相关论文: Series Photo Selection via Multi-view Graph Learni…

We propose sequenced-replacement sampling (SRS) for training deep neural networks. The basic idea is to assign a fixed sequence index to each sample in the dataset. Once a mini-batch is randomly drawn in each training iteration, we refill…

Small-object detection is a challenging problem. In the last few years, the convolution neural networks methods have been achieved considerable progress. However, the current detectors struggle with effective features extraction for…

Self-supervised learning (SSL) methods based on Siamese networks learn visual representations by aligning different views of the same image. The multi-crop strategy, which incorporates small local crops to global ones, enhances many SSL…

Image compression has been applied in the fields of image storage and video broadcasting. However, it's formidably tough to distinguish the subtle quality differences between those distorted images generated by different algorithms. In this…

Size uniformity is one of the main criteria of superpixel methods. But size uniformity rarely conforms to the varying content of an image. The chosen size of the superpixels therefore represents a compromise - how to obtain the fewest…

Clustering multi-view data has been a fundamental research topic in the computer vision community. It has been shown that a better accuracy can be achieved by integrating information of all the views than just using one view individually.…

The effort to understand network systems in increasing detail has resulted in a diversity of methods designed to extract their large-scale structure from data. Unfortunately, many of these methods yield diverging descriptions of the same…

The problem of learning the structure of a high dimensional graphical model from data has received considerable attention in recent years. In many applications such as sensor networks and proteomics it is often expensive to obtain samples…

Recently, there has been a panoptic segmentation task combining semantic and instance segmentation, in which the goal is to classify each pixel with the corresponding instance ID. In this work, we propose a solution to tackle the panoptic…

In this paper we tackle the problem of estimating the 3D pose of object instances, using convolutional neural networks. State of the art methods usually solve the challenging problem of regression in angle space indirectly, focusing on…

Graph neural networks (GNNs) work well when the graph structure is provided. However, this structure may not always be available in real-world applications. One solution to this problem is to infer a task-specific latent structure and then…

Multiview recognition has been well studied in the literature and achieves decent performance in object recognition and retrieval task. However, most previous works rely on supervised learning and some impractical underlying assumptions,…

This paper proposes to go beyond the state-of-the-art deep convolutional neural network (CNN) by incorporating the information from object detection, focusing on dealing with fine-grained image classification. Unfortunately, CNN suffers…

Automated person re-identification in a multi-camera surveillance setup is very important for effective tracking and monitoring crowd movement. In the recent years, few deep learning based re-identification approaches have been developed…

Semantic segmentation, like other fields of computer vision, has seen a remarkable performance advance by the use of deep convolution neural networks. However, considering that neighboring pixels are heavily dependent on each other, both…

Mass spectrometry imaging (MSI) enables label-free visualization of molecular distributions across tissue samples but generates large and complex datasets that require effective peak picking to reduce data size while preserving meaningful…

The recent statistical theory of neural networks focuses on nonparametric denoising problems that treat randomness as additive noise. Variability in image classification datasets does, however, not originate from additive noise but from…

There has recently been great interest in neural rendering methods. Some approaches use 3D geometry reconstructed with Multi-View Stereo (MVS) but cannot recover from the errors of this process, while others directly learn a volumetric…

We propose a novel image sampling method for differentiable image transformation in deep neural networks. The sampling schemes currently used in deep learning, such as Spatial Transformer Networks, rely on bilinear interpolation, which…

Features play a crucial role in computer vision. Initially designed to detect salient elements by means of handcrafted algorithms, features are now often learned by different layers in Convolutional Neural Networks (CNNs). This paper…