Better matching with fewer features: The selection of useful features in large database recognition problems
Bibliographic record
Abstract
There has been recent progress on the problem of recognizing specific objects in very large datasets. The most common approach has been based on the bag-of-words (BOW) method, in which local image features are clustered into visual words. This can provide significant savings in memory compared to storing and matching each feature independently. In this paper we take an additional step to reducing memory requirements by selecting only a small subset of the training features to use for recognition. This is based on the observation that many local features are unreliable or represent irrelevant clutter. We are able to select ¿useful¿ features, which are both robust and distinctive, by an unsupervised preprocessing step that identifies correctly matching features among the training images. We demonstrate that this selection approach allows an average of 4% of the original features per image to provide matching performance that is as accurate as the full set. In addition, we employ a graph to represent the matching relationships between images. Doing so enables us to effectively augment the feature set for each image through merging of useful features of neighboring images. We demonstrate adjacent and 2-adjacent augmentation, both of which give a substantial boost in performance.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.003 | 0.012 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.003 | 0.001 |
| Bibliometrics | 0.002 | 0.004 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.002 | 0.005 |
| Open science | 0.003 | 0.002 |
| Research integrity | 0.002 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 0.001 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".