Learning to Recognize Unmodified Lights with Invisible Features
Bibliographic record
Abstract
To enable accurate indoor localization at low cost, recent research in visible light positioning (VLP) proposed to employ existing ceiling lights as location landmarks, and use smartphone cameras or light sensors to identify the different lights using statistical visual/optical features. Despite the potential, we find such solutions are unreliable: the features are easily corrupted with a slight rotation of the smartphone, and are not discriminative enough for many practical light models with different size/shape/intensity. In this work, we propose Auto-Litell to resolve these critical challenges and make VLP truly robust. Auto-Litell builds a customized deep-learning neural network model to automatically distill the "invisible" visual features from the lights, which are resilient to smartphone orientation and light models. Moreover, Auto-Litell introduces a Light-CycleGAN to generate "fake" light images to augment the training data, so as to relieve human labors in data collection and labeling. We have implemented Auto-Litell as a real-time localization and navigation system on Android. Our experiments demonstrate Auto-Litell's high accuracy in discriminating the lights in the same building, and high reliability across a variety of practical usage scenarios.
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 | 0.001 |
| 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 | 0.000 |
| 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".