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 811 records · Page 45Linked to original sources

arXiv2024

WaveMixSR-V2: Enhancing Super-resolution with Higher Efficiency

Recent advancements in single image super-resolution have been predominantly driven by token mixers and transformer architectures. WaveMixSR utilized the WaveMix architecture, employing a two-dimensional discrete wavelet transform for spatial token mixing, achieving superior performance in super-resolution tasks with remarkable resource efficiency. In this work, we present an enhanced version of the WaveMixSR architecture by (1) replacing the traditional transpose convolution layer with a pixel shuffle operation and (2) implementing a multistage design for higher resolution tasks ($4\times$). Our experiments demonstrate that our enhanced model -- WaveMixSR-V2 -- outperforms other architectures in multiple super-resolution tasks, achieving state-of-the-art for the BSD100 dataset, while also consuming fewer resources, exhibits higher parameter efficiency, lower latency and higher throughput. Our code is available at https://github.com/pranavphoenix/WaveMixSR.

eess.IV↗

arXiv2021

When Does Pretraining Help? Assessing Self-Supervised Learning for Law and the CaseHOLD Dataset

While self-supervised learning has made rapid advances in natural language processing, it remains unclear when researchers should engage in resource-intensive domain-specific pretraining (domain pretraining). The law, puzzlingly, has yielded few documented instances of substantial gains to domain pretraining in spite of the fact that legal language is widely seen to be unique. We hypothesize that these existing results stem from the fact that existing legal NLP tasks are too easy and fail to meet conditions for when domain pretraining can help. To address this, we first present CaseHOLD (Case Holdings On Legal Decisions), a new dataset comprised of over 53,000+ multiple choice questions to identify the relevant holding of a cited case. This dataset presents a fundamental task to lawyers and is both legally meaningful and difficult from an NLP perspective (F1 of 0.4 with a BiLSTM baseline). Second, we assess performance gains on CaseHOLD and existing legal NLP datasets. While a Transformer architecture (BERT) pretrained on a general corpus (Google Books and Wikipedia) improves performance, domain pretraining (using corpus of approximately 3.5M decisions across all courts in the U.S. that is larger than BERT's) with a custom legal vocabulary exhibits the most substantial performance gains with CaseHOLD (gain of 7.2% on F1, representing a 12% improvement on BERT) and consistent performance gains across two other legal tasks. Third, we show that domain pretraining may be warranted when the task exhibits sufficient similarity to the pretraining corpus: the level of performance increase in three legal tasks was directly tied to the domain specificity of the task. Our findings inform when researchers should engage resource-intensive pretraining and show that Transformer-based architectures, too, learn embeddings suggestive of distinct legal language.

cs.CL↗

arXiv2025

FireFly-T: High-Throughput Sparsity Exploitation for Spiking Transformer Acceleration with Dual-Engine Overlay Architecture

Spiking transformers are emerging as a promising architecture that combines the energy efficiency of Spiking Neural Networks (SNNs) with the powerful attention mechanisms of transformers. However, existing hardware accelerators lack support for spiking attention, exhibit limited throughput in exploiting fine-grained sparsity, and struggle with scalable parallelism in sparse computation. To address these, we propose FireFly-T, a dual-engine overlay architecture that integrates a sparse engine for activation sparsity and a binary engine for spiking attention. In the sparse engine, we propose a highthroughput sparse decoder that exploits fine-grained sparsity by concurrently extracting multiple non-zero spikes. To complement this, we introduce a scalable load balancing mechanism with weight dispatch and out-of-order execution, eliminating bank conflicts to support scalable multidimensional parallelism. In the binary engine, we leverage the byte-level write capability of SRAMs to efficiently manipulate the 3D dataflows required for spiking attention with minimal resource overhead. We also optimize the core AND-PopCount operation in spiking attention through a LUT6-based implementation, improving timing closure and reducing LUT utilization on Xilinx FPGAs. As an overlay architecture, FireFly-T further incorporates an orchestrator that dynamically manipulates input dataflows with flexible adaptation for diverse network topologies, while ensuring efficient resource utilization and maintaining high throughput. Experimental results demonstrate that our accelerator achieves $1.39\times$ and $2.40\times$ higher energy efficiency, as well as $4.21\times$ and $7.10\times$ greater DSP efficiency, compared to FireFly v2 and the transformer-enabled SpikeTA, respectively. These results highlight its potential as an efficient hardware platform for spiking transformer.

cs.AR↗

arXiv2022

TransCenter: Transformers with Dense Representations for Multiple-Object Tracking

Transformers have proven superior performance for a wide variety of tasks since they were introduced. In recent years, they have drawn attention from the vision community in tasks such as image classification and object detection. Despite this wave, an accurate and efficient multiple-object tracking (MOT) method based on transformers is yet to be designed. We argue that the direct application of a transformer architecture with quadratic complexity and insufficient noise-initialized sparse queries - is not optimal for MOT. We propose TransCenter, a transformer-based MOT architecture with dense representations for accurately tracking all the objects while keeping a reasonable runtime. Methodologically, we propose the use of image-related dense detection queries and efficient sparse tracking queries produced by our carefully designed query learning networks (QLN). On one hand, the dense image-related detection queries allow us to infer targets' locations globally and robustly through dense heatmap outputs. On the other hand, the set of sparse tracking queries efficiently interacts with image features in our TransCenter Decoder to associate object positions through time. As a result, TransCenter exhibits remarkable performance improvements and outperforms by a large margin the current state-of-the-art methods in two standard MOT benchmarks with two tracking settings (public/private). TransCenter is also proven efficient and accurate by an extensive ablation study and comparisons to more naive alternatives and concurrent works. For scientific interest, the code is made publicly available at https://github.com/yihongxu/transcenter.

cs.CV↗

arXiv2025

$ShiftwiseConv:$ Small Convolutional Kernel with Large Kernel Effect

Large kernels make standard convolutional neural networks (CNNs) great again over transformer architectures in various vision tasks. Nonetheless, recent studies meticulously designed around increasing kernel size have shown diminishing returns or stagnation in performance. Thus, the hidden factors of large kernel convolution that affect model performance remain unexplored. In this paper, we reveal that the key hidden factors of large kernels can be summarized as two separate components: extracting features at a certain granularity and fusing features by multiple pathways. To this end, we leverage the multi-path long-distance sparse dependency relationship to enhance feature utilization via the proposed Shiftwise (SW) convolution operator with a pure CNN architecture. In a wide range of vision tasks such as classification, segmentation, and detection, SW surpasses state-of-the-art transformers and CNN architectures, including SLaK and UniRepLKNet. More importantly, our experiments demonstrate that $3 \times 3$ convolutions can replace large convolutions in existing large kernel CNNs to achieve comparable effects, which may inspire follow-up works. Code and all the models at https://github.com/lidc54/shift-wiseConv.

cs.CV↗

arXiv2021

3D Human Pose Estimation with Spatial and Temporal Transformers

Transformer architectures have become the model of choice in natural language processing and are now being introduced into computer vision tasks such as image classification, object detection, and semantic segmentation. However, in the field of human pose estimation, convolutional architectures still remain dominant. In this work, we present PoseFormer, a purely transformer-based approach for 3D human pose estimation in videos without convolutional architectures involved. Inspired by recent developments in vision transformers, we design a spatial-temporal transformer structure to comprehensively model the human joint relations within each frame as well as the temporal correlations across frames, then output an accurate 3D human pose of the center frame. We quantitatively and qualitatively evaluate our method on two popular and standard benchmark datasets: Human3.6M and MPI-INF-3DHP. Extensive experiments show that PoseFormer achieves state-of-the-art performance on both datasets. Code is available at \url{https://github.com/zczcwh/PoseFormer}

cs.CV↗

arXiv2026

Lizard: An Efficient Linearization Framework for Large Language Models

We propose Lizard, a linearization framework that transforms pretrained Transformer-based Large Language Models (LLMs) into subquadratic architectures. Transformers faces severe computational and memory bottlenecks with long sequences due to the quadratic complexity of softmax attention and the growing Key-Value (KV) cache that makes inference memory-bound by context length. Lizard addresses these limitations by introducing a subquadratic attention mechanism that closely approximates softmax attention while preserving model quality. Unlike prior linearization methods constrained by fixed, non-adaptive structures, Lizard augments the architecture with compact, learnable modules that enable adaptive memory control and robust length generalization. Moreover, we introduce a hardwareaware algorithm that solves numerical instability in gated attention to accelerate training. Extensive experiments show that Lizard achieves near-lossless recovery of its teacher model's performance, significantly outperforming previous methods by up to 9.4 - 24.5 points on the 5-shot MMLU benchmark and demonstrating superior associative recall.

cs.CL↗

arXiv2023

Hiformer: Heterogeneous Feature Interactions Learning with Transformers for Recommender Systems

Learning feature interaction is the critical backbone to building recommender systems. In web-scale applications, learning feature interaction is extremely challenging due to the sparse and large input feature space; meanwhile, manually crafting effective feature interactions is infeasible because of the exponential solution space. We propose to leverage a Transformer-based architecture with attention layers to automatically capture feature interactions. Transformer architectures have witnessed great success in many domains, such as natural language processing and computer vision. However, there has not been much adoption of Transformer architecture for feature interaction modeling in industry. We aim at closing the gap. We identify two key challenges for applying the vanilla Transformer architecture to web-scale recommender systems: (1) Transformer architecture fails to capture the heterogeneous feature interactions in the self-attention layer; (2) The serving latency of Transformer architecture might be too high to be deployed in web-scale recommender systems. We first propose a heterogeneous self-attention layer, which is a simple yet effective modification to the self-attention layer in Transformer, to take into account the heterogeneity of feature interactions. We then introduce \textsc{Hiformer} (\textbf{H}eterogeneous \textbf{I}nteraction Trans\textbf{former}) to further improve the model expressiveness. With low-rank approximation and model pruning, \hiformer enjoys fast inference for online deployment. Extensive offline experiment results corroborates the effectiveness and efficiency of the \textsc{Hiformer} model. We have successfully deployed the \textsc{Hiformer} model to a real world large scale App ranking model at Google Play, with significant improvement in key engagement metrics (up to +2.66\%).

cs.IR↗

arXiv2023

Vision Language Transformers: A Survey

Vision language tasks, such as answering questions about or generating captions that describe an image, are difficult tasks for computers to perform. A relatively recent body of research has adapted the pretrained transformer architecture introduced in \citet{vaswani2017attention} to vision language modeling. Transformer models have greatly improved performance and versatility over previous vision language models. They do so by pretraining models on a large generic datasets and transferring their learning to new tasks with minor changes in architecture and parameter values. This type of transfer learning has become the standard modeling practice in both natural language processing and computer vision. Vision language transformers offer the promise of producing similar advancements in tasks which require both vision and language. In this paper, we provide a broad synthesis of the currently available research on vision language transformer models and offer some analysis of their strengths, limitations and some open questions that remain.

cs.CV↗

arXiv2025

Why Do Transformers Fail to Forecast Time Series In-Context?

Time series forecasting (TSF) remains a challenging and largely unsolved problem in machine learning, despite significant recent efforts leveraging Large Language Models (LLMs), which predominantly rely on Transformer architectures. Empirical evidence consistently shows that even powerful Transformers often fail to outperform much simpler models, e.g., linear models, on TSF tasks; however, a rigorous theoretical understanding of this phenomenon remains limited. In this paper, we provide a theoretical analysis of Transformers' limitations for TSF through the lens of In-Context Learning (ICL) theory. Specifically, under AR($p$) data, we establish that: (1) Linear Self-Attention (LSA) models $\textit{cannot}$ achieve lower expected MSE than classical linear models for in-context forecasting; (2) as the context length approaches to infinity, LSA asymptotically recovers the optimal linear predictor; and (3) under Chain-of-Thought (CoT) style inference, predictions collapse to the mean exponentially. We empirically validate these findings through carefully designed experiments. Our theory not only sheds light on several previously underexplored phenomena but also offers practical insights for designing more effective forecasting architectures. We hope our work encourages the broader research community to revisit the fundamental theoretical limitations of TSF and to critically evaluate the direct application of increasingly sophisticated architectures without deeper scrutiny.

cs.LG↗

arXiv2024

NetMamba: Efficient Network Traffic Classification via Pre-training Unidirectional Mamba

Network traffic classification is a crucial research area aiming to enhance service quality, streamline network management, and bolster cybersecurity. To address the growing complexity of transmission encryption techniques, various machine learning and deep learning methods have been proposed. However, existing approaches face two main challenges. Firstly, they struggle with model inefficiency due to the quadratic complexity of the widely used Transformer architecture. Secondly, they suffer from inadequate traffic representation because of discarding important byte information while retaining unwanted biases. To address these challenges, we propose NetMamba, an efficient linear-time state space model equipped with a comprehensive traffic representation scheme. We adopt a specially selected and improved unidirectional Mamba architecture for the networking field, instead of the Transformer, to address efficiency issues. In addition, we design a traffic representation scheme to extract valid information from massive traffic data while removing biased information. Evaluation experiments on six public datasets encompassing three main classification tasks showcase NetMamba's superior classification performance compared to state-of-the-art baselines. It achieves an accuracy rate of nearly 99% (some over 99%) in all tasks. Additionally, NetMamba demonstrates excellent efficiency, improving inference speed by up to 60 times while maintaining comparably low memory usage. Furthermore, NetMamba exhibits superior few-shot learning abilities, achieving better classification performance with fewer labeled data. To the best of our knowledge, NetMamba is the first model to tailor the Mamba architecture for networking.

cs.LG↗

arXiv2019

Music theme recognition using CNN and self-attention

We present an efficient architecture to detect mood/themes in music tracks on autotagging-moodtheme subset of the MTG-Jamendo dataset. Our approach consists of two blocks, a CNN block based on MobileNetV2 architecture and a self-attention block from Transformer architecture to capture long term temporal characteristics. We show that our proposed model produces a significant improvement over the baseline model. Our model (team name: AMLAG) achieves 4th place on PR-AUC-macro Leaderboard in MediaEval 2019: Emotion and Theme Recognition in Music Using Jamendo.

cs.SD↗

arXiv2022

Long-Short Temporal Contrastive Learning of Video Transformers

Video transformers have recently emerged as a competitive alternative to 3D CNNs for video understanding. However, due to their large number of parameters and reduced inductive biases, these models require supervised pretraining on large-scale image datasets to achieve top performance. In this paper, we empirically demonstrate that self-supervised pretraining of video transformers on video-only datasets can lead to action recognition results that are on par or better than those obtained with supervised pretraining on large-scale image datasets, even massive ones such as ImageNet-21K. Since transformer-based models are effective at capturing dependencies over extended temporal spans, we propose a simple learning procedure that forces the model to match a long-term view to a short-term view of the same video. Our approach, named Long-Short Temporal Contrastive Learning (LSTCL), enables video transformers to learn an effective clip-level representation by predicting temporal context captured from a longer temporal extent. To demonstrate the generality of our findings, we implement and validate our approach under three different self-supervised contrastive learning frameworks (MoCo v3, BYOL, SimSiam) using two distinct video-transformer architectures, including an improved variant of the Swin Transformer augmented with space-time attention. We conduct a thorough ablation study and show that LSTCL achieves competitive performance on multiple video benchmarks and represents a convincing alternative to supervised image-based pretraining.

cs.CV↗

arXiv2022

TENT: Tensorized Encoder Transformer for Temperature Forecasting

Reliable weather forecasting is of great importance in science, business, and society. The best performing data-driven models for weather prediction tasks rely on recurrent or convolutional neural networks, where some of which incorporate attention mechanisms. In this work, we introduce a novel model based on Transformer architecture for weather forecasting. The proposed Tensorial Encoder Transformer (TENT) model is equipped with tensorial attention and thus it exploits the spatiotemporal structure of weather data by processing it in multidimensional tensorial format. We show that compared to the classical encoder transformer, 3D convolutional neural networks, LSTM, and Convolutional LSTM, the proposed TENT model can better learn the underlying complex pattern of the weather data for the studied temperature prediction task. Experiments on two real-life weather datasets are performed. The datasets consist of historical measurements from weather stations in the USA, Canada and Europe. The first dataset contains hourly measurements of weather attributes for 30 cities in the USA and Canada from October 2012 to November 2017. The second dataset contains daily measurements of weather attributes of 18 cities across Europe from May 2005 to April 2020. Two attention scores are introduced based on the obtained tonsorial attention and are visualized in order to shed light on the decision-making process of our model and provide insight knowledge on the most important cities for the target cities.

cs.LG↗

arXiv2022

PQ-Transformer: Jointly Parsing 3D Objects and Layouts from Point Clouds

3D scene understanding from point clouds plays a vital role for various robotic applications. Unfortunately, current state-of-the-art methods use separate neural networks for different tasks like object detection or room layout estimation. Such a scheme has two limitations: 1) Storing and running several networks for different tasks are expensive for typical robotic platforms. 2) The intrinsic structure of separate outputs are ignored and potentially violated. To this end, we propose the first transformer architecture that predicts 3D objects and layouts simultaneously, using point cloud inputs. Unlike existing methods that either estimate layout keypoints or edges, we directly parameterize room layout as a set of quads. As such, the proposed architecture is termed as P(oint)Q(uad)-Transformer. Along with the novel quad representation, we propose a tailored physical constraint loss function that discourages object-layout interference. The quantitative and qualitative evaluations on the public benchmark ScanNet show that the proposed PQ-Transformer succeeds to jointly parse 3D objects and layouts, running at a quasi-real-time (8.91 FPS) rate without efficiency-oriented optimization. Moreover, the new physical constraint loss can improve strong baselines, and the F1-score of the room layout is significantly promoted from 37.9% to 57.9%.

cs.CV↗

arXiv2022

End-to-End Instance Edge Detection

Edge detection has long been an important problem in the field of computer vision. Previous works have explored category-agnostic or category-aware edge detection. In this paper, we explore edge detection in the context of object instances. Although object boundaries could be easily derived from segmentation masks, in practice, instance segmentation models are trained to maximize IoU to the ground-truth mask, which means that segmentation boundaries are not enforced to precisely align with ground-truth edge boundaries. Thus, the task of instance edge detection itself is different and critical. Since precise edge detection requires high resolution feature maps, we design a novel transformer architecture that efficiently combines a FPN and a transformer decoder to enable cross attention on multi-scale high resolution feature maps within a reasonable computation budget. Further, we propose a light weight dense prediction head that is applicable to both instance edge and mask detection. Finally, we use a penalty reduced focal loss to effectively train the model with point supervision on instance edges, which can reduce annotation costs. We demonstrate highly competitive instance edge detection performance compared to state-of-the-art baselines, and also show that the proposed task and loss are complementary to instance segmentation and object detection.

cs.CV↗

arXiv2022

Proxyless Neural Architecture Adaptation for Supervised Learning and Self-Supervised Learning

Recently, Neural Architecture Search (NAS) methods have been introduced and show impressive performance on many benchmarks. Among those NAS studies, Neural Architecture Transformer (NAT) aims to adapt the given neural architecture to improve performance while maintaining computational costs. However, NAT lacks reproducibility and it requires an additional architecture adaptation process before network weight training. In this paper, we propose proxyless neural architecture adaptation that is reproducible and efficient. Our method can be applied to both supervised learning and self-supervised learning. The proposed method shows stable performance on various architectures. Extensive reproducibility experiments on two datasets, i.e., CIFAR-10 and Tiny Imagenet, present that the proposed method definitely outperforms NAT and is applicable to other models and datasets.

cs.LG↗

arXiv2022

Conviformers: Convolutionally guided Vision Transformer

Vision transformers are nowadays the de-facto choice for image classification tasks. There are two broad categories of classification tasks, fine-grained and coarse-grained. In fine-grained classification, the necessity is to discover subtle differences due to the high level of similarity between sub-classes. Such distinctions are often lost as we downscale the image to save the memory and computational cost associated with vision transformers (ViT). In this work, we present an in-depth analysis and describe the critical components for developing a system for the fine-grained categorization of plants from herbarium sheets. Our extensive experimental analysis indicated the need for a better augmentation technique and the ability of modern-day neural networks to handle higher dimensional images. We also introduce a convolutional transformer architecture called Conviformer which, unlike the popular Vision Transformer (ConViT), can handle higher resolution images without exploding memory and computational cost. We also introduce a novel, improved pre-processing technique called PreSizer to resize images better while preserving their original aspect ratios, which proved essential for classifying natural plants. With our simple yet effective approach, we achieved SoTA on Herbarium 202x and iNaturalist 2019 dataset.

cs.CV↗