Chromosome recognition is an essential task in karyotyping, which plays a vital role in birth defect diagnosis and biomedical research. However, existing classification methods face significant challenges due to the inter-class similarity and intra-class variation of chromosomes. To address this issue, we propose a supervised contrastive learning strategy that is tailored to train model-agnostic deep networks for reliable chromosome classification. This method enables extracting fine-grained chromosomal embeddings in latent space. These embeddings effectively expand inter-class boundaries and reduce intra-class variations, enhancing their distinctiveness in predicting chromosome types. On top of two large-scale chromosome datasets, we comprehensively validate the power of our contrastive learning strategy in boosting cutting-edge deep networks such as Transformers and ResNets. Extensive results demonstrate that it can significantly improve models' generalization performance, with an accuracy improvement up to +4.5%. Codes and pretrained models will be released upon acceptance of this work.
CDNet: Contrastive Disentangled Network for Fine-Grained Image Categorization of Ocular B-Scan Ultrasound
Hangzhou Dianzi University（杭州电子科技大学）；the Second Affiliated Hospital of Zhejiang University（浙江大学医学院附属第二医院）；Waseda University（早稻田大学）；Communication University of Zhejiang（浙江传媒学院）
Balanced Hierarchical Contrastive Learning with Decoupled Queries for Fine-grained Object Detection in Remote Sensing Images
School of Computer Science and Engineering, Nanjing University of Science and Technology, China（南京理工大学计算机科学与工程学院）；College of Computer Science, Zhejiang University, China（浙江大学计算机学院）
Towards Fine-grained Visual Representations by Combining Contrastive Learning with Image Reconstruction and Attention-weighted Pooling
Bayer AG（拜耳股份公司）
本文介绍了对比重建，ConRec -一种自监督学习算法，通过联合优化对比和自重建损失来获得图像表示。我们展示了最先进的对比学习方法（例如Simplified）在其表示中捕获细粒度视觉特征方面存在缺陷。ConRec通过添加（1）自我重建任务和（2）对比学习任务中的注意力机制扩展了Simplified框架。这是通过应用具有两个头的简单编码器-解码器架构来实现的。我们表明，这两个扩展有助于改善图像的矢量表示与细粒度的视觉特征。结合这些概念，ConRec在细粒度分类数据集上的性能优于Simplified和Simplified with Attention-Pooling。
Fine-grained Temporal Contrastive Learning for Weakly-supervised Temporal Action Localization
Institute of Automation, Chinese Academy of Sciences (CASIA)（中国科学院自动化研究所）；University of Chinese Academy of Sciences (UCAS)（中国科学院大学）；Peng Cheng Laboratory（鹏城实验室）
COMICS: End-to-end Bi-grained Contrastive Learning for Multi-face Forgery Detection
University of Chinese Academy of Sciences（中国科学院大学）；Institute of Computing Technology, Chinese Academy of Sciences（中国科学院计算技术研究所）；Pengcheng Laboratory（鹏城实验室）；College of Computer Science and Technology, Ocean University of China（中国海洋大学计算机科学与技术学院）；University at Buffalo, SUNY（纽约州立大学布法罗分校）
Extremely Fine-Grained Visual Classification over Resembling Glyphs in the Wild
School of Computer and Information Engineering, Henan University（河南大学计算机与信息工程学院）；UPV/EHU（巴斯克大学）；IKERBASQUE, Basque Foundation for Science（巴斯克科学基金会（IKERBASQUE））
Wavelet-Decoupling Contrastive Enhancement Network for Fine-Grained Skeleton-Based Action Recognition
Beijing Engineering Research Center of Mixed Reality and Advanced Display（北京混合现实与先进显示工程研究中心）；School of Optics and Photonics, Beijing Institute of Technology（北京理工大学光电学院）
H3Former: Hypergraph-based Semantic-Aware Aggregation via Hyperbolic Hierarchical Contrastive Loss for Fine-Grained Visual Classification
College of Computer Science and Technology, Jilin University（吉林大学计算机科学与技术学院）；College of Software, Jilin University（吉林大学软件学院）；School of Software, Tsinghua University（清华大学软件学院）
A Multihead Continual Learning Framework for Fine-Grained Fashion Image Retrieval with Contrastive Learning and Exponential Moving Average Distillation
Graduate School of Information Science and Technology, Hokkaido University（信息科学与技术研究生院，北海道大学）；Graduate School of Information Science and Technology, The University of Tokyo（信息科学与技术研究生院，东京大学）
AFiRe: Anatomy-Driven Self-Supervised Learning for Fine-Grained Representation in Radiographic Images
School of Computer Science and Technology, Tongji University（同济大学计算机科学与技术学院）；Shanghai Eye Diseases Prevention and Treatment Center, Shanghai Eye Hospital（上海市眼病防治中心、上海眼科医院）；School of Communication and Electronic Engineering, East China Normal University（华东师范大学通信与电子工程学院）
RealRAG: Retrieval-augmented Realistic Image Generation via Self-reflective Contrastive Learning
The Hong Kong University of Science（香港科学与技术大学）；Guangxi Key Laboratory of Digital Infrastructure, Guangxi Zhuang Autonomous Region Information Center（广西数字基础设施重点实验室，广西壮族自治区信息中心）；Shanghai Jiao Tong University（上海交通大学）
Learning Attentive Pairwise Interaction for Fine-Grained Classification
Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences（中国科学院深圳先进技术研究院）；Shenzhen Institute of Artificial Intelligence and Robotics for Society（深圳人工智能与机器人研究院）
Efficient Token-Guided Image-Text Retrieval with Consistent Multimodal Contrastive Training
Institute of Software, Chinese Academy of Sciences（中国科学院软件研究所）；Alibaba Group（阿里巴巴集团）；Southeast University（东南大学）；Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）
Clinically-Informed Modeling for Pediatric Brain Tumor Classification from Whole-Slide Histopathology Images
Dept. of Computer Science（计算机科学系）；University of Texas at Austin（德克萨斯大学奥斯汀分校）；School of Information（信息学院）；Dell Children's Medical Center（德尔儿童医学中心）；Dept. of OREI（OREI部门）；University of Nevada, Reno（内华达大学里诺分校）
