paper-with-me

홈 › Papers

Unsupervised Learning of Discriminative Attributes and Visual Representations

2016-06-01 · CVPR 2016 6 · Chen Huang, Chen Change Loy, Xiaoou Tang

Attributes offer useful mid-level features to interpret visual data. While most attribute learning methods are supervised by costly human-generated labels, we introduce a simple yet powerful unsupervised approach to learn and predict visual attributes directly from data. Given a large unlabeled image collection as input, we train deep Convolutional Neural Networks (CNNs) to output a set of discriminative, binary attributes often with semantic meanings. Specifically, we first train a CNN coupled with unsupervised discriminative clustering, and then use the cluster membership as a soft supervision to discover shared attributes from the clusters while maximizing their separability. The learned attributes are shown to be capable of encoding rich imagery properties from both natural images and contour patches. The visual representations learned in this way are also transferrable to other tasks such as object detection. We show other convincing results on the related tasks of image retrieval and classification, and contour detection.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

AttributeClusteringContour DetectionImage Retrievalobject-detectionObject DetectionRetrieval

Similar Papers 제목 키워드 기반

The red one!: On learning to refer to things based on their discriminative properties

2016-03-08 · Angeliki Lazaridou, Nghia The Pham, Marco Baroni

As a first step towards agents learning to communicate about their visual environment, we propose a system that, given visual representations of a referent (cat) and a context (sofa), identifies their discriminative attr…

Attribute

Unsupervised Discriminative Embedding for Sub-Action Learning in Complex Activities

2021-04-30 · Sirnam Swetha, Hilde Kuehne, Yogesh S Rawat, Mubarak Shah

Action recognition and detection in the context of long untrimmed video sequences has seen an increased attention from the research community. However, annotation of complex activities is usually time consuming and chall…

Action RecognitionAction Segmentation

Shaping Visual Representations with Attributes for Few-Shot Recognition

2021-12-13 · Haoxing Chen, Huaxiong Li, Yaohui Li, Chunlin Chen

Few-shot recognition aims to recognize novel categories under low-data regimes. Some recent few-shot recognition methods introduce auxiliary semantic modality, i.e., category attribute information, into representation le…

AttributeFew-Shot LearningMetric LearningRepresentation Learning

Discriminative Learning of Latent Features for Zero-Shot Recognition

2018-03-18 · CVPR 2018 6 · Yan Li, Junge Zhang, Jian-Guo Zhang, Kaiqi Huang

Zero-shot learning (ZSL) aims to recognize unseen image categories by learning an embedding space between image and semantic representations. For years, among existing works, it has been the center task to learn the prop…

Zero-Shot Learning

UNBNLP at SemEval-2018 Task 10: Evaluating unsupervised approaches to capturing discriminative attributes

2018-06-01 · SEMEVAL 2018 6 · Milton King, Ali Hakimi Parizi, Paul Cook

In this paper we present three unsupervised models for capturing discriminative attributes based on information from word embeddings, WordNet, and sentence-level word co-occurrence frequency. We show that, of these appro…

Semantic Textual SimilaritySentenceWord Embeddings