Tiny SSD: A Tiny Single-shot Detection Deep Convolutional Neural Network\n for Real-time Embedded Object Detection
Bibliographic record
Abstract
Object detection is a major challenge in computer vision, involving both\nobject classification and object localization within a scene. While deep neural\nnetworks have been shown in recent years to yield very powerful techniques for\ntackling the challenge of object detection, one of the biggest challenges with\nenabling such object detection networks for widespread deployment on embedded\ndevices is high computational and memory requirements. Recently, there has been\nan increasing focus in exploring small deep neural network architectures for\nobject detection that are more suitable for embedded devices, such as Tiny YOLO\nand SqueezeDet. Inspired by the efficiency of the Fire microarchitecture\nintroduced in SqueezeNet and the object detection performance of the\nsingle-shot detection macroarchitecture introduced in SSD, this paper\nintroduces Tiny SSD, a single-shot detection deep convolutional neural network\nfor real-time embedded object detection that is composed of a highly optimized,\nnon-uniform Fire sub-network stack and a non-uniform sub-network stack of\nhighly optimized SSD-based auxiliary convolutional feature layers designed\nspecifically to minimize model size while maintaining object detection\nperformance. The resulting Tiny SSD possess a model size of 2.3MB (~26X smaller\nthan Tiny YOLO) while still achieving an mAP of 61.3% on VOC 2007 (~4.2% higher\nthan Tiny YOLO). These experimental results show that very small deep neural\nnetwork architectures can be designed for real-time object detection that are\nwell-suited for embedded scenarios.\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 | 0.001 | 0.000 |
| Meta-epidemiology (narrow) | 0.001 | 0.002 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.003 |
| Science and technology studies | 0.002 | 0.001 |
| Scholarly communication | 0.000 | 0.001 |
| Open science | 0.003 | 0.002 |
| Research integrity | 0.001 | 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".