Improving alignment of faces for recognition
Why this work is in the frame
A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.
Bibliographic record
Abstract
Face recognition systems for uncontrolled environments often work through an alignment, feature extraction, and recognition pipeline. Effective alignment of faces is thus crucial as can be an entry point in the process and poor alignments can greatly affect recognition performance. The task of alignment is particularly difficult when a face comes from highly unconstrained environments or so called faces in the wild. A lot of recent research activity has focused on faces in the wild and even simple similarity or affine transformations have proven both effective and essential to achieving state of the art performance. In this paper we explore a straightforward, fast and effective approach to aligning faces based on detecting facial landmarks using Haar-like image features and a cascade of boosted classifiers. Our approach is reminiscent of widely used face detection approaches, but focused on much more detailed features of a face such eye centres, the nose tip and corners of the mouth. This process generates multiple candidates for each landmark and we present a fast and effective filtering strategy allowing us to find sets of landmarks that are consistent. Our experiments show that this approach can outperform contemporary methods and easily fits into popular processing pipelines for faces in the wild.
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.
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
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 it