Generalizable Embeddings with Cross-batch Metric Learning
OGAM-METU（中东技术大学OGAM）
Yeti Z. Gurbuz, A. Aydin Alatan
备注：
\c{opyright} 2023 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works
Global average pooling (GAP) is a popular component in deep metric learning (DML) for aggregating features. Its effectiveness is often attributed to treating each feature vector as a distinct semantic entity and GAP as a combination of them. Albeit substantiated, such an explanation's algorithmic implications to learn generalizable entities to represent unseen classes, a crucial DML goal, remain unclear. To address this, we formulate GAP as a convex combination of learnable prototypes. We then show that the prototype learning can be expressed as a recursive process fitting a linear predictor to a batch of samples. Building on that perspective, we consider two batches of disjoint classes at each iteration and regularize the learning by expressing the samples of a batch with the prototypes that are fitted to the other batch. We validate our approach on 4 popular DML benchmarks.
Toward Generalizable Cognitive Impairment Detection with Speech-Based Multimodal Large Language Models
Faculty of Digital Innovation, Arts \& Sciences, Saskatchewan Polytechnic, Regina SK S4S 5X1, Canada；School of Basic Medical Sciences, Hebei University, Baoding 071000, China；Department of Civil \& Environmental Engineering；School of Mining \& Petroleum Engineering, University of Alberta, Edmonton AB T6G 2H5, Canada
CAMEL-CLIP: Channel-aware Multimodal Electroencephalography-text Alignment for Generalizable Brain Foundation Models
Department of Computer Science and Engineering（计算机科学与工程系）；Incheon National University（庆尚国立大学）；Department of Artificial Intelligence（人工智能系）；Inha University（Inha大学）；Center for Brain-Machine Interface（脑机接口中心）
Embedding Space Interpolation Beyond Mini-Batch, Beyond Pairs and Beyond Examples
Inria（法国国家信息与自动化研究所）；Univ Rennes（雷恩大学）；CNRS（法国国家科学研究中心）；IRISA（IRISA研究所）；Institute of Advanced Research on Artificial Intelligence (IARAI)（人工智能高级研究所（IARAI））
Learning Less Generalizable Patterns with an Asymmetrically Trained Double Classifier for Better Test-Time Adaptation
Univ Lyon（里昂大学）；Ecole Centrale de Lyon（里昂中央理工学院）；CNRS（法国国家科学研究中心）；INSA Lyon（里昂国立应用科学学院）；Univ Claude Bernard Lyon 1（里昂第一大学克洛德·贝尔纳）；Univ Louis Lumière Lyon 2（里昂第二大学路易·卢米埃尔）；Thales LAS France（泰雷兹LAS法国公司）
Embedding Is (Almost) All You Need: Retrieval-Augmented Inference for Generalizable Genomic Prediction Tasks
Department of Computer Science and Engineering, Bangladesh University of Engineering and Technology（孟加拉工程与技术大学计算机科学与工程系）；Department of Computer Science and Engineering, BRAC University（布拉克大学计算机科学与工程系）
DinoBloom: A Foundation Model for Generalizable Cell Embeddings in Hematology
Helmholtz Munich（亥姆霍兹慕尼黑中心）；Ludwig-Maximilians-University Munich（慕尼黑大学）；Dr. von Haunersches Kinderspital（冯·豪内尔施儿童医院）；King’s College London（伦敦国王学院）；Technical University of Munich（慕尼黑工业大学）；School of Biomedical Engineering and Imaging Sciences, King’s College London（伦敦国王学院生物医学工程与影像科学学院）；School of Computation, Information and Technology, Technical University of Munich（慕尼黑工业大学计算、信息与技术学院）
Linear Embedding-based High-dimensional Batch Bayesian Optimization without Reconstruction Mappings
Graduate School of Information Science and Technology（信息科学技术研究生院）；The University of Tokyo（东京大学）；NTT Communication Science Laboratories（NTT通信科学实验室）；Epistra Inc.（Epistra公司）
TG-NAS: Generalizable Zero-Cost Proxies with Operator Description Embedding and Graph Learning for Efficient Neural Architecture Search
Department of EECS, University of California, Irvine（电子工程与计算机科学系，加州大学伊市分校）；Department of Computer Science, University of California, San Diego（计算机科学系，加州大学圣地亚哥分校）
LMAE4Eth: Generalizable and Robust Ethereum Fraud Detection by Exploring Transaction Semantics and Masked Graph Embedding
Yantai Research Institute, Harbin Engineering University（哈尔滨工程大学烟台研究院）；Hangzhou Research Institute, Xidian University（西安电子科技大学杭州研究院）；College of Computer Science, Zhejiang University（浙江大学计算机学院）
Histopathology Image Normalization via Latent Manifold Compaction
Knight Cancer Institute, Oregon Health and Science University（骑士癌症研究所，俄勒冈健康与科学大学）；Brenden-Colson Center for Pancreatic Care, Oregon Health and Science University（布雷登-科尔森胰腺护理中心，俄勒冈健康与科学大学）
Generalizable IoT Traffic Representations for Cross-Network Device Identification
School of Electrical Engineering and Telecommunications, University of New South Wales（新南威尔士大学电子工程与电信学院）；School of Computer Science and Engineering, University of New South Wales（新南威尔士大学计算机科学与工程学院）；School of Computing, Macquarie University（麦考瑞大学计算机学院）；Information Sciences Division, Defence Science & Technology Group（国防科学与技术集团信息科学部）
CAAT-EHR: Cross-Attentional Autoregressive Transformer for Multimodal Electronic Health Record Embeddings
Department of Computer Science and Engineering, University of North Texas（计算机科学与工程系，北卡罗来纳大学达顿分校）；BioDiscovery Institute, University of North Texas（生物发现研究所，北卡罗来纳大学达顿分校）；Center for Computational Life Sciences, University of North Texas（计算生命科学中心，北卡罗来纳大学达顿分校）
Institute of Analytics and Data Science, Kennesaw State University（肯尼索州立大学分析与数据科学研究所）；Department of Information Technology, Kennesaw State University（肯尼索州立大学信息技术系）
