English
Related papers

Related papers: Starbucks-v2: Improved Training for 2D Matryoshka …

200 papers

To achieve high performance of a machine learning (ML) task, a deep learning-based model must implicitly capture the entire distribution from data. Thus, it requires a huge amount of training samples, and data are expected to fully present…

Machine Learning · Computer Science 2021-11-17 Hung Nguyen , Morris Chang

Text embeddings are vital for tasks such as text retrieval and semantic textual similarity (STS). Recently, the advent of pretrained language models, along with unified benchmarks like the Massive Text Embedding Benchmark (MTEB), has…

Computation and Language · Computer Science 2024-10-22 Mingxin Li , Zhijie Nie , Yanzhao Zhang , Dingkun Long , Richong Zhang , Pengjun Xie

Understanding whether self-supervised learning methods can scale with unlimited data is crucial for training large-scale models. In this work, we conduct an empirical study on the scaling capability of masked image modeling (MIM) methods…

Computer Vision and Pattern Recognition · Computer Science 2023-05-25 Cheng-Ze Lu , Xiaojie Jin , Qibin Hou , Jun Hao Liew , Ming-Ming Cheng , Jiashi Feng

Multimodal retrieval relies heavily on single-vector retrievers, which compress rich, sequential token sequences into one single global representation. While efficient, they discard fine-grained, local evidence critical for dense retrieval…

Information Retrieval · Computer Science 2026-05-26 Jianrui Zhang , Hyun Jung Lee , Sukanta Ganguly , Tae-Eui Kam , Donghyun Kim , Yong Jae Lee

In recent years, self-supervised learning has played a pivotal role in advancing machine learning by allowing models to acquire meaningful representations from unlabeled data. An intriguing research avenue involves developing…

Machine Learning · Computer Science 2023-10-30 Denis Janiak , Jakub Binkowski , Piotr Bielak , Tomasz Kajdanowicz

The objective of deep metric learning (DML) is to learn embeddings that can capture semantic similarity and dissimilarity information among data points. Existing pairwise or tripletwise loss functions used in DML are known to suffer from…

Computer Vision and Pattern Recognition · Computer Science 2021-03-22 Xinshao Wang , Yang Hua , Elyor Kodirov , Neil M. Robertson

There is an increasing number of medical use-cases where classification algorithms based on deep neural networks reach performance levels that are competitive with human medical experts. To alleviate the challenges of small dataset sizes,…

Computer Vision and Pattern Recognition · Computer Science 2021-06-28 Vignesh Srinivasan , Nils Strodthoff , Jackie Ma , Alexander Binder , Klaus-Robert Müller , Wojciech Samek

This paper investigates the counterintuitive phenomenon where fine-tuning pre-trained transformer models degrades performance on the MS MARCO passage ranking task. Through comprehensive experiments involving five model variants-including…

Computation and Language · Computer Science 2025-06-24 Manu Pande , Shahil Kumar , Anay Yatin Damle

Developing self-supervised learning (SSL) models that can learn universal and transferable representations of H&E gigapixel whole-slide images (WSIs) is becoming increasingly valuable in computational pathology. These models hold the…

Image and Video Processing · Electrical Eng. & Systems 2024-08-07 Guillaume Jaume , Anurag Vaidya , Andrew Zhang , Andrew H. Song , Richard J. Chen , Sharifa Sahai , Dandan Mo , Emilio Madrigal , Long Phi Le , Faisal Mahmood

Navigation foundation models trained on massive webscale data enable agents to generalize across diverse environments and embodiments. However, these models trained solely on offline data, often lack the capacity to reason about the…

Computer Vision and Pattern Recognition · Computer Science 2025-07-30 Honglin He , Yukai Ma , Wayne Wu , Bolei Zhou

Recent general-purpose audio representations show state-of-the-art performance on various audio tasks. These representations are pre-trained by self-supervised learning methods that create training signals from the input. For example,…

Audio and Speech Processing · Electrical Eng. & Systems 2023-03-09 Daisuke Niizumi , Daiki Takeuchi , Yasunori Ohishi , Noboru Harada , Kunio Kashino

Deep neural networks can be easily fooled into making incorrect predictions through corruption of the input by adversarial perturbations: human-imperceptible artificial noise. So far adversarial training has been the most successful defense…

Computer Vision and Pattern Recognition · Computer Science 2023-03-28 Lin Li , Michael Spratling

Recent foundation models are capable of handling multiple tasks and multiple data modalities with the unified base model structure and several specialized model components. However, efficient training of such multi-task (MT) multi-modal…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-02-12 Yujie Wang , Shenhan Zhu , Fangcheng Fu , Xupeng Miao , Jie Zhang , Juan Zhu , Fan Hong , Yong Li , Bin Cui

The training of deep neural networks is inherently a nonconvex optimization problem, yet standard approaches such as stochastic gradient descent (SGD) require simultaneous updates to all parameters, often leading to unstable convergence and…

Machine Learning · Computer Science 2025-08-07 Chengcheng Yan , Jiawei Xu , Zheng Peng , Qingsong Wang

Metric learning is a fundamental problem in computer vision whereby a model is trained to learn a semantically useful embedding space via ranking losses. Traditionally, the effectiveness of a ranking loss depends on the minibatch size, and…

Computer Vision and Pattern Recognition · Computer Science 2023-03-31 Thalaiyasingam Ajanthan , Matt Ma , Anton van den Hengel , Stephen Gould

ViTs deliver SOTA performance, yet their fixed computational budget prevents scalable deployment across heterogeneous hardware. Recent Matryoshka-style Transformer architectures mitigate this by embedding nested subnetworks within a single…

Computer Vision and Pattern Recognition · Computer Science 2026-03-27 Ali Hojjat , Janek Haberer , Soren Pirk , Olaf Landsiedel

Medical imaging tasks are very challenging due to the lack of publicly available labeled datasets. Hence, it is difficult to achieve high performance with existing deep-learning models as they require a massive labeled dataset to be trained…

Image and Video Processing · Electrical Eng. & Systems 2024-07-23 Anubhav Gupta , Islam Osman , Mohamed S. Shehata , John W. Braun

Accurate and robust medical image classification is paramount for early disease diagnosis and treatment planning. However, challenges such as limited annotated data, high intra-class variability, and subtle inter-class differences often…

Image and Video Processing · Electrical Eng. & Systems 2026-05-22 Joao Florindo , Viviane Moura

As a key medium for human interaction and information exchange, social networking services (SNS) pose unique challenges for large language models (LLMs): heterogeneous workloads, fast-shifting norms and slang, and multilingual, culturally…

Artificial Intelligence · Computer Science 2025-11-11 Fei Zhao , Chonggang Lu , Haofu Qian , Fangcheng Shi , Zijie Meng , Jianzhao Huang , Xu Tang , Zheyong Xie , Zheyu Ye , Zhe Xu , Yao Hu , Shaosheng Cao

How to reduce compute and memory requirements of neural networks (NNs) without sacrificing performance? Many recent works use sparse Mixtures of Experts (MoEs) to build resource-efficient large language models (LMs). Here we introduce…

Machine Learning · Computer Science 2023-11-22 Róbert Csordás , Kazuki Irie , Jürgen Schmidhuber
‹ Prev 1 8 9 10 Next ›