TAPe+ML: A Compact Structured Representation for Multi-Task Computer Vision
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.
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
MoTE: Mixture of Task Experts for Multi-Task Video Understanding
MoTE introduces task-specific expert routing to replace dense decoder feed-forward networks in multi-task video understanding, improving accuracy and efficiency with interpretable, sparse computation.
VideoChat3: Fully Open Video MLLM for Efficient and Generalist Video Understanding
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.
MoE-ViE: Mixture of Experts Vision Encoder for Efficient Image and Video Understanding
This paper presents MoE-ViE, a mixture-of-experts vision encoder that efficiently scales for image and video understanding, outperforming larger dense models with lower inference latency.
Attention-based representations for multi-task computation
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.
SimpleMemVLA: A Simple but Effective Native-Video Memory for Vision-Language-Action Models
SimpleMemVLA introduces a simple memory mechanism for Vision-Language-Action models by feeding intact timestamped video history into a pretrained VLM backbone, achieving state-of-the-art results on long-horizon manipulation tasks without dedicated memory modules.