Related papers: Translation Insensitive CNNs
Convolutional neural network (CNN) approaches available in the current literature are designed to work primarily with low-resolution images. When applied on very large images, challenges related to GPU memory, smaller receptive field than…
Convolutional neural networks (CNNs) have been successfully used in a range of tasks. However, CNNs are often viewed as "black-box" and lack of interpretability. One main reason is due to the filter-class entanglement -- an intricate…
Spatial transformer networks (STNs) were designed to enable convolutional neural networks (CNNs) to learn invariance to image transformations. STNs were originally proposed to transform CNN feature maps as well as input images. This enables…
The objective of this paper is the effective transfer of the Convolutional Neural Network (CNN) feature in image search and classification. Systematically, we study three facts in CNN transfer. 1) We demonstrate the advantage of using…
We propose a novel method to increase shift invariance and prediction accuracy in convolutional neural networks. Specifically, we replace the first-layer combination "real-valued convolutions + max pooling" (RMax) by "complex-valued…
Image quality plays a big role in CNN-based image classification performance. Fine-tuning the network with distorted samples may be too costly for large networks. To solve this issue, we propose a transfer learning approach optimized to…
Inspired by two basic mechanisms in animal visual systems, we introduce a feature transform technique that imposes invariance properties in the training of deep neural networks. The resulting algorithm requires less parameter tuning, trains…
Gravity inversion is the problem of estimating subsurface density distributions from observed gravitational field data. We consider the two-dimensional (2D) case, in which recovering density models from one-dimensional (1D) measurements…
Convolutional neural networks have shown remarkable performance in recent years on various computer vision problems. However, the traditional convolutional neural network architecture lacks a critical property: shift equivariance and…
In this paper we propose integrating a priori knowledge into both design and training of convolutional neural networks (CNNs) to learn object representations that are invariant to affine transformations (i.e., translation, scale, rotation).…
In recent years, representation learning approaches have disrupted many multimedia computing tasks. Among those approaches, deep convolutional neural networks (CNNs) have notably reached human level expertise on some constrained image…
Previous work generally believes that improving the spatial invariance of convolutional networks is the key to object counting. However, after verifying several mainstream counting networks, we surprisingly found too strict pixel-level…
Convolution neural network demonstrates great capability for multiple tasks, such as image classification and many others. However, much resource is required to train a network. Hence much effort has been made to accelerate neural network…
Encoding the scale information explicitly into the representation learned by a convolutional neural network (CNN) is beneficial for many computer vision tasks especially when dealing with multiscale inputs. We study, in this paper, a…
Transformers achieve state-of-the-art accuracy and robustness across many tasks, but an understanding of their inductive biases and how those biases differ from other neural network architectures remains elusive. In this work, we identify…
Low-frequency word prediction remains a challenge in modern neural machine translation (NMT) systems. Recent adaptive training methods promote the output of infrequent words by emphasizing their weights in the overall training objectives.…
Convolutional Neural Networks (CNNs) do not have a predictable recognition behavior with respect to the input resolution change. This prevents the feasibility of deployment on different input image resolutions for a specific model. To…
Convolutional neural networks use pooling and other downscaling operations to maintain translational invariance for detection of features, but in their architecture they do not explicitly maintain a representation of the locations of the…
In this paper, we study the sensitivity of CNN outputs with respect to image transformations and noise in the area of fine-grained recognition. In particular, we answer the following questions (1) how sensitive are CNNs with respect to…
Although many studies suggest high performance hand detection methods, those methods are likely to be overfitting. Fortunately, the Convolution Neural Network (CNN) based approach provides a better way that is less sensitive to translation…