Another barrier in dental imaging is the limited number of available images for training, which is a challenge in the era of deep learning.
In spite of many advances, most of the approaches require a large amount of labeled data, which is often not available, due to costs and difficulties of manual labeling processes.
High effective results demonstrate the effectiveness of the proposed method on different tasks: unsupervised image retrieval, semi-supervised classification, and person Re-ID.
In our work, we propose to aggregate features from pretrained images and text embeddings to learn abstract visual concepts from GCD.
To the best of our knowledge, this is the first study that applied self-supervised learning methods to Swin Transformer on dental panoramic radiographs.
The recent advances of compressing high-accuracy convolution neural networks (CNNs) have witnessed remarkable progress for real-time object detection.
Ranked #12 on Object Detection on PASCAL VOC 2007
Due to the powerful ability to encode image details and semantics, many lightweight dual-resolution networks have been proposed in recent years.
Object detection often costs a considerable amount of computation to get satisfied performance, which is unfriendly to be deployed in edge devices.
Generating high-quality stitched images with natural structures is a challenging task in computer vision.
As an essential part of structure from motion (SfM) and Simultaneous Localization and Mapping (SLAM) systems, motion averaging has been extensively studied in the past years and continues to attract surging research attention.
Exploring contextual information in convolution neural networks (CNNs) has gained substantial attention in recent years for semantic segmentation.
Entropy minimization has been widely used in unsupervised domain adaptation (UDA).
Ranked #6 on Domain Adaptation on ImageCLEF-DA
Feature pyramid architecture has been broadly adopted in object detection and segmentation to deal with multi-scale problem.
LEDNet: A Lightweight Encoder-Decoder Network for Real-time Semantic Segmentation
Ranked #29 on Real-Time Semantic Segmentation on Cityscapes test
Recurrent neural networks (RNNs) have shown the ability to improve scene parsing through capturing long-range dependencies among image units.
Our new restart strategy is based on the re-occurrence of a local search scenario instead of that of a candidate solution.
This stimulates a great research interest of considering similarity fusion in the framework of diffusion process (i. e., fusion with diffusion) for robust retrieval.
We revisit the amodal 3D detection problem by sticking to the 2. 5D representation framework, and directly relate 2. 5D visual appearance to 3D objects.
We name the proposed 3D shape search engine, which combines GPU acceleration and Inverted File Twice, as GIFT.