Lightweight Image Classification of Raptor Species for Edge Devices: Rare-Species Dataset Expansion via Video Frame Extraction, Knowledge Distillation, and TensorRT Deployment

• URL: http://arxiv.org/abs/2607.26238v1
• Date: Tue, 28 Jul 2026 20:19:25 GMT
• Title: Lightweight Image Classification of Raptor Species for Edge Devices: Rare-Species Dataset Expansion via Video Frame Extraction, Knowledge Distillation, and TensorRT Deployment
• Abstract summary: We investigate lightweight raptor-species classification for real-time edge deployment in wind-turbine collision mitigation.<n>Using DINOv2-L (304M parameters) as a teacher, we distilled three lightweight students (MobileNetV4, ViT-Small, and EfficientNet-B0).<n>To reduce confusion between closely related species, we expanded the dataset to 2,050 images.<n>In five-seed controlled comparisons, neither distillation (versus CE-only) nor the change from a DINOv2-L to a DINOv3-L teacher yielded a clear ensemble-level improvement.
• Score: 0.060917028769172786
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We investigate lightweight raptor-species classification for real-time edge deployment in wind-turbine collision mitigation. Using DINOv2-L (304M parameters) as a teacher, we distilled three lightweight students (MobileNetV4, ViT-Small, and EfficientNet-B0). To reduce confusion between closely related species, we expanded the dataset to 12,519 images, including an increase in Steller's Sea Eagle images from 463 to 2,050 via video-frame extraction. Under a group split that separates samples at the video- and source-image level to mitigate source leakage at that granularity, the three-student ensemble achieved a macro recall of 0.935 +/- 0.004 over five distillation seeds (0.955 on a conventional image-level split, retaining 97.5% of the teacher's macro recall) with roughly one-eighth as many parameters. On a subset of 1,258 images disjoint from the former training images, White-tailed Eagle recall improved by up to 38.6 percentage points, while the rate at which it was misclassified as the Steller's Sea Eagle decreased from 61% to 15% of errors. TensorRT FP16 deployment of EfficientNet-B0 on an NVIDIA Jetson Orin Nano achieved 3.19 ms/image including host-device transfer (313 images/s), with 99.95% argmax agreement with FP32. In five-seed controlled comparisons, neither distillation (versus CE-only) nor the change from a DINOv2-L to a DINOv3-L teacher yielded a clear ensemble-level improvement; the primary gains stem from the dataset expansion and teacher re-fine-tuning.

Related papers

• Federated Binary Gating with Server-Side Vision-Language Inference for Surveillance Anomaly Classification [0.24629531282150874]
  We propose a hybrid two-stage architecture that combines a CNN gate with server-side zero-shot VLM inference.<n>We evaluate this design on UCF-Crime grouped into five coarse metaclasses and implement the federated stage in a real three-node heterogeneous deployment.
  arXiv  Detail & Related papers  (2026-09-07T12:14:57Z)
• Low Cost Two-Stage Fabric Defect Detection at the Edge [0.0]
  Fabric inspection in the garment industries remains largely manual,3.45 and commercial vision systems are priced beyond most small and medium mills.<n>We build such a cascade for four knitfabric defect classes and deploy it end-to-end on an NVIDIA Jetson Nano with FP16.<n>We report this as a caution for cascade speedups measured without controlling the data path, and position the system as AI-assisted triage rather than autonomous acceptance.
  arXiv  Detail & Related papers  (2026-08-12T19:49:00Z)
• Eddy-VL 1.9B: Structural Pruning and Layered Distillation for Edge-Deployable Multimodal Embedding [1.2132884030603328]
  We introduce Eddy-VL 1.9B, a compressed multimodal embedding model built on Qwen3-VL-Embedding-2B for offline, edge-deployable vision-language retrieval.<n>Eddy-VL targets air-gapped forensic and investigative settings where cloud APIs are unavailable and low latency is essential.<n>The released model contains 1,926,188,032 parameters (3.85 GB bf16), representing approximately 9.5% fewer parameters than the 2.13B teacher model.
  arXiv  Detail & Related papers  (2026-07-15T04:36:19Z)
• Multi-Teacher Contrastive Distillation for Edge-Efficient Pathology Foundation Models [1.9573380763700714]
  We propose MuCoDi, a pretraining framework that distills frozen tile embeddings from multiple PFMs into compact edge-oriented encoders.<n>We pretrain students on 14.3M TCGA tiles from only 11.8K WSIs and evaluate frozen encoders on 23 clinically curated downstream classification tasks.
  arXiv  Detail & Related papers  (2026-07-06T18:14:37Z)
• Single-Channel Tissue Segmentation via Cross-Modal Distillation from Foundation Models [0.0]
  Multiplexed fluorescence microscopy improves tissue segmentation by providing complementary channels including nuclear (DAPI) and membrane (E-cadherin)<n>This work proposes a cross-modal knowledge distillation framework that transfers semantic information from a frozen foundation model teacher processing multiplexed input to a lightweight student operating on the nuclear channel only.
  arXiv  Detail & Related papers  (2026-05-30T23:34:49Z)
• Lightweight Distillation of SAM 3 and DINOv3 for Edge-Deployable Individual-Level Livestock Monitoring and Longitudinal Visual Analytics [0.3609538870261841]
  Foundation-model pipelines for individual-level livestock monitoring have raised the accuracy ceiling of precision livestock farming.<n>But their GPU memory budgets exceed the envelope of commodity edge accelerators.<n>To close this gap, the backbone of SAM 3 is distilled into a 40.66M-scale multi-scale student.<n>The pipeline achieves 97.34% top-1 accuracy with 91.67% macro-F1 on nine-class pig behaviour classification.
  arXiv  Detail & Related papers  (2026-04-29T19:25:22Z)
• LC4-DViT: Land-cover Creation for Land-cover Classification with Deformable Vision Transformer [14.684808109822386]
  LC4-DViT is a framework that combines generative data creation with a deformation-aware Vision Transformer.<n>A text-guided diffusion pipeline uses GPT-4o-generated scene descriptions to synthesize high-fidelity training images.<n>DViT couples a DCNv4 deformable convolutional backbone with a Vision Transformer encoder to jointly capture fine-scale geometry and global context.
  arXiv  Detail & Related papers  (2025-11-27T23:56:35Z)
• TinyCLIP: CLIP Distillation via Affinity Mimicking and Weight Inheritance [97.01406871579525]
  We propose a novel cross-modal distillation method, called TinyCLIP, for large-scale language-image pre-trained models. We show that TinyCLIP can reduce the size of the pre-trained CLIP ViT-B/32 by 50%, while maintaining comparable zero-shot performance. Our TinyCLIP ViT-8M/16, trained on YFCC-15M, achieves an impressive zero-shot top-1 accuracy of 41.1% on ImageNet.
  arXiv  Detail & Related papers  (2023-09-21T17:59:53Z)
• Patch-Level Contrasting without Patch Correspondence for Accurate and Dense Contrastive Representation Learning [79.43940012723539]
  ADCLR is a self-supervised learning framework for learning accurate and dense vision representation. Our approach achieves new state-of-the-art performance for contrastive methods.
  arXiv  Detail & Related papers  (2023-06-23T07:38:09Z)
• Sigmoid Loss for Language Image Pre-Training [93.91385557929604]
  We propose a simple pairwise Sigmoid loss for Language-Image Pre-training (SigLIP) The sigmoid loss operates solely on image-text pairs and does not require a global view of the pairwise similarities for normalization. Combined with Locked-image Tuning, with only four TPUv4 chips, we train a SigLiT model that achieves 84.5% ImageNet zero-shot accuracy in two days.
  arXiv  Detail & Related papers  (2023-03-27T15:53:01Z)
• EATFormer: Improving Vision Transformer Inspired by Evolutionary Algorithm [111.17100512647619]
  This paper explains the rationality of Vision Transformer by analogy with the proven practical evolutionary algorithm (EA) We propose a novel pyramid EATFormer backbone that only contains the proposed EA-based transformer (EAT) block. Massive quantitative and quantitative experiments on image classification, downstream tasks, and explanatory experiments demonstrate the effectiveness and superiority of our approach.
  arXiv  Detail & Related papers  (2022-06-19T04:49:35Z)
• MEAL V2: Boosting Vanilla ResNet-50 to 80%+ Top-1 Accuracy on ImageNet without Tricks [57.69809561405253]
  We introduce a framework that is able to boost the vanilla ResNet-50 to 80%+ Top-1 accuracy on ImageNet without tricks. Our method obtains 80.67% top-1 accuracy on ImageNet using a single crop-size of 224x224 with vanilla ResNet-50. Our framework consistently improves from 69.76% to 73.19% on smaller ResNet-18.
  arXiv  Detail & Related papers  (2020-09-17T17:59:33Z)
• Spatiotemporal Contrastive Video Representation Learning [87.56145031149869]
  We present a self-supervised Contrastive Video Representation Learning (CVRL) method to learn visual representations from unlabeled videos. Our representations are learned using a contrasttemporalive loss, where two augmented clips from the same short video are pulled together in the embedding space. We study what makes for good data augmentations for video self-supervised learning and find that both spatial and temporal information are crucial.
  arXiv  Detail & Related papers  (2020-08-09T19:58:45Z)

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.