Related papers: Deep Metric Learning Beyond Binary Supervision

Stereo vision generally involves the computation of pixel correspondences and estimation of disparities between rectified image pairs. In many applications, including simultaneous localization and mapping (SLAM) and 3D object detection, the…

As a highlighting research topic in the multimedia area, cross-media retrieval aims to capture the complex correlations among multiple media types. Learning better shared representation and distance metric for multimedia data is important…

Continual learning aims to update a model so that it can sequentially learn new tasks without forgetting previously acquired knowledge. Recent continual learning approaches often leverage the vision-language model CLIP for its…

Recently, as an effective way of learning latent representations, contrastive learning has been increasingly popular and successful in various domains. The success of constrastive learning in single-label classifications motivates us to…

With the explosion of digital data in recent years, continuously learning new tasks from a stream of data without forgetting previously acquired knowledge has become increasingly important. In this paper, we propose a new continual learning…

Semi-supervised learning frameworks usually adopt mutual learning approaches with multiple submodels to learn from different perspectives. To avoid transferring erroneous pseudo labels between these submodels, a high threshold is usually…

Recently, learning from vast unlabeled data, especially self-supervised learning, has been emerging and attracted widespread attention. Self-supervised learning followed by the supervised fine-tuning on a few labeled examples can…

The usage of convolutional neural networks (CNNs) for unsupervised image segmentation was investigated in this study. In the proposed approach, label prediction and network parameter learning are alternately iterated to meet the following…

Deep hashing models have been proposed as an efficient method for large-scale similarity search. However, most existing deep hashing methods only utilize fine-level labels for training while ignoring the natural semantic hierarchy…

Depth completion is an important vision task, and many efforts have been made to enhance the quality of depth maps from sparse depth measurements. Despite significant advances, training these models to recover dense depth from sparse…

Modern video person re-identification (re-ID) machines are often trained using a metric learning approach, supervised by a triplet loss. The triplet loss used in video re-ID is usually based on so-called clip features, each aggregated from…

Image retrieval methods rely on metric learning to train backbone feature extraction models that can extract discriminant queries and reference (gallery) feature representations for similarity matching. Although state-of-the-art accuracy…

It is critical and meaningful to make image classification since it can help human in image retrieval and recognition, object detection, etc. In this paper, three-sides efforts are made to accomplish the task. First, visual features with…

In the past few years, the field of computer vision has gone through a revolution fueled mainly by the advent of large datasets and the adoption of deep convolutional neural networks for end-to-end learning. The person re-identification…

Aiming at improving performance of visual classification in a cost-effective manner, this paper proposes an incremental semi-supervised learning paradigm called Deep Co-Space (DCS). Unlike many conventional semi-supervised learning methods…

We present a multiview pseudo-labeling approach to video learning, a novel framework that uses complementary views in the form of appearance and motion information for semi-supervised learning in video. The complementary views help obtain…

We propose a semantic similarity metric for image registration. Existing metrics like Euclidean Distance or Normalized Cross-Correlation focus on aligning intensity values, giving difficulties with low intensity contrast or noise. Our…

Deep-learning metrics have recently demonstrated extremely good performance to match image patches for stereo reconstruction. However, training such metrics requires large amount of labeled stereo images, which can be difficult or costly to…

Semi-supervised learning aims to boost the accuracy of a model by exploring unlabeled images. The state-of-the-art methods are consistency-based which learn about unlabeled images by encouraging the model to give consistent predictions for…

Multi-label image classification allows predicting a set of labels from a given image. Unlike multiclass classification, where only one label per image is assigned, such a setup is applicable for a broader range of applications. In this…