liu.seSearch for publications in DiVA
Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • oxford
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
MCP-Based Model Routing for Efficient Computer Vision: A Multi-Domain Evaluation
Linköping University, Department of Computer and Information Science.
2026 (English)Independent thesis Basic level (degree of Bachelor), 10,5 credits / 16 HE creditsStudent thesisAlternative title
MCP-baserad modellrouting för effektivt datorseende : En flerdomänsevaluering (Swedish)
Abstract [en]

The growing computational cost of large vision models has intensified interest in mod-ular inference architectures that can reduce GPU memory consumption without sacrificingtask performance. This thesis investigates the viability of Model Context Protocol (MCP)as a dynamic dispatch layer for computer vision, proposing and evaluating a two-phaserouting pipeline as an alternative to monolithic vision-language model inference.The proposed system uses a lightweight host LLM (Qwen 3.5-2B) to first invoke animage classifier (ViT-Base-Patch16) via MCP, then route to one of three domain-specialiseddetection models based on the returned label: YOLO-Face for face/human centric images,Table-Transformer for document tables, and OWLViT as a general-purpose default. This iscompared against a monolithic baseline, Qwen3-VL-4B, which performs classification andlocalisation in a single forward pass. Both systems are evaluated on 8,674 images drawnfrom three benchmark datasets spanning distinct visual domains: COCO val2017, WIDERFACE, and PubTables-1M. Performance is measured across four dimensions: VRAM con-sumption, end-to-end latency, classification accuracy, and object localisation via IoU (Inter-section over Union).The routing system achieves a mean VRAM consumption of 2.80 GB against the base-line’s 7.05 GB, a 60% reduction, with a peak of 5.71 GB remaining well below the baseline’speak of 13.15 GB. Contrary to expectations, the routing system also demonstrates substan-tially lower latency, averaging 8.14 seconds per image against the baseline’s 33.48 seconds,with a significantly tighter distributional spread (P95: 9.33s vs 64.17s). Overall accuracyis comparable between the two systems at approximately 54.4% label match and 49% IoUsuccess, but the domain-level breakdown reveals a complete inversion. The routing systemsubstantially outperforms the baseline on face and table detection while underperformingon general object detection, where vocabulary misalignment between the ImageNet clas-sifier and COCO annotations limits zero-shot detection quality. A secondary retry config-uration, in which the pipeline invokes another of its specialist tools when no boundingboxes are returned, improved IoU success to 69.1% at a mean latency of 14.52 seconds,remaining approximately twice as fast as the monolithic baseline and suggesting a viableaccuracy-latency trade-off.These results support a cautiously positive assessment of MCP-based routing as a prac-tical architectural pattern for domain-specific computer vision deployments, demonstrat-ing that modular specialisation can deliver meaningful efficiency gains while matchingaggregate accuracy, at the cost of reduced generality.

Place, publisher, year, edition, pages
2026. , p. 14
Keywords [en]
Computer Vision, Model Context Protocol, Model Routing, Large Language Models, Modular Inference, Object Detection, Image Classification, VRAM Efficiency, Latency, Multi-Domain Evaluation, Qwen, YOLO-Face, Table Transformer, OWL-ViT, ViT, Intersection over Union
National Category
Computer and Information Sciences
Identifiers
URN: urn:nbn:se:liu:diva-225331ISRN: LIU-IDA/LITH-EX-G--26/059--SEOAI: oai:DiVA.org:liu-225331DiVA, id: diva2:2078016
Subject / course
Computer science
Presentation
2026-06-10, P18, Campus Valla, Hans Meijers väg 12, 14, 16, 20, Linköping, 13:15 (Swedish)
Supervisors
Examiners
Available from: 2026-06-24 Created: 2026-06-23 Last updated: 2026-06-24Bibliographically approved

Open Access in DiVA

fulltext(1089 kB)333 downloads
File information
File name FULLTEXT01.pdfFile size 1089 kBChecksum SHA-512
2926f80851e3b9f1bae8f9fd3b494bb0644610f5a6b389d8c0ba7212b4aed62639cc118b515c885acf32a929642e4b4b1bdc963af22adff1e28bf7edc551db21
Type fulltextMimetype application/pdf

By organisation
Department of Computer and Information Science
Computer and Information Sciences

Search outside of DiVA

GoogleGoogle Scholar
Total: 333 downloads
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

urn-nbn

Altmetric score

urn-nbn
Total: 376 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • oxford
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf