Local Convolutional Features With Unsupervised Training for Image Retrieval
Patch-level descriptors underlie several important computer vision tasks, such as stereo-matching or content-based image retrieval. We introduce a deep convolutional architecture that yields patch-level descriptors, as an alternative to the popular SIFT descriptor for image retrieval. The proposed family of descriptors, called Patch-CKN, adapt the recently introduced Convolutional Kernel Network (CKN), an unsupervised framework to learn convolutional architectures. We present a comparison framework to benchmark current deep convolutional approaches along with Patch-CKN for both patch and image retrieval, including our novel ``RomePatches'' dataset. Patch-CKN descriptors yield competitive results compared to supervised CNN alternatives on patch and image retrieval.
Code (0)
등록된 구현이 없습니다.
Tasks
Content-Based Image RetrievalImage RetrievalRetrievalStereo MatchingStereo Matching HandSimilar Papers 제목 키워드 기반
Principal Feature Visualisation in Convolutional Neural Networks
We introduce a new visualisation technique for CNNs called Principal Feature Visualisation (PFV). It uses a single forward pass of the original network to map principal features from the final convolutional layer to the …
Transfer LearningFastFlow: Unsupervised Anomaly Detection and Localization via 2D Normalizing Flows
Unsupervised anomaly detection and localization is crucial to the practical application when collecting and labeling sufficient anomaly data is infeasible. Most existing representation-based approaches extract normal ima…
Anomaly DetectionUnsupervised Anomaly DetectionWeakly Supervised Defect DetectionPatchRot: A Self-Supervised Technique for Training Vision Transformers
Vision transformers require a huge amount of labeled data to outperform convolutional neural networks. However, labeling a huge dataset is a very expensive process. Self-supervised learning techniques alleviate this prob…
Self-Supervised LearningConvolutional Sparse Kernel Network for Unsupervised Medical Image Analysis
The availability of large-scale annotated image datasets and recent advances in supervised deep learning methods enable the end-to-end derivation of representative image features that can impact a variety of image analys…
Image RetrievalMedical Image AnalysisMedical Image RetrievalRetrievalUnsupervised Deep Transfer Feature Learning for Medical Image Classification
The accuracy and robustness of image classification with supervised deep learning are dependent on the availability of large-scale, annotated training data. However, there is a paucity of annotated data available due to …
ClassificationGeneral Classificationimage-classificationImage Classification+1