首页/论文/2012.00904

arXiv 2012.009042020-12-02cs.CVcs.LG

ReMP: Rectified Metric Propagation for Few-Shot Learning

University at Buffalo（布法罗大学）；Microsoft Research（微软研究院）

Yang Zhao, Chunyuan Li, Ping Yu, Changyou Chen

备注：: Tech Report, 11 pages

阅读 PDF ↗

arXiv 页面 ↗HTML 原文 ↗

英文摘要相关论文

英文摘要：

Few-shot learning features the capability of generalizing from a few examples. In this paper, we first identify that a discriminative feature space, namely a rectified metric space, that is learned to maintain the metric consistency from training to testing, is an essential component to the success of metric-based few-shot learning. Numerous analyses indicate that a simple modification of the objective can yield substantial performance gains. The resulting approach, called rectified metric propagation (ReMP), further optimizes an attentive prototype propagation network, and applies a repulsive force to make confident predictions. Extensive experiments demonstrate that the proposed ReMP is effective and efficient, and outperforms the state of the arts on various standard few-shot learning datasets.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

阅读原文

阅读 PDF ↗

arXiv 页面 ↗HTML 原文 ↗

本文内容

英文摘要相关论文

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

继续探索

相关论文

Supervised Domain Adaptation: A Graph Embedding Perspective and a Rectified Experimental Protocol

Aarhus University（奥胡斯大学）

Domain Adaptation is the process of alleviating distribution gaps between data from different domains. In this paper, we show that Domain Adaptation methods using pair-wise relationships between source and target domain data can be formulated as a Graph Embedding in which the domain labels are incorporated into the structure of the intrinsic and penalty graphs. Specifically, we analyse the loss functions of three existing state-of-the-art Supervised Domain Adaptation methods and demonstrate that they perform Graph Embedding. Moreover, we highlight some generalisation and reproducibility issues…

2021-10-24cs.LGstat.ML

A Few-Shot Attention Recurrent Residual U-Net for Crack Segmentation

National Technical University of Athens（雅典国立技术大学）；University of Macedonia（马其顿大学）

Recent studies indicate that deep learning plays a crucial role in the automated visual inspection of road infrastructures. However, current learning schemes are static, implying no dynamic adaptation to users' feedback. To address this drawback, we present a few-shot learning paradigm for the automated segmentation of road cracks, which is based on a U-Net architecture with recurrent residual and attention modules (R2AU-Net). The retraining strategy dynamically fine-tunes the weights of the U-Net as a few new rectified samples are being fed into the classifier. Extensive experiments show that…

2023-03-02cs.CVcs.LGeess.IV

严重声学偏移下的原型修正迭代自监督流形去噪

Prototype-Rectified Iterative Self-supervised Manifold Denoising under Severe Acoustic Shift

Indian Institute of Science Education and Research（印度科学教育与研究学院）；Vellore Institute of Technology（韦洛尔理工大学）

针对严重声学噪声下音频-文本基础模型的失效问题，提出无训练无数据源的TTA框架PRISM，在UrbanSound8K数据集上取得显著性能提升，还解决了复音陷阱问题。

2026-08-18cs.LGcs.SD

Single-Shot Two-Pronged Detector with Rectified IoU Loss

Chongqing University（重庆大学）

In the CNN based object detectors, feature pyramids are widely exploited to alleviate the problem of scale variation across object instances. These object detectors, which strengthen features via a top-down pathway and lateral connections, are mainly to enrich the semantic information of low-level features, but ignore the enhancement of high-level features. This can lead to an imbalance between different levels of features, in particular a serious lack of detailed information in the high-level features, which makes it difficult to get accurate bounding boxes. In this paper, we introduce a nove…

2020-08-08cs.CV

GVCC：基于代码本驱动的随机修正流零样本视频压缩

GVCC: Zero-Shot Video Compression via Codebook-Driven Stochastic Rectified Flow

Graduate School of Fundamental Science and Engineering, Waseda University（早稻田大学基础科学与工程研究生院）

GVCC通过预训练视频生成模型直接作为解码器，在极低比特率下实现高质量视频重建，通过编码生成轨迹的随机创新信息，提升压缩效率。

2026-09-28cs.AIcs.CV

FREE-Edit：使用编辑感知注入在修正流模型中进行零样本图像驱动视频编辑

FREE-Edit: Using Editing-aware Injection in Rectified Flow Models for Zero-shot Image-Driven Video Editing

The University of Hong Kong（香港大学）；International Digital Economy Academy (IDEA)（国际数字经济学院（IDEA））

本文提出FREE-Edit框架，通过编辑感知注入提升图像驱动视频编辑效果，无需微调即可在多种场景中生成高质量输出。

2026-03-22cs.CV

更多相关论文收起更多论文

结合特征引导整流流与知识蒸馏的医学图像分类新One-Shot联邦学习框架

A New One-Shot Federated Learning Framework for Medical Imaging Classification with Feature-Guided Rectified Flow and Knowledge Distillation

Guangdong Provincial Key Laboratory of Ultra High Definition Immersive Media Technology（广东超高清沉浸媒体技术省重点实验室）；Shenzhen Graduate School, Peking University（北京大学深圳研究生院）

本文提出一种改进的One-Shot联邦学习框架，通过特征引导整流流模型加速生成建模并保护隐私，结合双层知识蒸馏聚合方法处理non-IID数据，在医学图像分类任务中显著优于多轮联邦学习方法。

2025-08-11cs.CVcs.DC

SR-GAN: Semantic Rectifying Generative Adversarial Network for Zero-shot Learning

Suzhou University of Science and Technology（苏州科技大学）；Tianjin University（天津大学）；University of Strathclyde（思克莱德大学）

The existing Zero-Shot learning (ZSL) methods may suffer from the vague class attributes that are highly overlapped for different classes. Unlike these methods that ignore the discrimination among classes, in this paper, we propose to classify unseen image by rectifying the semantic space guided by the visual space. First, we pre-train a Semantic Rectifying Network (SRN) to rectify semantic space with a semantic loss and a rectifying loss. Then, a Semantic Rectifying Generative Adversarial Network (SR-GAN) is built to generate plausible visual feature of unseen class from both semantic feature…

2019-04-15cs.CV

可解释的跨领域少样本学习与修正的目标域局部对齐

Interpretable Cross-Domain Few-Shot Learning with Rectified Target-Domain Local Alignment

School of Computer Science and Technology, Huazhong University of Science and Technology（华中科技大学计算机科学与技术学院）

本文提出CC-CDFSL方法，通过循环一致性解决CLIP-based CDFSL中的局部对齐问题，提升局部视觉语言对齐和可解释性，实现SOTA性能。

2026-03-22cs.AIcs.CV

用于跨域小样本分割的域校正适配器

Domain-Rectifying Adapter for Cross-Domain Few-Shot Segmentation

Harbin Institute of Technology, Shenzhen（哈尔滨工业大学（深圳））；Nanjing University（南京大学）

针对跨域小样本语义分割中的域偏移问题，提出DR-Adapter，通过局部-全局风格扰动和循环域对齐学习将目标域特征校正到源域，提升跨域分割性能。

2024-04-16cs.CV

通过区域增强原型Transformer实现少样本医学图像分割

Few-Shot Medical Image Segmentation via a Region-enhanced Prototypical Transformer

Nanjing University of Science and Technology（南京理工大学）；Newcastle University（纽卡斯尔大学）

提出区域增强原型Transformer（RPT），通过细分策略生成区域原型并结合自选择机制的BaT模块消除干扰，迭代优化原型以提升少样本医学图像分割精度。

2023-09-09cs.CV

Exploring Category-correlated Feature for Few-shot Image Classification

Harbin Institute of Technology, Shenzhen（哈尔滨工业大学（深圳））；University of Electronic Science and Technology of China（电子科技大学）

Few-shot classification aims to adapt classifiers to novel classes with a few training samples. However, the insufficiency of training data may cause a biased estimation of feature distribution in a certain class. To alleviate this problem, we present a simple yet effective feature rectification method by exploring the category correlation between novel and base classes as the prior knowledge. We explicitly capture such correlation by mapping features into a latent vector with dimension matching the number of base classes, treating it as the logarithm probability of the feature over base class…

2021-12-14cs.CV

Information Symmetry Matters: A Modal-Alternating Propagation Network for Few-Shot Learning

Tianjin University（天津大学）；Aberystwyth University（阿伯里斯特威斯大学）

Semantic information provides intra-class consistency and inter-class discriminability beyond visual concepts, which has been employed in Few-Shot Learning (FSL) to achieve further gains. However, semantic information is only available for labeled samples but absent for unlabeled samples, in which the embeddings are rectified unilaterally by guiding the few labeled samples with semantics. Therefore, it is inevitable to bring a cross-modal bias between semantic-guided samples and nonsemantic-guided samples, which results in an information asymmetry problem. To address this problem, we propose a…

2021-09-03cs.AIcs.CLcs.CV