CA2: Class-Agnostic Adaptive Feature Adaptation for One-class Classification
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.
Code (0)
등록된 구현이 없습니다.
Tasks
One-Class ClassificationSimilar Papers 제목 키워드 기반
Fast Task Adaptation for Few-Shot Learning
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 LearningDATR: Unsupervised Domain Adaptive Detection Transformer with Dataset-Level Adaptation and Prototypical Alignment
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+1APANet: Adaptive Prototypes Alignment Network for Few-Shot Semantic Segmentation
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 SegmentationDynamic Instance Domain Adaptation
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 AdaptationCoPT: Unsupervised Domain Adaptive Segmentation using Domain-Agnostic Text Embeddings
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