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

• URL: http://arxiv.org/abs/2607.14509v1
• Date: Thu, 16 Jul 2026 02:47:38 GMT
• Title: Multi-Scale ViT Inference with Habitat-Fit Priors and kNN Retrieval for Multi-Species Plant Identification
• Abstract summary: This paper describes DS@GT ARC's third-place solution to the PlantCLEF 2026 challenge on multi-species plant identification in vegetation quadrat images.<n>The pipeline is built around a fine-tuned DINOv2 ViT-L/14 classifier applied over a multi-scale tile decomposition of each quadrat.<n>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.
• Score: 0.04014524824655105
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• Cut-ViT: Task-Specific Model Pruning via Gram Anchoring Subspace Consistency [71.81785123423516]
  We propose a task-specific pruning pipeline, named Cut-ViT, for pruning visual foundation models.<n> Basis-agnostic and residual constraints are adopted to align the gram subspaces between the native and pruned DINOv3 models.<n>Experiments show that Cut-ViT requires approximately one minute on a single A100 GPU to obtainworks at various sparsity levels.
  arXiv  Detail & Related papers  (2026-08-28T11:25:36Z)
• DS@GT ARC at AnimalCLEF 2026: Species-Aware Graph Construction for Multi-Species Animal Re-Identification [0.0]
  The DS@GT ARC submission to AnimalCLEF 2026 introduces a multi-species image-clustering system for re-identification.<n>Instead of relying on a single descriptor or nearest-neighbor retrieval, this approach formulates re-identification as species-aware graph construction.
  arXiv  Detail & Related papers  (2026-07-17T18:49:49Z)
• DNA: Dual-stage Native Attribution for Generated Image Source Tracing [75.65470221927096]
  Existing proactive methods rely on watermark embedding or model modification.<n>DNA is a coarse-to-fine framework that follows this hierarchy without additional neural-network training.<n>Experiments show that DNA achieves 89.11% end-to-end attribution accuracy.
  arXiv  Detail & Related papers  (2026-07-15T10:27:52Z)
• EcoVision: AI-Powered Drone Imaging for Salt Marsh Vegetation Monitoring and Dominance Mapping [0.0]
  The framework targeted two ecologically significant halophytic grasses, Spartina maritima and Puccinellia maritima.<n>In order to identify these plants from the imagery, our segmentation yielded reliable species masks.<n>The developed system, named EcoVision, establishes a practical foundation for scalable, high-resolution salt marsh monitoring.
  arXiv  Detail & Related papers  (2026-07-07T10:16:31Z)
• Scaling Parallel Sequence Models to Foundation-Scale Vision Encoders [123.58723804218151]
  Vision foundation models are bottlenecked by the quadratic cost of self-attention.<n>We present C-GSPN based on 2D spatial propagation propagation.
  arXiv  Detail & Related papers  (2026-05-30T14:29:43Z)
• A Modelling and Evaluation Framework for EuroCrops-Driven Sentinel-2 Crop Segmentation [78.66324246922831]
  This work presents a pipeline for generating semantic-segmentation-ready agricultural datasets from Sentinel-2 imagery and EuroCrops parcel-level annotations.<n>The dataset contains 67,337 patches from five European countries and uses a reduced taxonomy of ten crop classes plus background.<n>A four-level U-Net with Group Normalization was trained using 10 Sentinel-2 spectral bands and a composite loss combining class-weighted cross-entropy and Dice loss.
  arXiv  Detail & Related papers  (2026-05-30T11:20:29Z)
• FLORO: A Multimodal Geospatial Foundation Model for Ecological Remote Sensing Across Sensors and Scales [65.4821703903285]
  FLORO is a multimodal foundation model designed to learn transferable representations from a small but highly diverse remote sensing corpus.<n> FLORO is pretrained using masked autoencoding on a heterogeneous combination of Sentinel-1, Sentinel-2, SkySAT imagery, elevation, and UAV-derived data.<n>We evaluated FLORO on the PANGAEA benchmark under a frozen-encoder protocol across scene classification, segmentation, and regression tasks.
  arXiv  Detail & Related papers  (2026-05-27T08:55:54Z)
• SEED: Targeted Data Selection by Weighted Independent Set [76.68391670109433]
  We develop a robust and scalable data selection pipeline dubbed SEED.<n>SEED consistently outperforms state-of-the-art methods on instruction tuning, visual instruction tuning, and semantic segmentation.
  arXiv  Detail & Related papers  (2026-05-15T07:26:54Z)
• Zero-Shot Segmentation through Prototype-Guidance for Multi-Label Plant Species Identification [0.5249805590164902]
  This paper presents an approach developed to address the PlantClef 2025 challenge, which consists of a fine-grained multi-label species identification.<n>Our solution focused on employing class prototypes obtained from the training dataset as a proxy guidance for training a segmentation Vision Transformer (ViT) on the test set images.<n>The proposed approach enabled a domain-adaptation from multi-class identification with individual species, into multi-label classification from high-resolution vegetation plots.
  arXiv  Detail & Related papers  (2025-12-23T01:06:55Z)
• Multi-Label Plant Species Prediction with Metadata-Enhanced Multi-Head Vision Transformers [0.0]
  We present a multi-head vision transformer approach for multi-label plant species prediction in vegetation plot images.<n>The task involves training models on single-species plant images while testing on multi-species quadrat images, creating a drastic domain shift.<n>Our methodology leverages a pre-trained DINOv2 Vision Transformer Base (ViT-B/14) backbone with multiple classification heads for species, genus, and family prediction.
  arXiv  Detail & Related papers  (2025-08-14T08:56:58Z)
• Tile-Based ViT Inference with Visual-Cluster Priors for Zero-Shot Multi-Species Plant Identification [0.1181206257787103]
  We describe DS@GT's second-place solution to the PlantCLEF 2025 challenge on multi-species plant identification in vegetation quadrat images.<n>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.
  arXiv  Detail & Related papers  (2025-07-08T15:35:19Z)
• A Deep Learning Approach Based on Graphs to Detect Plantation Lines [16.76043873454695]
  We propose a deep learning approach based on graphs to detect plantation lines in UAV-based RGB imagery. The proposed method was compared against state-of-the-art deep learning methods. It achieved superior performance with a significant margin, returning precision, recall, and F1-score of 98.7%, 91.9%, and 95.1%, respectively.
  arXiv  Detail & Related papers  (2021-02-05T14:56:42Z)
• Two-View Fine-grained Classification of Plant Species [66.75915278733197]
  We propose a novel method based on a two-view leaf image representation and a hierarchical classification strategy for fine-grained recognition of plant species. A deep metric based on Siamese convolutional neural networks is used to reduce the dependence on a large number of training samples and make the method scalable to new plant species.
  arXiv  Detail & Related papers  (2020-05-18T21:57:47Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.