相关论文: Attentive Normalization

Irregular text is widely used. However, it is considerably difficult to recognize because of its various shapes and distorted patterns. In this paper, we thus propose a multi-object rectified attention network (MORAN) for general scene text…

Feature fusion, the combination of features from different layers or branches, is an omnipresent part of modern network architectures. It is often implemented via simple operations, such as summation or concatenation, but this might not be…

Learning with few labeled data is a key challenge for visual recognition, as deep neural networks tend to overfit using a few samples only. One of the Few-shot learning methods called metric learning addresses this challenge by first…

Batch normalization (BN) is comprised of a normalization component followed by an affine transformation and has become essential for training deep neural networks. Standard initialization of each BN in a network sets the affine…

Adversarial training has been successfully applied to build robust models at a certain cost. While the robustness of a model increases, the standard classification accuracy declines. This phenomenon is suggested to be an inherent trade-off.…

We propose a convolutional neural network (CNN) architecture for image classification based on subband decomposition of the image using wavelets. The proposed architecture decomposes the input image spectra into multiple critically sampled…

Training quantised neural networks (QNNs) is a non-differentiable optimisation problem since weights and features are output by piecewise constant functions. The standard solution is to apply the straight-through estimator (STE), using…

Training a fine-grained image recognition model with limited data presents a significant challenge, as the subtle differences between categories may not be easily discernible amidst distracting noise patterns. One commonly employed strategy…

Different features have different relevance to a particular learning problem. Some features are less relevant; while some very important. Instead of selecting the most relevant features using feature selection, an algorithm can be given…

Normalization techniques have become a basic component in modern convolutional neural networks (ConvNets). In particular, many recent works demonstrate that promoting the orthogonality of the weights helps train deep models and improve…

Recently, deep convolutional neural network (CNN) have been widely used in image restoration and obtained great success. However, most of existing methods are limited to local receptive field and equal treatment of different types of…

Deep Neural Network has shown great strides in the coarse-grained image classification task. It was in part due to its strong ability to extract discriminative feature representations from the images. However, the marginal visual difference…

Attention Mechanism is a widely used method for improving the performance of convolutional neural networks (CNNs) on computer vision tasks. Despite its pervasiveness, we have a poor understanding of what its effectiveness stems from. It is…

With parallelizable attention networks, the neural Transformer is very fast to train. However, due to the auto-regressive architecture and self-attention in the decoder, the decoding procedure becomes slow. To alleviate this issue, we…

In recent years, significant progress has been made on the research of crowd counting. However, as the challenging scale variations and complex scenes existed in crowds, neither traditional convolution networks nor recent Transformer…

While the integration of transformers in vision models have yielded significant improvements on vision tasks they still require significant amounts of computation for both training and inference. Restricted attention mechanisms…

Convolutional networks have been the paradigm of choice in many computer vision applications. The convolution operation however has a significant weakness in that it only operates on a local neighborhood, thus missing global information.…

This paper proposes an adaptive auxiliary task learning based approach for object counting problems. Unlike existing auxiliary task learning based methods, we develop an attention-enhanced adaptively shared backbone network to enable both…

We propose a generalized convolutional neural network (CNN) architecture that first decomposes the input signal into subbands by an adaptive filter bank structure, and then uses convolutional layers to extract features from each subband…

In the realm of EEG decoding, enhancing the performance of artificial neural networks (ANNs) carries significant potential. This study introduces a novel approach, termed "weight freezing", that is anchored on the principles of ANN…