Research map / Detection and segmentation / Open-set and few-shot detection
AnimalClue: Recognizing Animals by their Traces
Risa Shinoda, Nakamasa Inoue, Iro Laina, Christian Rupprecht, Hirokatsu Kataoka
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 |
|---|---|---|---|
| add taxonomic context (genus, family, order, class) to CLIP text prompts (ablation) | fine-tuned CLIP · AnimalClue footprint species classification | top-1 accuracy: 17.6% to 21.7% | Improved |
| use Swin-B instead of ResNet-50 | classifier · AnimalClue feather species classification | top-1 accuracy (%): 59.7 -> 65.3 | Improved |
| use Swin-B instead of VGG-16 | classifier · AnimalClue bone species classification | top-1 accuracy (%): 14.7 -> 20.5 | Improved |
| restrict evaluation to frequent species categories | Swin-B · AnimalClue egg species classification | top-1 accuracy (%): 49.4 -> 58.5 | Improved |
| evaluate on rare species categories instead of all | Swin-B · AnimalClue feather species classification | top-1 accuracy (%): 65.3 -> 2.52 | Hurt |
| evaluate on rare species categories instead of all | RT-DETR · AnimalClue feather species detection | mAP@50-95: 0.17 -> 0.00 | Hurt |
| use RT-DETR instead of YOLOv11 | detector · AnimalClue egg species detection | mAP@50-95: 0.14 -> 0.04 | Hurt |
| use RT-DETR instead of Faster-RCNN | detector · AnimalClue feces species detection | mAP@50-95: 0.06 -> 0.17 | Improved |
| use MaskDINO instead of Mask-RCNN | segmenter · AnimalClue egg species instance segmentation | mask mAP@50-95: 0.16 -> 0.25 | Improved |
| fine-tune CLIP on AnimalClue instead of using generic CLIP or BioCLIP | CLIP ViT-B-32 · AnimalClue feature separation (t-SNE) | qualitative feature separation | Improved |
| use BioCLIP instead of standard CLIP | CLIP features · AnimalClue feather vs egg separation (t-SNE) | qualitative feature separation | Improved |
| predict coarser taxonomic level (order instead of species) | Swin-B · AnimalClue footprint classification | top-1 accuracy (%): 32.3 -> 66.1 | Improved |
Closest papers by meaning
- The SA-FARI Dataset: Segment Anything in Footage of Animals for Recognition and Identification (CVPR 2026 · similarity 0.90)
- WildCLIP: Scene and Animal Attribute Retrieval from Camera Trap Data with Domain-Adapted Vision-Language Models (IJCV 2024 · similarity 0.90)
- MammAlps: A Multi-view Video Behavior Monitoring Dataset of Wild Mammals in the Swiss Alps (CVPR 2025 · similarity 0.88)
- Generating the Wild: Individual-Consistent Image-to-Video Generation for Wildlife (NeurIPS 2026 · similarity 0.87)
- BuckTales: A multi-UAV dataset for multi-object tracking and re-identification of wild antelopes (NeurIPS 2024 · similarity 0.87)
- BirdCollect: A Comprehensive Benchmark for Analyzing Dense Bird Flock Attributes (AAAI 2024 · similarity 0.86)
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.
