8-Calves Image dataset

Abstract: We introduce the 8-Calves dataset, a benchmark for evaluating object detection and identity preservation in occlusion-rich, temporally consistent environments. Comprising a 1-hour video (67,760 frames) of eight Holstein Friesian calves with unique coat patterns and 900 static frames, the dataset emphasizes real-world challenges like prolonged occlusions, motion blur, and pose variation. By fine-tuning 28 object detectors (YOLO variants, transformers) and evaluating 23 pretrained backbones (ResNet, ConvNextV2, ViTs), we expose critical architectural trade-offs: smaller models (e.g., ConvNextV2 Nano, 15.6M parameters) excel in efficiency and retrieval accuracy, while pure vision transformers lag in occlusion-heavy settings. The dataset's structured design-fixed camera views, natural motion, and verified identities-provides a reproducible testbed for object detection challenges (mAP50:95: 56.5-66.4%), bridging synthetic simplicity and domain-specific complexity. The dataset and benchmark code are all publicly available at https://huggingface.co/datasets/tonyFang04/8-calves. Limitations include partial labeling and detector bias, addressed in later sections.