Do Deep Neural Networks Learn Facial Action Units When Doing Expression\n Recognition?
Bibliographic record
Abstract
Despite being the appearance-based classifier of choice in recent years,\nrelatively few works have examined how much convolutional neural networks\n(CNNs) can improve performance on accepted expression recognition benchmarks\nand, more importantly, examine what it is they actually learn. In this work,\nnot only do we show that CNNs can achieve strong performance, but we also\nintroduce an approach to decipher which portions of the face influence the\nCNN's predictions. First, we train a zero-bias CNN on facial expression data\nand achieve, to our knowledge, state-of-the-art performance on two expression\nrecognition benchmarks: the extended Cohn-Kanade (CK+) dataset and the Toronto\nFace Dataset (TFD). We then qualitatively analyze the network by visualizing\nthe spatial patterns that maximally excite different neurons in the\nconvolutional layers and show how they resemble Facial Action Units (FAUs).\nFinally, we use the FAU labels provided in the CK+ dataset to verify that the\nFAUs observed in our filter visualizations indeed align with the subject's\nfacial movements.\n
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 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 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.000 | 0.001 |
| 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 itClassification
machine, unvalidatedMachine predicted; a candidate call from one teacher head, 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".