SEARCH · Search arXiv

Results for “transformer architecture”

Search indexed arXiv papers on artificial intelligence, large language models, computer vision and robotics. Read source abstracts and follow links to arXiv.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 199 records · Page 11Linked to original sources

arXiv2021

GroupBERT: Enhanced Transformer Architecture with Efficient Grouped Structures

Attention based language models have become a critical component in state-of-the-art natural language processing systems. However, these models have significant computational requirements, due to long training times, dense operations and large parameter count. In this work we demonstrate a set of modifications to the structure of a Transformer layer, producing a more efficient architecture. First, we add a convolutional module to complement the self-attention module, decoupling the learning of local and global interactions. Secondly, we rely on grouped transformations to reduce the computational cost of dense feed-forward layers and convolutions, while preserving the expressivity of the model. We apply the resulting architecture to language representation learning and demonstrate its superior performance compared to BERT models of different scales. We further highlight its improved efficiency, both in terms of floating-point operations (FLOPs) and time-to-train.

cs.CL↗

arXiv2025

LungX: A Hybrid EfficientNet-Vision Transformer Architecture with Multi-Scale Attention for Accurate Pneumonia Detection

Pneumonia remains a leading global cause of mortality where timely diagnosis is critical. We introduce LungX, a novel hybrid architecture combining EfficientNet's multi-scale features, CBAM attention mechanisms, and Vision Transformer's global context modeling for enhanced pneumonia detection. Evaluated on 20,000 curated chest X-rays from RSNA and CheXpert, LungX achieves state-of-the-art performance (86.5 percent accuracy, 0.943 AUC), representing a 6.7 percent AUC improvement over EfficientNet-B0 baselines. Visual analysis demonstrates superior lesion localization through interpretable attention maps. Future directions include multi-center validation and architectural optimizations targeting 88 percent accuracy for clinical deployment as an AI diagnostic aid.

cs.CV↗

arXiv2024

Modeling Bilingual Sentence Processing: Evaluating RNN and Transformer Architectures for Cross-Language Structural Priming

This study evaluates the performance of Recurrent Neural Network (RNN) and Transformer models in replicating cross-language structural priming, a key indicator of abstract grammatical representations in human language processing. Focusing on Chinese-English priming, which involves two typologically distinct languages, we examine how these models handle the robust phenomenon of structural priming, where exposure to a particular sentence structure increases the likelihood of selecting a similar structure subsequently. Our findings indicate that transformers outperform RNNs in generating primed sentence structures, with accuracy rates that exceed 25.84\% to 33. 33\%. This challenges the conventional belief that human sentence processing primarily involves recurrent and immediate processing and suggests a role for cue-based retrieval mechanisms. This work contributes to our understanding of how computational models may reflect human cognitive processes across diverse language families.

cs.CL↗

arXiv2021

Memory-Efficient Differentiable Transformer Architecture Search

Differentiable architecture search (DARTS) is successfully applied in many vision tasks. However, directly using DARTS for Transformers is memory-intensive, which renders the search process infeasible. To this end, we propose a multi-split reversible network and combine it with DARTS. Specifically, we devise a backpropagation-with-reconstruction algorithm so that we only need to store the last layer's outputs. By relieving the memory burden for DARTS, it allows us to search with larger hidden size and more candidate operations. We evaluate the searched architecture on three sequence-to-sequence datasets, i.e., WMT'14 English-German, WMT'14 English-French, and WMT'14 English-Czech. Experimental results show that our network consistently outperforms standard Transformers across the tasks. Moreover, our method compares favorably with big-size Evolved Transformers, reducing search computation by an order of magnitude.

cs.LG↗

arXiv2024

SuperFormer: Volumetric Transformer Architectures for MRI Super-Resolution

This paper presents a novel framework for processing volumetric medical information using Visual Transformers (ViTs). First, We extend the state-of-the-art Swin Transformer model to the 3D medical domain. Second, we propose a new approach for processing volumetric information and encoding position in ViTs for 3D applications. We instantiate the proposed framework and present SuperFormer, a volumetric transformer-based approach for Magnetic Resonance Imaging (MRI) Super-Resolution. Our method leverages the 3D information of the MRI domain and uses a local self-attention mechanism with a 3D relative positional encoding to recover anatomical details. In addition, our approach takes advantage of multi-domain information from volume and feature domains and fuses them to reconstruct the High-Resolution MRI. We perform an extensive validation on the Human Connectome Project dataset and demonstrate the superiority of volumetric transformers over 3D CNN-based methods. Our code and pretrained models are available at https://github.com/BCV-Uniandes/SuperFormer.

eess.IV↗

arXiv2023

Edge-MoE: Memory-Efficient Multi-Task Vision Transformer Architecture with Task-level Sparsity via Mixture-of-Experts

Computer vision researchers are embracing two promising paradigms: Vision Transformers (ViTs) and Multi-task Learning (MTL), which both show great performance but are computation-intensive, given the quadratic complexity of self-attention in ViT and the need to activate an entire large MTL model for one task. M$^3$ViT is the latest multi-task ViT model that introduces mixture-of-experts (MoE), where only a small portion of subnetworks ("experts") are sparsely and dynamically activated based on the current task. M$^3$ViT achieves better accuracy and over 80% computation reduction but leaves challenges for efficient deployment on FPGA. Our work, dubbed Edge-MoE, solves the challenges to introduce the first end-to-end FPGA accelerator for multi-task ViT with a collection of architectural innovations, including (1) a novel reordering mechanism for self-attention, which requires only constant bandwidth regardless of the target parallelism; (2) a fast single-pass softmax approximation; (3) an accurate and low-cost GELU approximation; (4) a unified and flexible computing unit that is shared by almost all computational layers to maximally reduce resource usage; and (5) uniquely for M$^3$ViT, a novel patch reordering method to eliminate memory access overhead. Edge-MoE achieves 2.24x and 4.90x better energy efficiency comparing with GPU and CPU, respectively. A real-time video demonstration is available online, along with our open-source code written using High-Level Synthesis.

cs.AR↗

arXiv2025

Learning with SASQuaTCh: a Novel Variational Quantum Transformer Architecture with Kernel-Based Self-Attention

The recent exploding growth in size of state-of-the-art machine learning models highlights a well-known issue where exponential parameter growth, which has grown to trillions as in the case of the Generative Pre-trained Transformer (GPT), leads to training time and memory requirements which limit their advancement in the near term. The predominant models use the so-called transformer network and have a large field of applicability, including predicting text and images, classification, and even predicting solutions to the dynamics of physical systems. Here we present a variational quantum circuit architecture named Self-Attention Sequential Quantum Transformer Channel (SASQuaTCh), which builds networks of qubits that perform analogous operations of the transformer network, namely the keystone self-attention operation, and leads to an exponential improvement in parameter complexity and run-time complexity over its classical counterpart. Our approach leverages recent insights from kernel-based operator learning in the context of predicting spatiotemporal systems to represent deep layers of a vision transformer network using simple gate operations and a set of multi-dimensional quantum Fourier transforms. To validate our approach, we consider image classification tasks in simulation and with hardware, where with only 9 qubits and a handful of parameters we are able to simultaneously embed and classify a grayscale image of handwritten digits with high accuracy.

quant-ph↗

arXiv2024

On Limitations of the Transformer Architecture

What are the root causes of hallucinations in large language models (LLMs)? We use Communication Complexity to prove that the Transformer layer is incapable of composing functions (e.g., identify a grandparent of a person in a genealogy) if the domains of the functions are large enough; we show through examples that this inability is already empirically present when the domains are quite small. We also point out that several mathematical tasks that are at the core of the so-called compositional tasks thought to be hard for LLMs are unlikely to be solvable by Transformers, for large enough instances and assuming that certain well accepted conjectures in the field of Computational Complexity are true.

stat.ML↗

arXiv2026

HiPerViT: A Hierarchical Perceiver-Vision Transformer Architecture for Multi-Scale Texture Recognition

Texture recognition remains challenging for modern vision models because discriminative evidence is often carried by higher-order spatial statistics rather than by object shape alone. While Vision Transformers provide strong long-range modeling capacity, their standard object-centric representations do not explicitly expose such statistical structure, which limits texture sensitivity in fine-grained recognition settings. We present HiPerViT, a compact vision-only architecture that injects an explicit second-order statistical prior into a transformer-based recognition pipeline. The method combines global and local image views with a compact bilinear descriptor encoded as a statistical token, and integrates this token with first-order spatial representations through Perceiver-style latent distillation. This design enables direct interaction between spatial tokens and second-order feature co-occurrence statistics, providing the model with explicit access to texture-relevant information without requiring multimodal pretraining or ensemble construction. Across six texture recognition benchmarks, HiPerViT achieves consistent improvements over strong vision-only baselines under the reported evaluation protocols, including gains of +3.05 percentage points on DTD, +10.48 on GTOS-Mobile, and +10.10 on 1200Tex. Beyond benchmark performance, our analyses show that these gains are largely invariant to the backbone depth used to extract second-order statistics and to the ordering of interaction and distillation stages. This pattern suggests that the primary source of improvement is not a specific fusion topology, but the explicit availability of second-order statistical information as a first-class representational signal. These results support explicit statistical tokenization as an effective and robust design principle for texture-centric visual recognition.

cs.CV↗

arXiv2024

Effective Diffusion Transformer Architecture for Image Super-Resolution

Recent advances indicate that diffusion models hold great promise in image super-resolution. While the latest methods are primarily based on latent diffusion models with convolutional neural networks, there are few attempts to explore transformers, which have demonstrated remarkable performance in image generation. In this work, we design an effective diffusion transformer for image super-resolution (DiT-SR) that achieves the visual quality of prior-based methods, but through a training-from-scratch manner. In practice, DiT-SR leverages an overall U-shaped architecture, and adopts a uniform isotropic design for all the transformer blocks across different stages. The former facilitates multi-scale hierarchical feature extraction, while the latter reallocates the computational resources to critical layers to further enhance performance. Moreover, we thoroughly analyze the limitation of the widely used AdaLN, and present a frequency-adaptive time-step conditioning module, enhancing the model's capacity to process distinct frequency information at different time steps. Extensive experiments demonstrate that DiT-SR outperforms the existing training-from-scratch diffusion-based SR methods significantly, and even beats some of the prior-based methods on pretrained Stable Diffusion, proving the superiority of diffusion transformer in image super-resolution.

cs.CV↗

arXiv2022

DPTNet: A Dual-Path Transformer Architecture for Scene Text Detection

The prosperity of deep learning contributes to the rapid progress in scene text detection. Among all the methods with convolutional networks, segmentation-based ones have drawn extensive attention due to their superiority in detecting text instances of arbitrary shapes and extreme aspect ratios. However, the bottom-up methods are limited to the performance of their segmentation models. In this paper, we propose DPTNet (Dual-Path Transformer Network), a simple yet effective architecture to model the global and local information for the scene text detection task. We further propose a parallel design that integrates the convolutional network with a powerful self-attention mechanism to provide complementary clues between the attention path and convolutional path. Moreover, a bi-directional interaction module across the two paths is developed to provide complementary clues in the channel and spatial dimensions. We also upgrade the concentration operation by adding an extra multi-head attention layer to it. Our DPTNet achieves state-of-the-art results on the MSRA-TD500 dataset, and provides competitive results on other standard benchmarks in terms of both detection accuracy and speed.

cs.CV↗

arXiv2024

Computer-Aided Diagnosis of Thoracic Diseases in Chest X-rays using hybrid CNN-Transformer Architecture

Medical imaging has been used for diagnosis of various conditions, making it one of the most powerful resources for effective patient care. Due to widespread availability, low cost, and low radiation, chest X-ray is one of the most sought after radiology examination for the diagnosis of various thoracic diseases. Due to advancements in medical imaging technologies and increasing patient load, current radiology workflow faces various challenges including increasing backlogs, working long hours, and increase in diagnostic errors. An automated computer-aided diagnosis system that can interpret chest X-rays to augment radiologists by providing actionable insights has potential to provide second opinion to radiologists, highlight relevant regions in the image, in turn expediting clinical workflow, reducing diagnostic errors, and improving patient care. In this study, we applied a novel architecture augmenting the DenseNet121 Convolutional Neural Network (CNN) with multi-head self-attention mechanism using transformer, namely SA-DenseNet121, that can identify multiple thoracic diseases in chest X-rays. We conducted experiments on four of the largest chest X-ray datasets, namely, ChestX-ray14, CheXpert, MIMIC-CXR-JPG, and IU-CXR. Experimental results in terms of area under the receiver operating characteristics (AUC-ROC) shows that augmenting CNN with self-attention has potential in diagnosing different thoracic diseases from chest X-rays. The proposed methodology has the potential to support the reading workflow, improve efficiency, and reduce diagnostic errors.

eess.IV↗

arXiv2018

On-Chip Implementation of Pipeline Digit-Slicing Multiplier-Less Butterfly for Fast Fourier Transform Architecture

The need for wireless communication has driven the communication systems to high performance. However, the main bottleneck that affects the communication capability is the Fast Fourier Transform (FFT), which is the core of most modulators. This study presents an on-chip implementation of pipeline digit-slicing multiplier-less butterfly for FFT structure. The approach is taken, in order to reduce computation complexity in the butterfly, digit-slicing multiplier-less single constant technique was utilized in the critical path of Radix-2 Decimation In Time (DIT) FFT structure. The proposed design focused on the trade-off between the speed and active silicon area for the chip implementation. The new architecture was investigated and simulated with MATLAB software. The Verilog HDL code in Xilinx ISE environment was derived to describe the FFT Butterfly functionality and was downloaded to Virtex II FPGA board. Consequently, the Virtex-II FG456 Proto board was used to implement and test the design on the real hardware. As a result, from the findings, the synthesis report indicates the maximum clock frequency of 549.75 MHz with the total equivalent gate count of 31,159 is a marked and significant improvement over Radix 2 FFT butterfly. In comparison with the conventional butterfly architecture, the design that can only run at a maximum clock frequency of 198.987 MHz and the conventional multiplier can only run at a maximum clock frequency of 220.160 MHz, the proposed system exhibits better results. The resulting maximum clock frequency increases by about 276.28% for the FFT butterfly and about 277.06% for the multiplier. It can be concluded that on-chip implementation of pipeline digit-slicing multiplier-less butterfly for FFT structure is an enabler in solving problems that affect communications capability in FFT and possesses huge potentials for future related works and research areas.

eess.SP↗

arXiv2023

Composable Function-preserving Expansions for Transformer Architectures

Training state-of-the-art neural networks requires a high cost in terms of compute and time. Model scale is recognized to be a critical factor to achieve and improve the state-of-the-art. Increasing the scale of a neural network normally requires restarting from scratch by randomly initializing all the parameters of the model, as this implies a change of architecture's parameters that does not allow for a straightforward transfer of knowledge from smaller size models. In this work, we propose six composable transformations to incrementally increase the size of transformer-based neural networks while preserving functionality, allowing to expand the capacity of the model as needed. We provide proof of exact function preservation under minimal initialization constraints for each transformation. The proposed methods may enable efficient training pipelines for larger and more powerful models by progressively expanding the architecture throughout training.

cs.LG↗

arXiv2022

EdgeNeXt: Efficiently Amalgamated CNN-Transformer Architecture for Mobile Vision Applications

In the pursuit of achieving ever-increasing accuracy, large and complex neural networks are usually developed. Such models demand high computational resources and therefore cannot be deployed on edge devices. It is of great interest to build resource-efficient general purpose networks due to their usefulness in several application areas. In this work, we strive to effectively combine the strengths of both CNN and Transformer models and propose a new efficient hybrid architecture EdgeNeXt. Specifically in EdgeNeXt, we introduce split depth-wise transpose attention (STDA) encoder that splits input tensors into multiple channel groups and utilizes depth-wise convolution along with self-attention across channel dimensions to implicitly increase the receptive field and encode multi-scale features. Our extensive experiments on classification, detection and segmentation tasks, reveal the merits of the proposed approach, outperforming state-of-the-art methods with comparatively lower compute requirements. Our EdgeNeXt model with 1.3M parameters achieves 71.2% top-1 accuracy on ImageNet-1K, outperforming MobileViT with an absolute gain of 2.2% with 28% reduction in FLOPs. Further, our EdgeNeXt model with 5.6M parameters achieves 79.4% top-1 accuracy on ImageNet-1K. The code and models are available at https://t.ly/_Vu9.

cs.CV↗

arXiv2024

Comprehensive Multimodal Deep Learning Survival Prediction Enabled by a Transformer Architecture: A Multicenter Study in Glioblastoma

Background: This research aims to improve glioblastoma survival prediction by integrating MR images, clinical and molecular-pathologic data in a transformer-based deep learning model, addressing data heterogeneity and performance generalizability. Method: We propose and evaluate a transformer-based non-linear and non-proportional survival prediction model. The model employs self-supervised learning techniques to effectively encode the high-dimensional MRI input for integration with non-imaging data using cross-attention. To demonstrate model generalizability, the model is assessed with the time-dependent concordance index (Cdt) in two training setups using three independent public test sets: UPenn-GBM, UCSF-PDGM, and RHUH-GBM, each comprising 378, 366, and 36 cases, respectively. Results: The proposed transformer model achieved promising performance for imaging as well as non-imaging data, effectively integrating both modalities for enhanced performance (UPenn-GBM test-set, imaging Cdt 0.645, multimodal Cdt 0.707) while outperforming state-of-the-art late-fusion 3D-CNN-based models. Consistent performance was observed across the three independent multicenter test sets with Cdt values of 0.707 (UPenn-GBM, internal test set), 0.672 (UCSF-PDGM, first external test set) and 0.618 (RHUH-GBM, second external test set). The model achieved significant discrimination between patients with favorable and unfavorable survival for all three datasets (logrank p 1.9\times{10}^{-8}, 9.7\times{10}^{-3}, and 1.2\times{10}^{-2}). Conclusions: The proposed transformer-based survival prediction model integrates complementary information from diverse input modalities, contributing to improved glioblastoma survival prediction compared to state-of-the-art methods. Consistent performance was observed across institutions supporting model generalizability.

eess.IV↗

arXiv2026

AI-Powered Deepfake Detection Using CNN and Vision Transformer Architectures

The increasing use of artificial intelligence generated deepfakes creates major challenges in maintaining digital authenticity. Four AI-based models, consisting of three CNNs and one Vision Transformer, were evaluated using large face image datasets. Data preprocessing and augmentation techniques improved model performance across different scenarios. VFDNET demonstrated superior accuracy with MobileNetV3, showing efficient performance, thereby demonstrating AI's capabilities for dependable deepfake detection.

cs.CV↗

arXiv2021

A Transformer Architecture for Stress Detection from ECG

Electrocardiogram (ECG) has been widely used for emotion recognition. This paper presents a deep neural network based on convolutional layers and a transformer mechanism to detect stress using ECG signals. We perform leave-one-subject-out experiments on two publicly available datasets, WESAD and SWELL-KW, to evaluate our method. Our experiments show that the proposed model achieves strong results, comparable or better than the state-of-the-art models for ECG-based stress detection on these two datasets. Moreover, our method is end-to-end, does not require handcrafted features, and can learn robust representations with only a few convolutional blocks and the transformer component.

eess.SP↗