Related papers: Camera Bias in a Fine Grained Classification Task
Although recent deep learning-based calibration methods can predict extrinsic and intrinsic camera parameters from a single image, their generalization remains limited by the number and distribution of training data samples. The huge…
This paper proposes a straightforward and cost-effective approach to assess whether a deep neural network (DNN) relies on the primary concepts of training samples or simply learns discriminative, yet simple and irrelevant features that can…
In existing image classification systems that use deep neural networks, the knowledge needed for image classification is implicitly stored in model parameters. If users want to update this knowledge, then they need to fine-tune the model…
Unconstrained video recognition and Deep Convolution Network (DCN) are two active topics in computer vision recently. In this work, we apply DCNs as frame-based recognizers for video recognition. Our preliminary studies, however, show that…
Following the rapidly growing digital image usage, automatic image categorization has become preeminent research area. It has broaden and adopted many algorithms from time to time, whereby multi-feature (generally, hand-engineered features)…
Deep learning models have demonstrated remarkable capabilities in learning complex patterns and concepts from training data. However, recent findings indicate that these models tend to rely heavily on simple and easily discernible features…
Recognition algorithms based on convolutional networks (CNNs) typically use the output of the last layer as feature representation. However, the information in this layer may be too coarse to allow precise localization. On the contrary,…
Deep convolutional neural networks have shown remarkable performance on various computer vision tasks, and yet, they are susceptible to picking up spurious correlations from the training signal. So called `shortcuts' can occur during…
Most current single image camera calibration methods rely on specific image features or user input, and cannot be applied to natural images captured in uncontrolled settings. We propose directly inferring camera calibration parameters from…
Determining the material category of a surface from an image is a demanding task in perception that is drawing increasing attention. Following the recent remarkable results achieved for image classification and object detection utilising…
Recent models for image processing are using the Convolutional neural network (CNN) which requires a pixel per pixel analysis of the input image. This method works well. However, it is time-consuming if we have large images. To increase the…
Convolutional neural networks (CNNs) tend to become a standard approach to solve a wide array of computer vision problems. Besides important theoretical and practical advances in their design, their success is built on the existence of…
We propose a novel approach to enhance the discriminability of Convolutional Neural Networks (CNN). The key idea is to build a tree structure that could progressively learn fine-grained features to distinguish a subset of classes, by…
Deep convolutional networks have achieved the state-of-the-art for semantic image segmentation tasks. However, training these networks requires access to densely labeled images, which are known to be very expensive to obtain. On the other…
Convolutional Neural Network (CNN) is the state-of-the-art for image classification task. Here we have briefly discussed different components of CNN. In this paper, We have explained different CNN architectures for image classification.…
Convolutional Neural Networks (CNN) has been widely applied in the realm of computer vision. However, given the fact that CNN models are translation invariant, they are not aware of the coordinate information of each pixel. Thus the…
CNNs have excelled at performing place recognition over time, particularly when the neural network is optimized for localization in the current environmental conditions. In this paper we investigate the concept of feature map filtering,…
Even though convolutional neural networks can classify objects in images very accurately, it is well known that the attention of the network may not always be on the semantically important regions of the scene. It has been observed that…
Graph Neural Networks (GNNs) have gained popularity in various learning tasks, with successful applications in fields like molecular biology, transportation systems, and electrical grids. These fields naturally use graph data, benefiting…
Convolutional neural networks (CNNs) trained with cross-entropy loss have proven to be extremely successful in classifying images. In recent years, much work has been done to also improve the theoretical understanding of neural networks.…