Contents
- Introduction
- Hard Code Word
- Results
- Locality-constrained Linear
- Results
- Grid Search
- Sequential Hierarchy Classifier
- Manually assigned clusters
- Results
- Clusters from K-means
- Results
- Other Dataset Evaluation
- Birds
- Butterflies
- Other Experiments
- Results
- Scene Datasets
- Code
- Git Logs
- References
|
Sequential Hierarchy Classifier
We tried to implement a simple multi-level classifier and evaluate its performance.
The dataset is first assigned in two classes then sequential classification is done.
The motivation for this approach is that certain scenes are inherently very different from others;
hence if we can initally separate them in diffrent bags and drill down to the fewer possible classes may be we can reduce our errors.
Two approaches were employed for the level come classification:
- Manually assigning clusters
- Using K-means to find 2 categories
|