A new dataset of dog breed images and a benchmark for fine-grained classification
In this paper, we introduce an image dataset for fine-grained classification of dog breeds: the Tsinghua Dogs Dataset. It is currently the largest dataset for fine-grained classification of dogs, including130 dog breeds and 70,428 real-world images. It has only one dog in each image and provides annotated bounding boxes for the whole body and head. In comparison to previous similar datasets, it contains more breeds and more carefully chosen images for each breed. The diversity within each breed is greater, with between 200 and 7000+ images for each breed. Annotation of the whole body and head makes the dataset not only suitable for the improvement of fine-grained image classification models based on overall features, but also for those locating local informative parts. We show that dataset provides a tough challenge by benchmarking several state-of-the-art deep neural models. The dataset is available for academic purposes at https://cg.cs.tsinghua.edu.cn/ThuDogs/.
Code (1)
Tasks
BenchmarkingClassificationDiversityFine-Grained Image ClassificationGeneral Classificationimage-classificationImage ClassificationMetric LearningSimilar Papers 제목 키워드 기반
Fine-Grained Cat Breed Recognition with Global Context Vision Transformer
Accurate identification of cat breeds from images is a challenging task due to subtle differences in fur patterns, facial structure, and color. In this paper, we present a deep learning-based approach for classifying cat…
Fine-Grained Image ClassificationData AugmentationPetFace: A Large-Scale Dataset and Benchmark for Animal Identification
Automated animal face identification plays a crucial role in the monitoring of behaviors, conducting of surveys, and finding of lost animals. Despite the advancements in human face identification, the lack of datasets an…
Face IdentificationFace VerificationCombining Fine- and Coarse-Grained Classifiers for Diabetic Retinopathy Detection
Visual artefacts of early diabetic retinopathy in retinal fundus images are usually small in size, inconspicuous, and scattered all over retina. Detecting diabetic retinopathy requires physicians to look at the whole ima…
Diabetic Retinopathy DetectionBonnBeetClouds3D: A Dataset Towards Point Cloud-based Organ-level Phenotyping of Sugar Beet Plants under Field Conditions
Agricultural production is facing severe challenges in the next decades induced by climate change and the need for sustainability, reducing its impact on the environment. Advancements in field management through non-chem…
Keypoint DetectionPoint Cloud CompletionSurface ReconstructionWhen Generative Augmentation Hurts: A Benchmark Study of GAN and Diffusion Models for Bias Correction in AI Classification Systems
Generative models are widely used to compensate for class imbalance in AI training pipelines, yet their failure modes under low-data conditions are poorly understood. This paper reports a controlled benchmark comparing t…