| title | TAPe+ML: A Compact Structured Representation for Multi-Task Computer Vision |
|---|---|
| authors | Sergey Kurinov, Alexey Upatov |
| date | 2026-09-15 |
| venue | arXiv (preprint, not peer reviewed) |
| id | arXiv:2609.20869 |
| affiliation | Comexp Research Lab |
| upvotes | 2 (Hugging Face Daily Papers, 2026-11-01) |
| links | abs pdf hf |
| abstract | We present TAPe+ML v3, a compact computer vision system based on TAPe (Theory of Active Perception), a structured representation that encodes relations among perceptual elements before recognition. Instead of operating directly on pixel tensors, the system uses a shared TAPe representation and a modular recognition architecture for image classification, object detection, and instance segmentation. TAPe+ML v3 combines background and contour processing, local object localization, prototype-based classification, and a coordinator for specialized submodels. Across the reported experiments, it uses fewer than 100,000 parameters. On COCO object detection, it obtains 84.7 mAP50 and 65.3 mAP50-95. On COCO instance segmentation, it obtains 80.7 mask mAP50 and 58.4 mask mAP50-95. In classification experiments, it reaches 92 percent validation accuracy on Imagenette under an identical-training comparison with a raw-pixel baseline, and 89.9 percent Top-1 accuracy on ImageNet-Real. We also evaluate compactness in video scene detection and adaptation under distribution shift in an industrial pilot. The results suggest that shifting part of the modeling burden from network parameters to a structured input representation can support compact multi-task vision systems with reduced data, memory, and compute requirements. |
cite
@misc{kurinov2026tape,
title={TAPe+ML: A Compact Structured Representation for Multi-Task Computer Vision},
author={Sergey Kurinov and Alexey Upatov},
year={2026},
eprint={2609.20869},
archivePrefix={arXiv},
url={https://arxiv.org/abs/2609.20869}
}