相关论文: multi-patch aggregation models for resampling dete…

3D shape analysis is an important research topic in computer vision and graphics. While existing methods have generalized image-based deep learning to meshes using graph-based convolutions, the lack of an effective pooling operation…

Recently, very deep convolutional neural networks (CNNs) have shown outstanding performance in object recognition and have also been the first choice for dense classification problems such as semantic segmentation. However, repeated…

Hyper-parameter selection remains a daunting task when building a pattern recognition architecture which performs well, particularly in recently constructed visual pipeline models for feature extraction. We re-formulate pooling in an…

Motivated by the emerging needs of personalized preventative intervention in many healthcare applications, we consider a multi-stage, dynamic decision-making problem in the online setting with unknown model parameters. To deal with the…

Image forensics, aiming to ensure the authenticity of the image, has made great progress in dealing with common image manipulation such as copy-move, splicing, and inpainting in the past decades. However, only a few researchers pay…

Many computer vision systems require low-cost segmentation algorithms based on deep learning, either because of the enormous size of input images or limited computational budget. Common solutions uniformly downsample the input images to…

Pooling is a critical operation in convolutional neural networks for increasing receptive fields and improving robustness to input variations. Most existing pooling operations downsample the feature maps, which is a lossy process. Moreover,…

Based on an idea in [4] we propose a new iterative multiplicative filtering algorithm for label assignment matrices which can be used for the supervised partitioning of data. Starting with a row-normalized matrix containing the averaged…

The pooling operation is a cornerstone element of convolutional neural networks. These elements generate receptive fields for neurons, in which local perturbations should have minimal effect on the output activations, increasing robustness…

Recently, image representation built upon Convolutional Neural Network (CNN) has been shown to provide effective descriptors for image search, outperforming pre-CNN features as short-vector representations. Yet such models are not…

In modern computer vision tasks, convolutional neural networks (CNNs) are indispensable for image classification tasks due to their efficiency and effectiveness. Part of their superiority compared to other architectures, comes from the fact…

This paper addresses the problem of very large-scale image retrieval, focusing on improving its accuracy and robustness. We target enhanced robustness of search to factors such as variations in illumination, object appearance and scale,…

Downsampling is widely adopted to achieve a good trade-off between accuracy and latency for visual recognition. Unfortunately, the commonly used pooling layers are not learned, and thus cannot preserve important information. As another…

The task of learning from point cloud data is always challenging due to the often occurrence of noise and outliers in the data. Such data inaccuracies can significantly influence the performance of state-of-the-art deep learning networks…

Person re identification is a challenging retrieval task that requires matching a person's acquired image across non overlapping camera views. In this paper we propose an effective approach that incorporates both the fine and coarse pose…

We study non-adaptive pooling strategies for detection of rare faulty items. Given a binary sparse N-dimensional signal x, how to construct a sparse binary MxN pooling matrix F such that the signal can be reconstructed from the smallest…

A novel algorithm is proposed for segmenting an image into multiple levels using its mean and variance. Starting from the extreme pixel values at both ends of the histogram plot, the algorithm is applied recursively on sub-ranges computed…

Dataset distillation provides an effective approach to reduce memory and computational costs by optimizing a compact dataset that achieves performance comparable to the full original. However, for large-scale datasets and complex deep…

Recent advances in deep-learning based methods for image matching have demonstrated their superiority over traditional algorithms, enabling correspondence estimation in challenging scenes with significant differences in viewing angles,…

The growth and success of deep learning approaches can be attributed to two major factors: availability of hardware resources and availability of large number of training samples. For problems with large training databases, deep learning…