of Both Worlds: Combining Learned Embeddings with Engineered Features for Accurate Prediction of Correct Patches.
Haoye TianKui LiuYinghua LiAbdoul Kader KaboréAnil KoyuncuAndrew HabibLi LiJunhao WenJacques KleinTegawendé F. BissyandéPublished in: CoRR (2022)
Keyphrases
- feature extraction
- prediction accuracy
- high quality
- feature vectors
- low level
- image features
- high accuracy
- combining multiple
- feature set
- computer vision
- co occurrence
- classification accuracy
- dimensionality reduction
- training set
- computationally efficient
- high level
- spatial information
- manifold learning
- euclidean space
- prediction error
- salient features
- decision trees