paper-with-me

Papers

CA2: Class-Agnostic Adaptive Feature Adaptation for One-class Classification

2023-09-04 · Zilong Zhang, Zhibin Zhao, Deyu Meng, Xingwu Zhang, Xuefeng Chen

One-class classification (OCC), i.e., identifying whether an example belongs to the same distribution as the training data, is essential for deploying machine learning models in the real world. Adapting the pre-trained features on the target dataset has proven to be a promising paradigm for improving OCC performance. Existing methods are constrained by assumptions about the number of classes. This contradicts the real scenario where the number of classes is unknown. In this work, we propose a simple class-agnostic adaptive feature adaptation method (CA2). We generalize the center-based method to unknown classes and optimize this objective based on the prior existing in the pre-trained network, i.e., pre-trained features that belong to the same class are adjacent. CA2 is validated to consistently improve OCC performance across a spectrum of training data classes, spanning from 1 to 1024, outperforming current state-of-the-art methods. Code is available at https://github.com/zhangzilongc/CA2.

📄 PDF Abstract BibTeX arXiv:2309.01483

Code (0)

등록된 구현이 없습니다.

Tasks

One-Class Classification

Similar Papers 제목 키워드 기반

Fast Task Adaptation for Few-Shot Learning

2019-09-25 · Yingying Zhang, Qiaoyong Zhong, Di Xie, ShiLiang Pu

Few-shot classification is a challenging task due to the scarcity of training examples for each class. The key lies in generalization of prior knowledge learned from large-scale base classes and fast adaptation of the cl…

Few-Shot Learning

DATR: Unsupervised Domain Adaptive Detection Transformer with Dataset-Level Adaptation and Prototypical Alignment

2024-05-20 · Jianhong Han, Liang Chen, Yupei Wang

Object detectors frequently encounter significant performance degradation when confronted with domain gaps between collected data (source domain) and data from real-world applications (target domain). To address this tas…

Contrastive LearningDomain Adaptationobject-detectionObject Detection+1

APANet: Adaptive Prototypes Alignment Network for Few-Shot Semantic Segmentation

2021-11-24 · Jiacheng Chen, Bin-Bin Gao, Zongqing Lu, Jing-Hao Xue 외

Few-shot semantic segmentation aims to segment novel-class objects in a given query image with only a few labeled support images. Most advanced solutions exploit a metric learning framework that performs segmentation thr…

Few-Shot Semantic SegmentationMetric LearningSegmentationSemantic Segmentation

Dynamic Instance Domain Adaptation

2022-03-09 · Zhongying Deng, Kaiyang Zhou, Da Li, Junjun He 외

Most existing studies on unsupervised domain adaptation (UDA) assume that each domain's training samples come with domain labels (e.g., painting, photo). Samples from each domain are assumed to follow the same distributi…

Domain AdaptationUnsupervised Domain Adaptation

CoPT: Unsupervised Domain Adaptive Segmentation using Domain-Agnostic Text Embeddings

2025-07-08 · Cristina Mata, Kanchana Ranasinghe, Michael S. Ryoo arxiv

Unsupervised domain adaptation (UDA) involves learning class semantics from labeled data within a source domain that generalize to an unseen target domain. UDA methods are particularly impactful for semantic segmentation…

Unsupervised Domain AdaptationRepresentation LearningSemantic SegmentationImage Classification