AVLLM-Based Multimodal Reasoning Segmentation and Detection Approach for Intelligent Driving
Bibliographic record
Abstract
Reasoning segmentation and detection are important to realize secure and reliable intelligent driving. In this paper, we propose an Audio-Vision-Language Large Model-based Multimodal Reasoning Segmentation and Detection (AVLLM-MRSD) approach, where audio prompts or text prompts in Chinese or English are allowed when executing reasoning segmentation and detection tasks. The proposed AVLLM-MRSD approach can simultaneously output reasoning language response and segmented-detected image. Specifically, the multimodal audio-language large model (ALLM) module which is composed of the audio encoder and large language model (LLM) is first employed to convert the audio prompt to the text prompt. Then, the text prompt and image are input to the multimodal vision-language large model (VLLM) module to obtain the reasoning language response and segmented-detected image. Besides, the proposed method supports multi-round and multi-object reasoning segmentation and detection tasks. Extensive experimental results in real traffic scenarios show that the proposed AVLLM-MRSD approach can more efficiently and accurately complete reasoning segmentation and detection of various vehicles, pedestrians, lanes, barriers, and traffic lights compared with the existing LISA and Grounded SAM methods.
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 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.002 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.001 | 0.002 |
| Open science | 0.002 | 0.002 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.004 | 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".