Emissivity-Guided Thermal Image Encoding: A Robust Multitask Learning Approach for Object Detection
Bibliographic record
Abstract
Thermal imaging provides critical information for object detection in low-light environments. However, effectively leveraging thermal data remains challenging due to the degraded performance of RGB-trained models in the thermal domain and the lack of large-scale labeled thermal datasets. To address these challenges, we propose Emissivity-Guided Thermal Image Encoding (EGTIE), a novel thermal image representation that integrates physical principles with multitask learning to enhance thermal image understanding. EGTIE employs a physically grounded encoder to extract compact and semantically rich features from thermal data, jointly optimized for reconstruction and detection tasks. By pretraining on the thermal image reconstruction task, the encoder captures the intrinsic characteristics of thermal images, providing a robust feature representation for downstream object detection. This multitask learning approach not only reduces dependence on large-scale labeled supervision but also enhances generalization across diverse scenarios. Experimental results show that EGTIE outperforms state-of-the-art methods in thermal object detection, demonstrating its effectiveness in addressing the unique challenges of thermal vision.
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 | 0.003 | 0.004 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.002 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.001 | 0.002 |
| Insufficient payload (model declined to judge) | 0.001 | 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".