Extreme low-data fine-grained classification is common in expert domains where labeling is expensive, yet practitioners still need principled guidance for selecting pretrained encoders. We study emerald inclusion grading with a custom dataset of labeled images across three classes and ask: under matched backbone capacity, how does pretraining objective affect downstream representation quality? We compare four frozen ViT-B/16 encoders trained with supervised classification, contrastive learning (SigLIP2), masked reconstruction (MAE), and self-distillation (DINOv3), and evaluate them with leave-one-out cross-validation using linear and nonlinear probes. To control statistical noise in the low-N regime, we use permutation testing (N=1000) on macro one-vs-rest AUC. Supervised and contrastive encoders provide the strongest linear separability (logistic AUC: 0.768 and 0.735; SVM AUC: 0.739 and 0.697), while MAE improves under nonlinear probes (XGBoost AUC: 0.713). We find that DINOv3 underperforms across probe families in this domain. These results support a practical recommendation for extreme low-data FGVC: prioritize margin-enforcing pretraining objectives when data scarcity restricts probing to linear decision rules, and consider reconstruction-style encoders when nonlinear classifiers are feasible given dataset constraints.
Army Engineering University of PLA（中国人民解放军陆军工程大学）；Nanjing University of Science and Technology（南京理工大学）；Nanjing University（南京大学）
Unsupervised learning technology has caught up with or even surpassed supervised learning technology in general object classification (GOC) and person re-identification (re-ID). However, it is found that the unsupervised learning of fine-grained visual classification (FGVC) is more challenging than GOC and person re-ID. In order to bridge the gap between unsupervised and supervised learning for FGVC, we investigate the essential factors (including feature extraction, clustering, and contrastive learning) for the performance gap between supervised and unsupervised FGVC. Furthermore, we propose …
Fudan University（复旦大学）；Institute of Information Engineering, Chinese Academy of Sciences（中国科学院信息工程研究所）；Shenzhen Research Institute of Big Data（深圳市大数据研究院）；Southern University of Science and Technology（南方科技大学）
Most deep neural networks (DNNs) based ultrasound (US) medical image analysis models use pretrained backbones (e.g., ImageNet) for better model generalization. However, the domain gap between natural and medical images causes an inevitable performance bottleneck. To alleviate this problem, an US dataset named US-4 is constructed for direct pretraining on the same domain. It contains over 23,000 images from four US video sub-datasets. To learn robust features from US-4, we propose an US semi-supervised contrastive learning method, named USCL, for pretraining. In order to avoid high similarities…
Recent findings have shown that highly over-parameterized Neural Networks generalize without pretraining or explicit regularization. It is achieved with zero training error, i.e., complete over-fitting by memorizing the training data. This is surprising, since it is completely against traditional machine learning wisdom. In our empirical study we fortify these findings in the domain of fine-grained image classification. We show that very large Convolutional Neural Networks with millions of weights do learn with only a handful of training samples and without image augmentation, explicit regular…
Huazhong University of Science and Technology（华中科技大学）；Alibaba Group（阿里巴巴集团）；Ant Group（蚂蚁集团）；MyBank（网商银行）
Fine-Grained Visual Classification (FGVC) is a longstanding and fundamental problem in computer vision and pattern recognition, and underpins a diverse set of real-world applications. This paper describes our contribution at SnakeCLEF2022 with FGVC. Firstly, we design a strong multimodal backbone to utilize various meta-information to assist in fine-grained identification. Secondly, we provide new loss functions to solve the long tail distribution with dataset. Then, in order to take full advantage of unlabeled datasets, we use self-supervised learning and supervised learning joint training to…
Large-scale pretraining of visual representations has led to state-of-the-art performance on a range of benchmark computer vision tasks, yet the benefits of these techniques at extreme scale in complex production systems has been relatively unexplored. We consider the case of a popular visual discovery product, where these representations are trained with multi-task learning, from use-case specific visual understanding (e.g. skin tone classification) to general representation learning for all visual content (e.g. embeddings for retrieval). In this work, we describe how we (1) generate a datase…
Proposal-Contrastive Pretraining for Object Detection from Fewer Data
Université Paris-Saclay（巴黎-萨克雷大学）；CEA（法国原子能委员会）；Université Jean Monnet Saint-Etienne（圣艾蒂安让·莫内大学）；CNRS（法国国家科学研究中心）；Laboratoire Hubert Curien UMR 5516（于贝尔·居里安实验室）；Institut Universitaire de France (IUF)（法国大学研究院）
Pretraining is a dominant paradigm in computer vision. Generally, supervised ImageNet pretraining is commonly used to initialize the backbones of person re-identification (Re-ID) models. However, recent works show a surprising result that CNN-based pretraining on ImageNet has limited impacts on Re-ID system due to the large domain gap between ImageNet and person Re-ID data. To seek an alternative to traditional pretraining, here we investigate semantic-based pretraining as another method to utilize additional textual data against ImageNet pretraining. Specifically, we manually construct a dive…
MedNeXt-v2: Scaling 3D ConvNeXts for Large-Scale Supervised Representation Learning in Medical Image Segmentation
German Cancer Research Center (DKFZ) Heidelberg, Division of Medical Image Computing（德国癌症研究中心（DKFZ）海德堡，医学影像计算部）；Faculty of Mathematics and Computer Science, Heidelberg University（海德堡大学数学与计算机科学学院）；HIDSS4Health - Helmholtz Information and Data Science School for Health, Karlsruhe/Heidelberg, Germany（HIDSS4Health - 欧洲信息与数据科学健康学校，卡尔斯鲁厄/海德堡，德国）；Medical Faculty Heidelberg, Heidelberg University（海德堡大学医学学院）；National Center for Tumor Diseases (NCT), Heidelberg, Germany（肿瘤国家研究中心（NCT），海德堡，德国）；Helmholtz Imaging, German Cancer Research Center, Germany（海德堡成像，德国癌症研究中心，德国）；Pattern Analysis and Learning Group, Department of Radiation Oncology, Heidelberg University Hospital（模式分析与学习组，放射肿瘤学部，海德堡大学医院）
ITO: Multi-View Alignment and Training-Time Fusion for Image-Text Pretraining
School of Computer Science（计算机科学学院）；Huazhong University of Science and Technology（华中科技大学）；Li Auto Inc.（力汽车公司）；Institute of AI for Industries, Chinese Academy of Sciences（产业人工智能研究院，中国科学院）
Mitigating Overfitting in Medical Imaging: Self-Supervised Pretraining vs. ImageNet Transfer Learning for Dermatological Diagnosis
Dpt. of Signal Theory and Communications University of Seville（信号理论与通信系塞维利亚大学）；Department of Dermatology Hospital Universitario Virgen Macarena（皮肤科部门塞维利亚大学医院）；Department of Dermatology Hospital Quirón Salud Sevilla（皮肤科部门Quirón Salud Sevilla医院）
Beijing University of Posts and Telecommunications（北京邮电大学）；Aerospace Information Research Institute, Chinese Academy of Sciences（中国科学院空天信息创新研究院）
Fine-grained visual classification (FGVC) aims to classify sub-classes of objects in the same super-class (e.g., species of birds, models of cars). For the FGVC tasks, the essential solution is to find discriminative subtle information of the target from local regions. TraditionalFGVC models preferred to use the refined features,i.e., high-level semantic information for recognition and rarely use low-level in-formation. However, it turns out that low-level information which contains rich detail information also has effect on improving performance. Therefore, in this paper, we propose cross-lay…
University of Chinese Academy of Sciences（中国科学院大学）；Horizon Robotics（地平线机器人）；Harbin Institute of Technology（哈尔滨工业大学）
The target of 2D human pose estimation is to locate the keypoints of body parts from input 2D images. State-of-the-art methods for pose estimation usually construct pixel-wise heatmaps from keypoints as labels for learning convolution neural networks, which are usually initialized randomly or using classification models on ImageNet as their backbones. We note that 2D pose estimation task is highly dependent on the contextual relationship between image patches, thus we introduce a self-supervised method for pretraining 2D pose estimation networks. Specifically, we propose Heatmap-Style Jigsaw P…
DIET-CP: Lightweight and Data Efficient Self Supervised Continued Pretraining
Fordham University（福特汉姆大学）；Rutgers University（罗格斯大学）；Pioneer Centre for AI（先锋人工智能中心）；Cold Spring Harbor Laboratory（冷泉港实验室）；Brown University（布朗大学）；University of Copenhagen（哥本哈根大学）
TOLiD: Bridging the Architecture Gap in Vision Foundation Model to LiDAR Pretraining via Token Lifting for Distillation
SAIVT Group, School of Electrical Engineering and Robotics, Queensland University of Technology（澳大利亚昆士兰科技大学电气工程与机器人学院SAIVT组）；CSIRO Robotics, CSIRO（澳大利亚联邦科学与工业研究组织机器人部）
GroundingPI: A Grounding Foundation Model towards Physical Intelligence with Visual Primitives
XPeng Inc.（小鹏汽车）；Peking University（北京大学）；The University of Hong Kong（香港大学）；University of California, Berkeley（加州大学伯克利分校）；Princeton University（普林斯顿大学）；National University of Singapore（新加坡国立大学）；Tsinghua University（清华大学）；HKUST (GZ)（香港科技大学（广州））
Purdue University（普渡大学）；Amazon AWS AI Labs（亚马逊AWS人工智能实验室）；OPPO US Research Center（OPPO美国研究中心）
Unsupervised learning of vision transformers seeks to pretrain an encoder via pretext tasks without labels. Among them is the Masked Image Modeling (MIM) aligned with pretraining of language transformers by predicting masked patches as a pretext task. A criterion in unsupervised pretraining is the pretext task needs to be sufficiently hard to prevent the transformer encoder from learning trivial low-level features not generalizable well to downstream tasks. For this purpose, we propose an Adversarial Positional Embedding (AdPE) approach -- It distorts the local visual structures by perturbing …
University of Science and Technology of China（中国科学技术大学）；Microsoft Research Asia（微软亚洲研究院）
We propose bootstrapped masked autoencoders (BootMAE), a new approach for vision BERT pretraining. BootMAE improves the original masked autoencoders (MAE) with two core designs: 1) momentum encoder that provides online feature as extra BERT prediction targets; 2) target-aware decoder that tries to reduce the pressure on the encoder to memorize target-specific information in BERT pretraining. The first design is motivated by the observation that using a pretrained MAE to extract the features as the BERT prediction target for masked tokens can achieve better pretraining performance. Therefore, w…
Diffusion Masked Pretraining for Dynamic Point Cloud
Xi’an Jiaotong University（西安交通大学）；School of Artificial Intelligence and Robotics, Hunan University（湖南大学人工智能与机器人学院）；University of Western Australia（西澳大学）
