A Hierarchical Deep Architecture and Mini-Batch Selection Method For\n Joint Traffic Sign and Light Detection
Bibliographic record
Abstract
Traffic light and sign detectors on autonomous cars are integral for road\nscene perception. The literature is abundant with deep learning networks that\ndetect either lights or signs, not both, which makes them unsuitable for\nreal-life deployment due to the limited graphics processing unit (GPU) memory\nand power available on embedded systems. The root cause of this issue is that\nno public dataset contains both traffic light and sign labels, which leads to\ndifficulties in developing a joint detection framework. We present a deep\nhierarchical architecture in conjunction with a mini-batch proposal selection\nmechanism that allows a network to detect both traffic lights and signs from\ntraining on separate traffic light and sign datasets. Our method solves the\noverlapping issue where instances from one dataset are not labelled in the\nother dataset. We are the first to present a network that performs joint\ndetection on traffic lights and signs. We measure our network on the\nTsinghua-Tencent 100K benchmark for traffic sign detection and the Bosch Small\nTraffic Lights benchmark for traffic light detection and show it outperforms\nthe existing Bosch Small Traffic light state-of-the-art method. We focus on\nautonomous car deployment and show our network is more suitable than others\nbecause of its low memory footprint and real-time image processing time.\nQualitative results can be viewed at https://youtu.be/_YmogPzBXOw\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 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 | 0.001 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.003 | 0.001 |
| Research integrity | 0.001 | 0.002 |
| Insufficient payload (model declined to judge) | 0.005 | 0.002 |
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".