Research map / Label-efficient and robust learning / Semi-supervised learning
Species196: A One-Million Semi-supervised Dataset for Fine-grained Species Recognition
Wei He, Kai Han, Ying Nie, Chengcheng Wang, Yunhe Wang
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Train a larger ResNet34 student from a ResNet18 teacher using Noisy Student | Noisy Student on Species196-U · Species196-L | student top-1 accuracy: 71.1 -> 73.4 | Improved |
| Use a same-size ResNet18 student instead of a larger student (ablation) | Noisy Student on Species196-U · Species196-L | student top-1 accuracy: 71.1 -> 70.6 | Hurt |
| Pretrain ViT-B with SimMIM on Species-U rather than ImageNet-1K (ablation) | ViT-B · Species196-L | top-1 accuracy: 80.9 -> 81.0 | Improved |
| Pretrain Swin-B with SimMIM on Species-U rather than ImageNet-1K (ablation) | Swin-B · Species196-L | top-1 accuracy: 80.5 -> 81.6 | Improved |
| Pretrain ResNet50 with SparK on Species-U rather than ImageNet-1K (ablation) | ResNet50 · Species196-L | top-1 accuracy: 73.2 -> 73.2 | No clear effect |
| Pretrain ConvNeXt V2-T with FCMAE on Species-U rather than ImageNet-1K (ablation) | ConvNeXt V2-T · Species196-L | top-1 accuracy: 77.1 -> 79.3 | Improved |
| Pretrain ConvNeXt V2-B with FCMAE on Species-U rather than ImageNet-1K (ablation) | ConvNeXt V2-B · Species196-L | top-1 accuracy: 79.9 -> 81.2 | Improved |
| Use the Species-U domain-specific data for masked-image pretraining instead of ImageNet-1K (ablation) | MIM-pretrained models · Species196-L | top-1 accuracy: ViT-B: 80.9 -> 81.0; Swin-B: 80.5 -> 81.6; ResNet50: 73.2 -> 73.2; ConvNeXt V2-T: 77.1 -> 79.3; ConvNeXt V2-B: 79.9 -> 8 | Mixed |
| Use a larger Noisy Student model rather than a same-size student (ablation) | Noisy Student · Species196-L | student top-1 accuracy: ResNet18 teacher to ResNet34 student: 71.1 -> 73.4; ResNet18 teacher to ResNet18 student: 71.1 -> 70.6; ResNet34 teacher | Mixed |
| Combine class-name and species-description prompts (1) + (4) + (5) (ablation) | OpenCLIP ViT-B/32 · Species196-L zero-shot classification | top-1 accuracy: 10.7 -> 10.94 | Improved |
| Add prompt (6) to combination (1) + (4) + (5) (ablation) | OpenCLIP ViT-B/32 · Species196-L zero-shot classification | top-1 accuracy: 10.94 -> 10.91 | Hurt |
| Use common names rather than scientific names as classnames (ablation) | OpenCLIP models · Species196-L zero-shot classification | top-1 accuracy: ViT-B/32: 10.94 -> 16.71; ViT-B/16: 10.40 -> 16.90; ViT-L/14: 12.07 -> 18.43; ViT-H/14: 15.00 -> 22.57 | Improved |
Closest papers by meaning
- The INaturalist Species Classification and Detection Dataset (CVPR 2018 · similarity 0.89)
- Open-Insect: Benchmarking Open-Set Recognition of Novel Species in Biodiversity Monitoring (NeurIPS 2025 · similarity 0.88)
- BioTrove: A Large Curated Image Dataset Enabling AI for Biodiversity (NeurIPS 2024 · similarity 0.87)
- DivShift: Exploring Domain-Specific Distribution Shifts in Large-Scale, Volunteer-Collected Biodiversity Datasets (AAAI 2025 · similarity 0.86)
- RealBirdID: Benchmarking Bird Species Identification in the Era of MLLMs (CVPR 2026 · similarity 0.86)
- Fish-Vista: A Multi-Purpose Dataset for Understanding & Identification of Traits from Images (CVPR 2025 · similarity 0.84)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
