arXiv (OAI Expanded)
open access
Variable-Granularity Tokenization for High-Resolution Object Detection
ViT detectors fix a uniform token grid before any learned stage. A native-resolution aerial detector must then choose between resolving few-pixel objects and staying inside compute and memory limits. We introduce VGTok, a training-free tokenizer that sets patch granularity per region from pixels, ah
Conceptio Open Archive
Analyze & explore related research in Conceptio
Connect this record directly into your research workflow or AI agent. Explore citations across open repositories, query full text, and export structured proof bundles.
This document is indexed with metadata only: full text is not available in the archive for this record. Open the official source ↗
Related documents
- Variable-Granularity Tokenization for High-Resolution Object Detection#792954
- DyFrDet: Towards Accurate Small Object Detection via Dynamic Frequency Suppression with Label Disambiguation#424007
- Scene tokenization for unified perception in autonomous driving#370132
- SARTM: Segment Any RGB Thermal Model with Language aided Distillation#820199
- Modularized Dynamic-Granularity Video LLM for Multi-Event Long Video Understanding#381795
Record · ID 788950
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Bring this data into your agent: Connect via MCP or API · 20 free credits to start · no card required
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive