# Multi-Scale ViT Inference with Habitat-Fit Priors and kNN Retrieval for Multi-Species Plant Identification

arXiv: https://arxiv.org/abs/2607.14509 · HTML: https://mlsanity.com/paper/2607.14509/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 15 of its 24 references that are in the map.
- First posted on arXiv 16 Jul 2026.

## Builds on (most cited first, 15 of 15)

- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [SAM 3: Segment Anything with Concepts](https://mlsanity.com/paper/2511.16719/) (2025)
- [Vision Transformers Need Registers](https://mlsanity.com/paper/2309.16588/) (2023)
- [Asymmetric Loss For Multi-Label Classification](https://mlsanity.com/paper/2009.14119/) (2020)
- [Data Augmentation using Random Image Cropping and Patching for Deep CNNs](https://mlsanity.com/paper/1811.09030/) (2018)
- [ML-Decoder: Scalable and Versatile Classification Head](https://mlsanity.com/paper/2111.12933/) (2021)
- [Multi-Label Plant Species Classification with Self-Supervised Vision Transformers](https://mlsanity.com/paper/2407.06298/) (2024)
- [Overview of PlantCLEF 2024: multi-species plant identification in vegetation plot images](https://mlsanity.com/paper/2509.15768/) (2025)
- [Overview of PlantCLEF 2025: Multi-Species Plant Identification in Vegetation Quadrat Images](https://mlsanity.com/paper/2509.17602/) (2025)
- [Overview of PlantCLEF 2023: Image-based Plant Identification at Global Scale](https://mlsanity.com/paper/2509.17622/) (2025)
- [Tile-Based ViT Inference with Visual-Cluster Priors for Zero-Shot Multi-Species Plant Identification](https://mlsanity.com/paper/2507.06093/) (2025)
- [Multi-Label Plant Species Prediction with Metadata-Enhanced Multi-Head Vision Transformers](https://mlsanity.com/paper/2508.10457/) (2025)
- [Overview of PlantCLEF 2022: Image-based plant identification at global scale](https://mlsanity.com/paper/2509.17632/) (2025)
- [Plant identification based on noisy web data: the amazing performance of deep learning (LifeCLEF 2017)](https://mlsanity.com/paper/2509.20856/) (2025)

## Abstract (arXiv)

This paper describes DS@GT ARC's third-place solution to the PlantCLEF 2026 challenge on multi-species plant identification in vegetation quadrat images, where systems must predict every species present in high-resolution (~3000 x 3000 pixel) plot photographs while training only on single-label images of individual plants. The pipeline is built around a fine-tuned DINOv2 ViT-L/14 classifier applied over a multi-scale tile decomposition of each quadrat, with per-tile predictions blended with a FAISS kNN retriever and post-processed by source-aware temporal fusion across repeated plot visits, a habitat-fit demotion that injects geographic and altitude priors from the training data, and a South-Western Europe geographic mask. Habitat-fit demotion and multi-scale aggregation are the largest individual contributors in the ablations. Two complementary training-centric directions, a cross-region transformer with noisy-student distillation on the LUCAS dataset and a label-as-query transformer decoder over synthetic CLS-domain pseudo-quadrats, yielded null results. An inference-time augmentation with instance-aware segmentation crops also did not improve performance. The selected submission reaches a private-leaderboard macro-F1 of 0.43902 (third place; public 0.51096); an unselected configuration of the same pipeline scored above 0.45 on the private set. Code: https://github.com/dsgt-arc/plantclef-2026.