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 1,531 records · Page 85Linked to original sources

arXiv2022

Document-Level Abstractive Summarization

The task of automatic text summarization produces a concise and fluent text summary while preserving key information and overall meaning. Recent approaches to document-level summarization have seen significant improvements in recent years by using models based on the Transformer architecture. However, the quadratic memory and time complexities with respect to the sequence length make them very expensive to use, especially with long sequences, as required by document-level summarization. Our work addresses the problem of document-level summarization by studying how efficient Transformer techniques can be used to improve the automatic summarization of very long texts. In particular, we will use the arXiv dataset, consisting of several scientific papers and the corresponding abstracts, as baselines for this work. Then, we propose a novel retrieval-enhanced approach based on the architecture which reduces the cost of generating a summary of the entire document by processing smaller chunks. The results were below the baselines but suggest a more efficient memory a consumption and truthfulness.

cs.CL↗

arXiv2023

Auto-Spikformer: Spikformer Architecture Search

The integration of self-attention mechanisms into Spiking Neural Networks (SNNs) has garnered considerable interest in the realm of advanced deep learning, primarily due to their biological properties. Recent advancements in SNN architecture, such as Spikformer, have demonstrated promising outcomes by leveraging Spiking Self-Attention (SSA) and Spiking Patch Splitting (SPS) modules. However, we observe that Spikformer may exhibit excessive energy consumption, potentially attributable to redundant channels and blocks. To mitigate this issue, we propose Auto-Spikformer, a one-shot Transformer Architecture Search (TAS) method, which automates the quest for an optimized Spikformer architecture. To facilitate the search process, we propose methods Evolutionary SNN neurons (ESNN), which optimizes the SNN parameters, and apply the previous method of weight entanglement supernet training, which optimizes the Vision Transformer (ViT) parameters. Moreover, we propose an accuracy and energy balanced fitness function $\mathcal{F}_{AEB}$ that jointly considers both energy consumption and accuracy, and aims to find a Pareto optimal combination that balances these two objectives. Our experimental results demonstrate the effectiveness of Auto-Spikformer, which outperforms the state-of-the-art method including CNN or ViT models that are manually or automatically designed while significantly reducing energy consumption.

cs.NE↗

arXiv2023

TransNetR: Transformer-based Residual Network for Polyp Segmentation with Multi-Center Out-of-Distribution Testing

Colonoscopy is considered the most effective screening test to detect colorectal cancer (CRC) and its precursor lesions, i.e., polyps. However, the procedure experiences high miss rates due to polyp heterogeneity and inter-observer dependency. Hence, several deep learning powered systems have been proposed considering the criticality of polyp detection and segmentation in clinical practices. Despite achieving improved outcomes, the existing automated approaches are inefficient in attaining real-time processing speed. Moreover, they suffer from a significant performance drop when evaluated on inter-patient data, especially those collected from different centers. Therefore, we intend to develop a novel real-time deep learning based architecture, Transformer based Residual network (TransNetR), for colon polyp segmentation and evaluate its diagnostic performance. The proposed architecture, TransNetR, is an encoder-decoder network that consists of a pre-trained ResNet50 as the encoder, three decoder blocks, and an upsampling layer at the end of the network. TransNetR obtains a high dice coefficient of 0.8706 and a mean Intersection over union of 0.8016 and retains a real-time processing speed of 54.60 on the Kvasir-SEG dataset. Apart from this, the major contribution of the work lies in exploring the generalizability of the TransNetR by testing the proposed algorithm on the out-of-distribution (test distribution is unknown and different from training distribution) dataset. As a use case, we tested our proposed algorithm on the PolypGen (6 unique centers) dataset and two other popular polyp segmentation benchmarking datasets. We obtained state-of-the-art performance on all three datasets during out-of-distribution testing. The source code of TransNetR will be made publicly available at https://github.com/DebeshJha.

eess.IV↗

arXiv2020

Stress Test Evaluation of Transformer-based Models in Natural Language Understanding Tasks

There has been significant progress in recent years in the field of Natural Language Processing thanks to the introduction of the Transformer architecture. Current state-of-the-art models, via a large number of parameters and pre-training on massive text corpus, have shown impressive results on several downstream tasks. Many researchers have studied previous (non-Transformer) models to understand their actual behavior under different scenarios, showing that these models are taking advantage of clues or failures of datasets and that slight perturbations on the input data can severely reduce their performance. In contrast, recent models have not been systematically tested with adversarial-examples in order to show their robustness under severe stress conditions. For that reason, this work evaluates three Transformer-based models (RoBERTa, XLNet, and BERT) in Natural Language Inference (NLI) and Question Answering (QA) tasks to know if they are more robust or if they have the same flaws as their predecessors. As a result, our experiments reveal that RoBERTa, XLNet and BERT are more robust than recurrent neural network models to stress tests for both NLI and QA tasks. Nevertheless, they are still very fragile and demonstrate various unexpected behaviors, thus revealing that there is still room for future improvement in this field.

cs.AI↗

arXiv2022

On Learning the Transformer Kernel

In this work we introduce KERNELIZED TRANSFORMER, a generic, scalable, data driven framework for learning the kernel function in Transformers. Our framework approximates the Transformer kernel as a dot product between spectral feature maps and learns the kernel by learning the spectral distribution. This not only helps in learning a generic kernel end-to-end, but also reduces the time and space complexity of Transformers from quadratic to linear. We show that KERNELIZED TRANSFORMERS achieve performance comparable to existing efficient Transformer architectures, both in terms of accuracy as well as computational efficiency. Our study also demonstrates that the choice of the kernel has a substantial impact on performance, and kernel learning variants are competitive alternatives to fixed kernel Transformers, both in long as well as short sequence tasks.

cs.LG↗

arXiv2021

Scene-Adaptive Attention Network for Crowd Counting

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 architectures with fixed-size attention could handle the task well. To address this problem, this paper proposes a scene-adaptive attention network, termed SAANet. First of all, we design a deformable attention in-built Transformer backbone, which learns adaptive feature representations with deformable sampling locations and dynamic attention weights. Then we propose the multi-level feature fusion and count-attentive feature enhancement modules further, to strengthen feature representation under the global image context. The learned representations could attend to the foreground and are adaptive to different scales of crowds. We conduct extensive experiments on four challenging crowd counting benchmarks, demonstrating that our method achieves state-of-the-art performance. Especially, our method currently ranks No.1 on the public leaderboard of the NWPU-Crowd benchmark. We hope our method could be a strong baseline to support future research in crowd counting. The source code will be released to the community.

cs.CV↗

arXiv2023

Outlier Suppression: Pushing the Limit of Low-bit Transformer Language Models

Transformer architecture has become the fundamental element of the widespread natural language processing~(NLP) models. With the trends of large NLP models, the increasing memory and computation costs hinder their efficient deployment on resource-limited devices. Therefore, transformer quantization attracts wide research interest. Recent work recognizes that structured outliers are the critical bottleneck for quantization performance. However, their proposed methods increase the computation overhead and still leave the outliers there. To fundamentally address this problem, this paper delves into the inherent inducement and importance of the outliers. We discover that $\boldsymbol γ$ in LayerNorm (LN) acts as a sinful amplifier for the outliers, and the importance of outliers varies greatly where some outliers provided by a few tokens cover a large area but can be clipped sharply without negative impacts. Motivated by these findings, we propose an outlier suppression framework including two components: Gamma Migration and Token-Wise Clipping. The Gamma Migration migrates the outlier amplifier to subsequent modules in an equivalent transformation, contributing to a more quantization-friendly model without any extra burden. The Token-Wise Clipping takes advantage of the large variance of token range and designs a token-wise coarse-to-fine pipeline, obtaining a clipping range with minimal final quantization loss in an efficient way. This framework effectively suppresses the outliers and can be used in a plug-and-play mode. Extensive experiments prove that our framework surpasses the existing works and, for the first time, pushes the 6-bit post-training BERT quantization to the full-precision (FP) level. Our code is available at https://github.com/wimh966/outlier_suppression.

cs.LG↗

arXiv2023

ELiOT : End-to-end Lidar Odometry using Transformer Framework

In recent years, deep-learning-based point cloud registration methods have shown significant promise. Furthermore, learning-based 3D detectors have demonstrated their effectiveness in encoding semantic information from LiDAR data. In this paper, we introduce ELiOT, an end-to-end LiDAR odometry framework built on a transformer architecture. Our proposed Self-attention flow embedding network implicitly represents the motion of sequential LiDAR scenes, bypassing the need for 3D-2D projections traditionally used in such tasks. The network pipeline, composed of a 3D transformer encoder-decoder, has shown effectiveness in predicting poses on urban datasets. In terms of translational and rotational errors, our proposed method yields encouraging results, with 7.59% and 2.67% respectively on the KITTI odometry dataset. This is achieved with an end-to-end approach that foregoes the need for conventional geometric concepts.

eess.IV↗

arXiv2023

Is context all you need? Scaling Neural Sign Language Translation to Large Domains of Discourse

Sign Language Translation (SLT) is a challenging task that aims to generate spoken language sentences from sign language videos, both of which have different grammar and word/gloss order. From a Neural Machine Translation (NMT) perspective, the straightforward way of training translation models is to use sign language phrase-spoken language sentence pairs. However, human interpreters heavily rely on the context to understand the conveyed information, especially for sign language interpretation, where the vocabulary size may be significantly smaller than their spoken language equivalent. Taking direct inspiration from how humans translate, we propose a novel multi-modal transformer architecture that tackles the translation task in a context-aware manner, as a human would. We use the context from previous sequences and confident predictions to disambiguate weaker visual cues. To achieve this we use complementary transformer encoders, namely: (1) A Video Encoder, that captures the low-level video features at the frame-level, (2) A Spotting Encoder, that models the recognized sign glosses in the video, and (3) A Context Encoder, which captures the context of the preceding sign sequences. We combine the information coming from these encoders in a final transformer decoder to generate spoken language translations. We evaluate our approach on the recently published large-scale BOBSL dataset, which contains ~1.2M sequences, and on the SRF dataset, which was part of the WMT-SLT 2022 challenge. We report significant improvements on state-of-the-art translation performance using contextual information, nearly doubling the reported BLEU-4 scores of baseline approaches.

cs.CV↗

arXiv2023

Not all layers are equally as important: Every Layer Counts BERT

This paper introduces a novel modification of the transformer architecture, tailored for the data-efficient pretraining of language models. This aspect is evaluated by participating in the BabyLM challenge, where our solution won both the strict and strict-small tracks. Our approach allows each transformer layer to select which outputs of previous layers to process. The empirical results verify the potential of this simple modification and show that not all layers are equally as important.

cs.CL↗

arXiv2024

DenseFormer: Enhancing Information Flow in Transformers via Depth Weighted Averaging

The transformer architecture by Vaswani et al. (2017) is now ubiquitous across application domains, from natural language processing to speech processing and image understanding. We propose DenseFormer, a simple modification to the standard architecture that improves the perplexity of the model without increasing its size -- adding a few thousand parameters for large-scale models in the 100B parameters range. Our approach relies on an additional averaging step after each transformer block, which computes a weighted average of current and past representations -- we refer to this operation as Depth-Weighted-Average (DWA). The learned DWA weights exhibit coherent patterns of information flow, revealing the strong and structured reuse of activations from distant layers. Experiments demonstrate that DenseFormer is more data efficient, reaching the same perplexity of much deeper transformer models, and that for the same perplexity, these new models outperform transformer baselines in terms of memory efficiency and inference time.

cs.CL↗

arXiv2024

LAPDoc: Layout-Aware Prompting for Documents

Recent advances in training large language models (LLMs) using massive amounts of solely textual data lead to strong generalization across many domains and tasks, including document-specific tasks. Opposed to that there is a trend to train multi-modal transformer architectures tailored for document understanding that are designed specifically to fuse textual inputs with the corresponding document layout. This involves a separate fine-tuning step for which additional training data is required. At present, no document transformers with comparable generalization to LLMs are available That raises the question which type of model is to be preferred for document understanding tasks. In this paper we investigate the possibility to use purely text-based LLMs for document-specific tasks by using layout enrichment. We explore drop-in modifications and rule-based methods to enrich purely textual LLM prompts with layout information. In our experiments we investigate the effects on the commercial ChatGPT model and the open-source LLM Solar. We demonstrate that using our approach both LLMs show improved performance on various standard document benchmarks. In addition, we study the impact of noisy OCR and layout errors, as well as the limitations of LLMs when it comes to utilizing document layout. Our results indicate that layout enrichment can improve the performance of purely text-based LLMs for document understanding by up to 15% compared to just using plain document text. In conclusion, this approach should be considered for the best model choice between text-based LLM or multi-modal document transformers.

cs.CL↗

arXiv2024

Deeper, Sharper, Faster: Application of Efficient Transformer to Galaxy Image Restoration

The Transformer architecture has revolutionized the field of deep learning over the past several years in diverse areas, including natural language processing, code generation, image recognition, time series forecasting, etc. We propose to apply Zamir et al.'s efficient transformer to perform deconvolution and denoising to enhance astronomical images. We conducted experiments using pairs of high-quality images and their degraded versions, and our deep learning model demonstrates exceptional restoration of photometric, structural, and morphological information. When compared with the ground-truth JWST images, the enhanced versions of our HST-quality images reduce the scatter of isophotal photometry, Sersic index, and half-light radius by factors of 4.4, 3.6, and 4.7, respectively, with Pearson correlation coefficients approaching unity. The performance is observed to degrade when input images exhibit correlated noise, point-like sources, and artifacts. We anticipate that this deep learning model will prove valuable for a number of scientific applications, including precision photometry, morphological analysis, and shear calibration.

astro-ph.IM↗

arXiv2025

Adaptive Query Prompting for Multi-Domain Landmark Detection

Medical landmark detection is crucial in various medical imaging modalities and procedures. Although deep learning-based methods have achieve promising performance, they are mostly designed for specific anatomical regions or tasks. In this work, we propose a universal model for multi-domain landmark detection by leveraging transformer architecture and developing a prompting component, named as Adaptive Query Prompting (AQP). Instead of embedding additional modules in the backbone network, we design a separate module to generate prompts that can be effectively extended to any other transformer network. In our proposed AQP, prompts are learnable parameters maintained in a memory space called prompt pool. The central idea is to keep the backbone frozen and then optimize prompts to instruct the model inference process. Furthermore, we employ a lightweight decoder to decode landmarks from the extracted features, namely Light-MLD. Thanks to the lightweight nature of the decoder and AQP, we can handle multiple datasets by sharing the backbone encoder and then only perform partial parameter tuning without incurring much additional cost. It has the potential to be extended to more landmark detection tasks. We conduct experiments on three widely used X-ray datasets for different medical landmark detection tasks. Our proposed Light-MLD coupled with AQP achieves SOTA performance on many metrics even without the use of elaborate structural designs or complex frameworks.

cs.CV↗

arXiv2024

Conversational Topic Recommendation in Counseling and Psychotherapy with Decision Transformer and Large Language Models

Given the increasing demand for mental health assistance, artificial intelligence (AI), particularly large language models (LLMs), may be valuable for integration into automated clinical support systems. In this work, we leverage a decision transformer architecture for topic recommendation in counseling conversations between patients and mental health professionals. The architecture is utilized for offline reinforcement learning, and we extract states (dialogue turn embeddings), actions (conversation topics), and rewards (scores measuring the alignment between patient and therapist) from previous turns within a conversation to train a decision transformer model. We demonstrate an improvement over baseline reinforcement learning methods, and propose a novel system of utilizing our model's output as synthetic labels for fine-tuning a large language model for the same task. Although our implementation based on LLaMA-2 7B has mixed results, future work can undoubtedly build on the design.

cs.CL↗

arXiv2025

Dinomaly: The Less Is More Philosophy in Multi-Class Unsupervised Anomaly Detection

Recent studies highlighted a practical setting of unsupervised anomaly detection (UAD) that builds a unified model for multi-class images. Despite various advancements addressing this challenging task, the detection performance under the multi-class setting still lags far behind state-of-the-art class-separated models. Our research aims to bridge this substantial performance gap. In this paper, we introduce a minimalistic reconstruction-based anomaly detection framework, namely Dinomaly, which leverages pure Transformer architectures without relying on complex designs, additional modules, or specialized tricks. Given this powerful framework consisted of only Attentions and MLPs, we found four simple components that are essential to multi-class anomaly detection: (1) Foundation Transformers that extracts universal and discriminative features, (2) Noisy Bottleneck where pre-existing Dropouts do all the noise injection tricks, (3) Linear Attention that naturally cannot focus, and (4) Loose Reconstruction that does not force layer-to-layer and point-by-point reconstruction. Extensive experiments are conducted across popular anomaly detection benchmarks including MVTec-AD, VisA, and Real-IAD. Our proposed Dinomaly achieves impressive image-level AUROC of 99.6%, 98.7%, and 89.3% on the three datasets respectively, which is not only superior to state-of-the-art multi-class UAD methods, but also achieves the most advanced class-separated UAD records.

cs.CV↗

arXiv2026

When Can Transformers Count to n?

Large language models based on the transformer architecture can solve highly complex tasks, yet their fundamental limitations on simple algorithmic problems remain poorly understood. In this work, we focus on basic counting tasks and investigate how the difficulty of these tasks scales with the transformer embedding dimension, the context length, and the vocabulary size. We reveal a sharp theoretical phase transition governed by the relationship between the embedding dimension and the vocabulary size. When the dimension is at least as large as the vocabulary, transformers can perfectly maintain token counts. However, when the vocabulary exceeds the embedding dimension, the interference between non-orthogonal token representations forces the network weights to scale polynomially. This renders the exact counting algorithm numerically unstable and practically unlearnable. We empirically validate this bottleneck by training transformers from scratch, demonstrating a strict performance drop at the theoretical threshold and catastrophic out of distribution failure when scaling the vocabulary or context length. Furthermore, we show that state-of-the-art pretrained models suffer from similar failure cases. Our work reveals a critical blind spot absent from the current literature regarding the connection among these three parameters, proving that vocabulary size fundamentally dictates the difficulty of counting tasks.

cs.CL↗

arXiv2024

A short trajectory is all you need: A transformer-based model for long-time dissipative quantum dynamics

In this communication we demonstrate that a deep artificial neural network based on a transformer architecture with self-attention layers can predict the long-time population dynamics of a quantum system coupled to a dissipative environment provided that the short-time population dynamics of the system is known. The transformer neural network model developed in this work predicts the long-time dynamics of spin-boson model efficiently and very accurately across different regimes, from weak system-bath coupling to strong coupling non-Markovian regimes. Our model is more accurate than classical forecasting models, such as recurrent neural networks and is comparable to the state-of-the-art models for simulating the dynamics of quantum dissipative systems based on kernel ridge regression.

quant-ph↗