Related papers: Domain-Size Pooling in Local Descriptors: DSP-SIFT

Diffusion-based policies have shown remarkable capability in executing complex robotic manipulation tasks but lack explicit characterization of geometry and semantics, which often limits their ability to generalize to unseen objects and…

Visual localization to compute 6DoF camera pose from a given image has wide applications such as in robotics, virtual reality, augmented reality, etc. Two kinds of descriptors are important for the visual localization. One is global…

Deep Convolutional Neural Networks (DCNNs) commonly use generic `max-pooling' (MP) layers to extract deformation-invariant features, but we argue in favor of a more refined treatment. First, we introduce epitomic convolution as a building…

The application of machine learning to image and video data often yields a high dimensional feature space. Effective feature selection techniques identify a discriminant feature subspace that lowers computational and modeling costs with…

Domain generalization involves learning a classifier from a heterogeneous collection of training sources such that it generalizes to data drawn from similar unknown target domains, with applications in large-scale learning and personalized…

Image representation and classification are two fundamental tasks towards multimedia content retrieval and understanding. The idea that shape and texture information (e.g. edge or orientation) are the key features for visual representation…

To be invariant, or not to be invariant: that is the question formulated in this work about local descriptors. A limitation of current feature descriptors is the trade-off between generalization and discriminative power: more invariance…

In most convolution neural networks (CNNs), downsampling hidden layers is adopted for increasing computation efficiency and the receptive field size. Such operation is commonly so-called pooling. Maximation and averaging over sliding…

Existing convolutional neural networks widely adopt spatial down-/up-sampling for multi-scale modeling. However, spatial up-sampling operators (\emph{e.g.}, interpolation, transposed convolution, and un-pooling) heavily depend on local…

In this paper we focus on the spatial nature of visual domain shift, attempting to learn where domain adaptation originates in each given image of the source and target set. We borrow concepts and techniques from the CNN visualization…

In this work, we connect two distinct concepts for unsupervised domain adaptation: feature distribution alignment between domains by utilizing the task-specific decision boundary and the Wasserstein metric. Our proposed sliced Wasserstein…

Preserving accuracy is a challenging issue in super resolution images. In this paper, we propose a new FFT based image registration algorithm and a sparse based super resolution algorithm to improve the accuracy of super resolution image.…

State-of-the-art stereo matching networks have difficulties in generalizing to new unseen environments due to significant domain differences, such as color, illumination, contrast, and texture. In this paper, we aim at designing a…

The objective of unsupervised domain adaptation is to leverage features from a labeled source domain and learn a classifier for an unlabeled target domain, with a similar but different data distribution. Most deep learning approaches to…

Recent advances in deep learning for medical image segmentation demonstrate expert-level accuracy. However, in clinically realistic environments, such methods have marginal performance due to differences in image domains, including…

Recently, many methods have been proposed for object detection. They cannot detect objects by semantic features, adaptively. In this work, according to channel and spatial attention mechanisms, we mainly analyze that different methods…

The standard closed-set domain adaptation approaches seek to mitigate distribution discrepancies between two domains under the constraint of both sharing identical label sets. However, in realistic scenarios, finding an optimal source…

In this paper, we introduce source domain subset sampling (SDSS) as a new perspective of semi-supervised domain adaptation. We propose domain adaptation by sampling and exploiting only a meaningful subset from source data for training. Our…

Hierarchical visual localization methods achieve state-of-the-art accuracy but require substantial memory as they need to store all database images. Direct 2D-3D matching requires significantly less memory but suffers from lower accuracy…

Single Domain Generalization (SDG) tackles the problem of training a model on a single source domain so that it generalizes to any unseen target domain. While this has been well studied for image classification, the literature on SDG object…