mlsanityData to 14 Oct 2026

Tile-Based ViT Inference with Visual-Cluster Priors for Zero-Shot Multi-Species Plant Identification

arXiv 2507.06093 ↗First posted 8 Jul 2025cs.CV cs.IR cs.LGcited by 2

Not on the map. Why?

Abstract (arXiv)

We describe DS@GT's second-place solution to the PlantCLEF 2025 challenge on multi-species plant identification in vegetation quadrat images. Our pipeline combines (i) a fine-tuned Vision Transformer ViTD2PC24All for patch-level inference, (ii) a 4x4 tiling strategy that aligns patch size with the network's 518x518 receptive field, and (iii) domain-prior adaptation through PaCMAP + K-Means visual clustering and geolocation filtering. Tile predictions are aggregated by majority vote and re-weighted with cluster-specific Bayesian priors, yielding a macro-averaged F1 of 0.348 (private leaderboard) while requiring no additional training. All code, configuration files, and reproducibility scripts are publicly available at https://github.com/dsgt-arc/plantclef-2025.

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 10 of its 20 references that are in the map. First posted on arXiv 8 Jul 2025.

Builds on

10 of 20 references.

References · 10

  1. 2023DINOv2: Learning Robust Visual Features without Supervisioncited by 7,974
  2. 2021Adaptive Token Sampling For Efficient Vision Transformerscited by 183
  3. 2020Understanding How Dimension Reduction Tools Work: An Empirical Approach to Deciphering t-SNE, UMAP, TriMAP, and PaCMAP for Data Visualizationcited by 173
  4. 2023PatchFusion: An End-to-End Tile-Based Framework for High-Resolution Monocular Metric Depth Estimationcited by 41
  5. 2024ViTAR: Vision Transformer with Any Resolutioncited by 25
  6. 2023PerceptionCLIP: Visual Classification by Inferring and Conditioning on Contextscited by 17
  7. 2023Win-Win: Training High-Resolution Vision Transformers from Two Windowscited by 12
  8. 2024Multi-Label Plant Species Classification with Self-Supervised Vision Transformerscited by 7
  9. 2024Bayesian Exploration of Pre-trained Models for Low-shot Image Classificationcited by 6
  10. 2023[CLS] Token is All You Need for Zero-Shot Semantic Segmentationcited by 5

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 2.

2 papers.

  1. 2026Multi-Scale ViT Inference with Habitat-Fit Priors and kNN Retrieval for Multi-Species Plant Identificationcited by 0
  2. 2026Decoupled Pipeline with Proposal Reranking and Score Fusion for Positive-Unlabeled Marine Species Detectioncited by 0