Related papers: Feature Fusion for Robust Patch Matching With Comp…

Existing learning-based point feature descriptors are usually task-agnostic, which pursue describing the individual 3D point clouds as accurate as possible. However, the matching task aims at describing the corresponding points consistently…

Learning feature representation from discriminative local regions plays a key role in fine-grained visual classification. Employing attention mechanisms to extract part features has become a trend. However, there are two major limitations…

Although synthetic data can alleviate acquisition challenges in image dehazing tasks, it also introduces the problem of domain bias when dealing with small-scale data. This paper proposes a novel dual-branch collaborative unpaired dehazing…

The success of deep neural networks in image classification and learning can be partly attributed to the features they extract from images. It is often speculated about the properties of a low-dimensional manifold that models extract and…

Occluded person re-identification is one of the challenging areas of computer vision, which faces problems such as inefficient feature representation and low recognition accuracy. Convolutional neural network pays more attention to the…

The tracking-by-detection framework receives growing attentions through the integration with the Convolutional Neural Networks (CNNs). Existing tracking-by-detection based methods, however, fail to track objects with severe appearance…

Local feature extraction is a standard approach in computer vision for tackling important tasks such as image matching and retrieval. The core assumption of most methods is that images undergo affine transformations, disregarding more…

Domain adaptation aims at training a classifier in one dataset and applying it to a related but not identical dataset. One successfully used framework of domain adaptation is to learn a transformation to match both the distribution of the…

In this paper, we propose a learning-based image fragment pair-searching and -matching approach to solve the challenging restoration problem. Existing works use rule-based methods to match similar contour shapes or textures, which are…

Feature alignment between domains is one of the mainstream methods for Unsupervised Domain Adaptation (UDA) semantic segmentation. Existing feature alignment methods for semantic segmentation learn domain-invariant features by adversarial…

In this paper, we study the problem of transfer learning with the attribute data. In the transfer learning problem, we want to leverage the data of the auxiliary and the target domains to build an effective model for the classification…

Transfer learning for feature extraction can be used to exploit deep representations in contexts where there is very few training data, where there are limited computational resources, or when tuning the hyper-parameters needed for training…

Federated Learning (FL) faces significant challenges with domain shifts in heterogeneous data, degrading performance. Traditional domain generalization aims to learn domain-invariant features, but the federated nature of model averaging…

Feature fusion is a commonly used strategy in image retrieval tasks, which aggregates the matching responses of multiple visual features. Feasible sets of features can be either descriptors (SIFT, HSV) for an entire image or the same…

Fusing LiDAR and image features in a homogeneous BEV domain has become popular for 3D object detection in autonomous driving. However, this paradigm is constrained by the excessive feature compression. While some works explore dense voxel…

Applying feature dependent network weights have been proved to be effective in many fields. However, in practice, restricted by the enormous size of model parameters and memory footprints, scalable and versatile dynamic convolutions with…

There is a growing interest in designing models that can deal with images from different visual domains. If there exists a universal structure in different visual domains that can be captured via a common parameterization, then we can use a…

Spatial optimization is often overlooked in many computer vision tasks. Filters should be able to recognize the features of an object regardless of where it is in the image. Similarity search is a crucial task where spatial features decide…

In image-to-image translation, each patch in the output should reflect the content of the corresponding patch in the input, independent of domain. We propose a straightforward method for doing so -- maximizing mutual information between the…

We propose a convolutional neural network (ConvNet) based approach for learning local image descriptors which can be used for significantly improved patch matching and 3D reconstructions. A multi-resolution ConvNet is used for learning…