Encoder transformer models compress information from all tokens in a sequence into a single [CLS] token to represent global context. This approach risks diluting fine-grained or hierarchical features, leading to information loss in downstream tasks where local patterns are important. To remedy this, we propose a lightweight architectural enhancement: an inception-style 1-D convolution module that sits on top of the transformer layer and augments token representations with multi-scale local features. This enriched feature space is then processed by a self-attention layer that dynamically weights tokens based on their task relevance. Experiments on five diverse tasks show that our framework consistently improves general-purpose, domain-specific, and multilingual models, outperforming baselines by 1% to 14% while maintaining efficiency. Ablation studies show that multi-scale convolution performs better than any single kernel and that the self-attention layer is critical for performance.

We thank the reviewers for their thoughtful and constructive feedback. The reviewer notes that the proposed conditional convolution method is novel and shows promising results. The reviewer suggests that results would be more convincing if tested on more network structures. The reviewer suggests we compare our approach with squeeze-and-excite (SE). A1 performance, which includes SE layers.

DL methods have been successfully applied to SSVEP-BCI. This study proposes a new model called IncepFormerNet, which is a hybrid of the Inception and Transformer architectures. IncepFormerNet adeptly extracts multi-scale temporal information from time series data using parallel convolution kernels of varying sizes, accurately capturing the subtle variations and critical features within SSVEP signals.Furthermore, the model integrates the multi-head attention mechanism from the Transformer architecture, which not only provides insights into global dependencies but also significantly enhances the understanding and representation of complex patterns.Additionally, it takes advantage of filter bank techniques to extract features based on the spectral characteristics of SSVEP data. To validate the effectiveness of the proposed model, we conducted experiments on two public datasets, . The experimental results show that IncepFormerNet achieves an accuracy of 87.41% on Dataset 1 and 71.97% on Dataset 2 using a 1.0-second time window.

ERP-based EEG detection is gaining increasing attention in the field of brain-computer interfaces. However, due to the complexity of ERP signal components, their low signal-to-noise ratio, and significant inter-subject variability, cross-subject ERP signal detection has been challenging. The continuous advancement in deep learning has greatly contributed to addressing this issue. This brief proposes a contrastive learning training framework and an Inception module to extract multi-scale temporal and spatial features, representing the subject-invariant components of ERP signals. Specifically, a base encoder integrated with a linear Inception module and a nonlinear projector is used to project the raw data into latent space. By maximizing signal similarity under different targets, the inter-subject EEG signal differences in latent space are minimized. The extracted spatiotemporal features are then used for ERP target detection. The proposed algorithm achieved the best AUC performance in single-trial binary classification tasks on the P300 dataset and showed significant optimization in speller decoding tasks compared to existing algorithms.

Automated emotion recognition using electroencephalogram (EEG) signals has gained substantial attention. Although deep learning approaches exhibit strong performance, they often suffer from vulnerabilities to various perturbations, like environmental noise and adversarial attacks. In this paper, we propose an Inception feature generator and two-sided perturbation (INC-TSP) approach to enhance emotion recognition in brain-computer interfaces. INC-TSP integrates the Inception module for EEG data analysis and employs two-sided perturbation (TSP) as a defensive mechanism against input perturbations. TSP introduces worst-case perturbations to the model's weights and inputs, reinforcing the model's elasticity against adversarial attacks. The proposed approach addresses the challenge of maintaining accurate emotion recognition in the presence of input uncertainties. We validate INC-TSP in a subject-independent three-class emotion recognition scenario, demonstrating robust performance.

Beyond the generally deployed features for microstructure property prediction this study aims to improve the machine learned prediction by developing novel feature descriptors. Therefore, Bayesian infused data mining is conducted to acquire samples containing characteristics inexplicable to the current feature set, and suitable feature descriptors to describe these characteristics are proposed. The iterative development of feature descriptors resulted in 37 novel features, being able to reduce the prediction error by roughly one third. To further improve the predictive model, convolutional neural networks (Conv Nets) are deployed to generate auxiliary features in a supervised machine learning manner. The Conv Nets were able to outperform the feature based approach. A key ingredient for that is a newly proposed data augmentation scheme and the development of so-called deep inception modules. A combination of the feature based approach and the convolutional neural network leads to a hybrid neural network: A parallel deployment of the both neural network archetypes in a single model achieved a relative rooted mean squared error below 1%, more than halving the error compared to prior models operating on the same data. The hybrid neural network was found powerful enough to be extended to predict variable material parameters, from a low to high phase contrast, while allowing for arbitrary microstructure geometry at the same time.

If you're reading this, chances are you're just as passionate about deep learning and computer vision as I am. CNNs are an integral part of the field and have been responsible for some of the most impressive breakthroughs in image classification and object recognition. In this post, I'll introduce you to some of the most famous CNNs developed over the years and discuss their unique characteristics and contributions to the field. Whether you're a seasoned deep learning practitioner or just starting out, I hope this post will inspire you to dive deeper into the world of CNNs and learn more about how they work. So, without further ado, let's get started!

Many CNNs have been created, but the following are some of the most effective designs, which are implemented in various CV tasks via transfer learning. AlexNet (2012): AlexNet includes five convolutional and three fully connected layers. It uses a dual pipeline structure to accommodate the use of two GPUs during training. It uses ReLU) instead of sigmoid or Tanh used in LeNet. GoogleNet (2014): GoogleNet (Inception V1) has 22 layers made of small groups of convolutions, called "inception modules".

Back in 2012, Alexnet scored 63.3% Top-1 accuracy on ImageNet. Now, we are over 90% with EfficientNet architectures and teacher-student training. In this article, we will focus on the evolution of convolutional neural networks (CNN) architectures. Rather than reporting plain numbers, we will focus on the fundamental principles. All the depicted architectures are based on the concepts that we will describe. Note that, the FLoating point Operations Per second (FLOPs) indicate the complexity of the model, while on the vertical axis we have the Imagenet accuracy. The radius of the circle indicates the number of parameters.

Xception: Deep Learning with Depthwise Separable Convolutions  (CVPR 2017) We present an interpretation of Inception modules in convolutional neural networks as being an intermediate step in-between regular convolution and the depthwise separable convolution operation (a depthwise convolution followed by a pointwise convolution). In this light, a depthwise separable convolution can be understood as an Inception module with a maximally large number of towers. This observation leads us to propose a novel deep convolutional neural network architecture inspired by Inception, where Inception modules have been replaced with depthwise separable convolutions. We show that this architecture, dubbed Xception, slightly outperforms Inception V3 on the ImageNet dataset (which Inception V3 was designed for), and significantly outperforms Inception V3 on a larger image classification dataset comprising 350 million images and 17,000 classes. Since the Xception architecture has the same number of parameters as Inception V3, the performance gains are not due to increased capacity but rather to a more efficient use of model parameters. Paper:   https://arxiv.org/pdf/1610.02357.pdf