English
Related papers

Related papers: PD-Loss: Proxy-Decidability for Efficient Metric L…

200 papers

Learning discriminative representations is a central goal of supervised deep learning. While cross-entropy (CE) remains the dominant objective for classification, it does not explicitly enforce desirable geometric properties in the…

Machine Learning · Computer Science 2026-04-13 Matheus Vinícius Todescato , Joel Luís Carbonera

Many industrial applications use Metric Learning as a way to circumvent scalability issues when designing systems with a high number of classes. Because of this, this field of research is attracting a lot of interest from the academic and…

Computer Vision and Pattern Recognition · Computer Science 2020-06-11 Carlos Roig , David Varas , Issey Masuda , Juan Carlos Riveiro , Elisenda Bou-Balust

Deep neural networks (DNNs) are often prone to learn the spurious correlations between target classes and bias attributes, like gender and race, inherent in a major portion of training data (bias-aligned samples), thus showing unfair…

Computer Vision and Pattern Recognition · Computer Science 2024-10-01 Mei Wang , Weihong Deng , Jiani Hu , Sen Su

Learning with noisy labels can significantly hinder the generalization performance of deep neural networks (DNNs). Existing approaches address this issue through loss correction or example selection methods. However, these methods often…

Machine Learning · Computer Science 2024-06-05 Chen-Chen Zong , Ye-Wen Wang , Ming-Kun Xie , Sheng-Jun Huang

Visual Similarity plays an important role in many computer vision applications. Deep metric learning (DML) is a powerful framework for learning such similarities which not only generalize from training data to identically distributed test…

Computer Vision and Pattern Recognition · Computer Science 2020-09-11 Timo Milbich , Karsten Roth , Homanga Bharadhwaj , Samarth Sinha , Yoshua Bengio , Björn Ommer , Joseph Paul Cohen

When Masked Diffusion Models (MDMs) generate sequences through iterative refinement, the rich internal computation over masked positions is discarded, forcing every subsequent refinement step to recompute the valuable internal information…

Image retrieval has become an increasingly appealing technique with broad multimedia application prospects, where deep hashing serves as the dominant branch towards low storage and efficient retrieval. In this paper, we carried out in-depth…

Computer Vision and Pattern Recognition · Computer Science 2022-08-16 Chengyin Xu , Zenghao Chai , Zhengzhuo Xu , Chun Yuan , Yanbo Fan , Jue Wang

Distributed Deep Learning (DDL) is essential for large-scale Deep Learning (DL) training. Synchronous Stochastic Gradient Descent (SSGD) 1 is the de facto DDL optimization method. Using a sufficiently large batch size is critical to…

Machine Learning · Computer Science 2021-12-03 Wei Zhang , Mingrui Liu , Yu Feng , Xiaodong Cui , Brian Kingsbury , Yuhai Tu

A natural desideratum for generative models is self-correction--detecting and revising low-quality tokens at inference. While Masked Diffusion Models (MDMs) have emerged as a promising approach for generative modeling in discrete spaces,…

Machine Learning · Computer Science 2026-05-26 Jaeyeon Kim , Seunggeun Kim , Taekyun Lee , David Z. Pan , Hyeji Kim , Sham Kakade , Sitan Chen

This paper proposes a novel pixel-level distribution regularization scheme (DRSL) for self-supervised domain adaptation of semantic segmentation. In a typical setting, the classification loss forces the semantic segmentation model to…

Computer Vision and Pattern Recognition · Computer Science 2022-06-22 Javed Iqbal , Hamza Rawal , Rehan Hafiz , Yu-Tseh Chi , Mohsen Ali

Density-based distances (DBDs) provide a principled approach to metric learning by defining distances in terms of the underlying data distribution. By employing a Riemannian metric that increases in regions of low probability density,…

Machine Learning · Computer Science 2025-06-02 Peter Sorrenson , Daniel Behrend-Uriarte , Christoph Schnörr , Ullrich Köthe

In this paper, we explore the application of mean field theory, a technique from statistical physics, to deep metric learning and address the high training complexity commonly associated with conventional metric learning loss functions. By…

Machine Learning · Computer Science 2023-06-28 Takuya Furusawa

Many recent loss functions in deep metric learning are expressed with logarithmic and exponential forms, and they involve margin and scale as essential hyper-parameters. Since each data class has an intrinsic characteristic, several…

Audio and Speech Processing · Electrical Eng. & Systems 2023-05-24 Myunghun Jung , Hoirin Kim

Collaborative Metric Learning (CML) has recently emerged as a popular method in recommendation systems (RS), closing the gap between metric learning and Collaborative Filtering. Following the convention of RS, existing methods exploit…

Information Retrieval · Computer Science 2022-10-03 Shilong Bao , Qianqian Xu , Zhiyong Yang , Yuan He , Xiaochun Cao , Qingming Huang

In metric learning, the goal is to learn an embedding so that data points with the same class are close to each other and data points with different classes are far apart. We propose a distance-ratio-based (DR) formulation for metric…

Machine Learning · Computer Science 2022-01-24 Hyeongji Kim , Pekka Parviainen , Ketil Malde

Modern challenges of robustness, fairness, and decision-making in machine learning have led to the formulation of multi-distribution learning (MDL) frameworks in which a predictor is optimized across multiple distributions. We study the…

Machine Learning · Computer Science 2024-12-19 Rajeev Verma , Volker Fischer , Eric Nalisnick

The use of machine learning methods helps to improve decision making in different fields. In particular, the idea of bridging predictions (machine learning models) and prescriptions (optimization problems) is gaining attention within the…

Optimization and Control · Mathematics 2022-11-22 Antonio Alcántara , Carlos Ruiz

We propose Evolutionary Dynamic Loss (EDL), a framework that learns a transferable classification loss in the probability space using unlimited synthetic prediction-label pairs, without accessing real samples during the main loss…

Machine Learning · Computer Science 2026-05-06 Meng Xiang , Yan Pei

Pruning has recently been widely adopted to reduce the parameter scale and improve the inference efficiency of Large Language Models (LLMs). Mainstream pruning techniques often rely on uniform layerwise pruning strategies, which can lead to…

Computation and Language · Computer Science 2025-06-04 Yuli Chen , Bo Cheng , Jiale Han , Yingying Zhang , Yingting Li , Shuhao Zhang

In this paper, we develop a novel efficient and robust nonparametric regression estimator under a framework of feedforward neural network. There are several interesting characteristics for the proposed estimator. First, the loss function is…

Methodology · Statistics 2023-09-25 Xuancheng Wang , Ling Zhou , Huazhen Lin