TAPe+ML: A Compact Structured Representation for Multi-Task Computer Vision

Hugging Face Daily Papers Papers

Summary

The paper introduces TAPe+MLv3, a compact computer vision system using structured representation for multi-task tasks, achieving competitive performance on benchmarks like COCO with fewer than 100,000 parameters.

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.
Original Article
View Cached Full Text

Cached at: 09/22/26, 03:27 PM

Paper page - TAPe+ML: A Compact Structured Representation for Multi-Task Computer Vision

Source: https://huggingface.co/papers/2609.20869

Abstract

WepresentTAPe+MLv3,acompactcomputervisionsystembasedonTAPe(TheoryofActivePerception),astructuredrepresentationthatencodesrelationsamongperceptualelementsbeforerecognition.Insteadofoperatingdirectlyonpixeltensors,thesystemusesasharedTAPerepresentationandamodularrecognitionarchitectureforimageclassification,objectdetection,andinstancesegmentation.TAPe+MLv3combinesbackgroundandcontourprocessing,localobjectlocalization,prototype-basedclassification,andacoordinatorforspecializedsubmodels.Acrossthereportedexperiments,itusesfewerthan100,000parameters.OnCOCOobjectdetection,itobtains84.7mAP50and65.3mAP50-95.OnCOCOinstancesegmentation,itobtains80.7maskmAP50and58.4maskmAP50-95.Inclassificationexperiments,itreaches92percentvalidationaccuracyonImagenetteunderanidentical-trainingcomparisonwitharaw-pixelbaseline,and89.9percentTop-1accuracyonImageNet-Real.Wealsoevaluatecompactnessinvideoscenedetectionandadaptationunderdistributionshiftinanindustrialpilot.Theresultssuggestthatshiftingpartofthemodelingburdenfromnetworkparameterstoastructuredinputrepresentationcansupportcompactmulti-taskvisionsystemswithreduceddata,memory,andcomputerequirements.

View arXiv pageView PDFProject pageAdd to collection

Models citing this paper0

No model linking this paper

Cite arxiv.org/abs/2609.20869 in a model README.md to link it from this page.

Datasets citing this paper0

No dataset linking this paper

Cite arxiv.org/abs/2609.20869 in a dataset README.md to link it from this page.

Spaces citing this paper0

No Space linking this paper

Cite arxiv.org/abs/2609.20869 in a Space README.md to link it from this page.

Collections including this paper0

No Collection including this paper

Add this paper to acollectionto link it from this page.

Similar Articles

VideoChat3: Fully Open Video MLLM for Efficient and Generalist Video Understanding

Papers with Code Trending

VideoChat3 is a fully open, efficient, and generalist video-centric multimodal large language model that introduces Inflated 3D Vision Transformer (I3D-ViT) and Adaptive Frame Resolution for streaming video perception, along with scalable video data synthesis pipelines, achieving superior performance with only 4B parameters.

Attention-based representations for multi-task computation

arXiv cs.LG

This paper establishes theoretical bounds on the number of attention heads needed to produce vector representations that support multiple tasks, such as computing min/max and XOR, showing trade-offs between head count, embedding dimension, and precision.