As an essential ingredient of modern deep learning, attention mechanism, especially self-attention, plays a vital role in the global correlation discovery. However, is hand-crafted attention irreplaceable when modeling the global context? Our intriguing finding is that self-attention is not better than the matrix decomposition (MD) model developed 20 years ago regarding the performance and computational cost for encoding the long-distance dependencies. We model the global context issue as a low-rank recovery problem and show that its optimization algorithms can help design global information blocks. This paper then proposes a series of Hamburgers, in which we employ the optimization algorithms for solving MDs to factorize the input representations into sub-matrices and reconstruct a low-rank embedding. Hamburgers with different MDs can perform favorably against the popular global context module self-attention when carefully coping with gradients back-propagated through MDs. Comprehensive experiments are conducted in the vision tasks where it is crucial to learn the global context, including semantic segmentation and image generation, demonstrating significant improvements over self-attention and its variants.
Few-Shot Specific Emitter Identification via Integrated Complex Variational Mode Decomposition and Spatial Attention Transfer
School of Information Science and Technology, Harbin Institute of Technology (Shenzhen)（信息科学与技术学院，哈尔滨工业大学（深圳））；Ranplan Wireless Network Design Ltd.（Ranplan无线网络设计有限公司）
College of Intelligence and Computing, Tianjin University（天津大学智能与计算学部）；Microsoft Research Asia（微软亚洲研究院）；School of Computer Science and Technology, Beijing Institute of Technology（北京理工大学计算机学院）
Latest development of neural models has connected the encoder and decoder through a self-attention mechanism. In particular, Transformer, which is solely based on self-attention, has led to breakthroughs in Natural Language Processing (NLP) tasks. However, the multi-head attention mechanism, as a key component of Transformer, limits the effective deployment of the model to a resource-limited setting. In this paper, based on the ideas of tensor decomposition and parameters sharing, we propose a novel self-attention model (namely Multi-linear attention) with Block-Term Tensor Decomposition (BTD)…
Extending the forecasting time is a critical demand for real applications, such as extreme weather early warning and long-term energy consumption planning. This paper studies the long-term forecasting problem of time series. Prior Transformer-based models adopt various self-attention mechanisms to discover the long-range dependencies. However, intricate temporal patterns of the long-term future prohibit the model from finding reliable dependencies. Also, Transformers have to adopt the sparse versions of point-wise self-attentions for long series efficiency, resulting in the information utiliza…
Image datasets with high-quality pixel-level annotations are valuable for semantic segmentation: labelling every pixel in an image ensures that rare classes and small objects are annotated. However, full-image annotations are expensive, with experts spending up to 90 minutes per image. We propose block sub-image annotation as a replacement for full-image annotation. Despite the attention cost of frequent task switching, we find that block annotations can be crowdsourced at higher quality compared to full-image annotation with equal monetary cost using existing annotation tools developed for fu…
We propose a new attention model for video question answering. The main idea of the attention models is to locate on the most informative parts of the visual data. The attention mechanisms are quite popular these days. However, most existing visual attention mechanisms regard the question as a whole. They ignore the word-level semantics where each word can have different attentions and some words need no attention. Neither do they consider the semantic structure of the sentences. Although the Extended Soft Attention (E-SA) model for video question answering leverages the word-level attention, …
Attention Normalization Impacts Cardinality Generalization in Slot Attention
Max Planck Institute for Intelligent Systems（马克斯·普朗克智能系统研究所）；University of Augsburg（奥格斯堡大学）；Robert Bosch GmbH - Corporate Research（罗伯特·博世有限公司企业研究部）；Bosch Center for Artificial Intelligence (BCAI)（博世人工智能中心）
INESC TEC（葡萄牙系统与计算机工程研究所）；University of Porto（波尔图大学）
The increasing popularity of attention mechanisms in deep learning algorithms for computer vision and natural language processing made these models attractive to other research domains. In healthcare, there is a strong need for tools that may improve the routines of the clinicians and the patients. Naturally, the use of attention-based algorithms for medical applications occurred smoothly. However, being healthcare a domain that depends on high-stake decisions, the scientific community must ponder if these high-performing algorithms fit the needs of medical applications. With this motto, this …
In this paper we present an unconventional image segmentation approach which is devised to meet the requirements of image understanding and pattern recognition tasks. Generally image understanding assumes interplay of two sub-processes: image information content discovery and image information content interpretation. Despite of its widespread use, the notion of "image information content" is still ill defined, intuitive, and ambiguous. Most often, it is used in the Shannon's sense, which means information content assessment averaged over the whole signal ensemble. Humans, however,rarely resort…
Class Activation Mapping (CAM) is a powerful technique used to understand the decision making of Convolutional Neural Network (CNN) in computer vision. Recently, there have been attempts not only to generate better visual explanations, but also to improve classification performance using visual explanations. However, the previous works still have their own drawbacks. In this paper, we propose a novel architecture, LFI-CAM, which is trainable for image classification and visual explanation in an end-to-end manner. LFI-CAM generates an attention map for visual explanation during forward propagat…
Few-Shot Object Detection (FSOD) methods are mainly designed and evaluated on natural image datasets such as Pascal VOC and MS COCO. However, it is not clear whether the best methods for natural images are also the best for aerial images. Furthermore, direct comparison of performance between FSOD methods is difficult due to the wide variety of detection frameworks and training strategies. Therefore, we propose a benchmarking framework that provides a flexible environment to implement and compare attention-based FSOD methods. The proposed framework focuses on attention mechanisms and is divided…
Tsinghua University（清华大学）；Nanjing University of Science and Technology（南京理工大学）；Peking Union Medical College, Chinese Academy of Medical Sciences（中国医学科学院北京协和医学院）
Science of science (SciSci) is an emerging discipline wherein science is used to study the structure and evolution of science itself using large data sets. The increasing availability of digital data on scholarly outcomes offers unprecedented opportunities to explore SciSci. In the progress of science, the previously discovered knowledge principally inspires new scientific ideas, and citation is a reasonably good reflection of this cumulative nature of scientific research. The researches that choose potentially influential references will have a lead over the emerging publications. Although th…
A Multi-Scale Decomposition MLP-Mixer for Time Series Analysis
The Hong Kong University of Science and Technology（香港科技大学）；BNU-HKBU United International College（北京师范大学-香港浸会大学联合国际学院）；Guangzhou Urban Planning and Design Survey Research Institute（广州市城市规划勘测设计研究院）
Infinity Lab（无限实验室）；Stevens Institute of Technology（史蒂文斯理工学院）
Attention mechanisms have recently demonstrated impressive performance on a range of NLP tasks, and attention scores are often used as a proxy for model explainability. However, there is a debate on whether attention weights can, in fact, be used to identify the most important inputs to a model. We approach this question from an information theoretic perspective by measuring the mutual information between the model output and the hidden states. From extensive experiments, we draw the following conclusions: (i) Additive and Deep attention mechanisms are likely to be better at preserving the inf…
Technion Institute of Technology（以色列理工学院）；Rambam Health Care Campus（兰巴姆医疗中心）
A key concern in integrating machine learning models in medicine is the ability to interpret their reasoning. Popular explainability methods have demonstrated satisfactory results in natural image recognition, yet in medical image analysis, many of these approaches provide partial and noisy explanations. Recently, attention mechanisms have shown compelling results both in their predictive performance and in their interpretable qualities. A fundamental trait of attention is that it leverages salient parts of the input which contribute to the model's prediction. To this end, our work focuses on …
Center of Excellence in Visual Intelligence（视觉智能卓越中心）；KLE Technological University（KLE理工大学）
In this paper, we propose Attention Based Decomposition Network (ABD-Net), for point cloud decomposition into basic geometric shapes namely, plane, sphere, cone and cylinder. We show improved performance of 3D object classification using attention features based on primitive shapes in point clouds. Point clouds, being the simple and compact representation of 3D objects have gained increasing popularity. They demand robust methods for feature extraction due to unorderness in point sets. In ABD-Net the proposed Local Proximity Encapsulator captures the local geometric variations along with spati…
Recently, scene text detection has been a challenging task. Texts with arbitrary shape or large aspect ratio are usually hard to detect. Previous segmentation-based methods can describe curve text more accurately but suffer from over segmentation and text adhesion. In this paper, we propose attention-based feature decomposition-reconstruction network for scene text detection, which utilizes contextual information and low-level feature to enhance the performance of segmentation-based text detector. In the phase of feature fusion, we introduce cross level attention module to enrich contextual in…
Intrinsic image decomposition is a challenging, long-standing computer vision problem for which ground truth data is very difficult to acquire. We explore the use of synthetic data for training CNN-based intrinsic image decomposition models, then applying these learned models to real-world images. To that end, we present \ICG, a new, large-scale dataset of physically-based rendered images of scenes with full ground truth decompositions. The rendering process we use is carefully designed to yield high-quality, realistic images, which we find to be crucial for this problem domain. We also propos…
Faster Diffusion via Temporal Attention Decomposition
Center of Excellence for Generative AI, King Abdullah University of Science and Technology (KAUST)（阿卜杜拉国王科技大学生成式AI卓越中心）；Show Lab, National University of Singapore (NUS)（新加坡国立大学Show Lab）；Swiss AI Lab, IDSIA, USI & SUPSI（瑞士AI实验室）；Meta AI
The ability to decompose complex multi-object scenes into meaningful abstractions like objects is fundamental to achieve higher-level cognition. Previous approaches for unsupervised object-oriented scene representation learning are either based on spatial-attention or scene-mixture approaches and limited in scalability which is a main obstacle towards modeling real-world scenes. In this paper, we propose a generative latent variable model, called SPACE, that provides a unified probabilistic modeling framework that combines the best of spatial-attention and scene-mixture approaches. SPACE can e…
Fraunhofer Institute for Computer Graphics Research IGD（弗劳恩霍夫计算机图形研究所）；TU Darmstadt（达姆施塔特工业大学）
With the increased deployment of face recognition systems in our daily lives, face presentation attack detection (PAD) is attracting much attention and playing a key role in securing face recognition systems. Despite the great performance achieved by the hand-crafted and deep-learning-based methods in intra-dataset evaluations, the performance drops when dealing with unseen scenarios. In this work, we propose a dual-stream convolution neural networks (CNNs) framework. One stream adapts four learnable frequency filters to learn features in the frequency domain, which are less influenced by vari…
University of California San Diego（加利福尼亚大学圣迭戈分校）；Microsoft（微软公司）
Recent research in dynamic convolution shows substantial performance boost for efficient CNNs, due to the adaptive aggregation of K static convolution kernels. It has two limitations: (a) it increases the number of convolutional weights by K-times, and (b) the joint optimization of dynamic attention and static convolution kernels is challenging. In this paper, we revisit it from a new perspective of matrix decomposition and reveal the key issue is that dynamic convolution applies dynamic attention over channel groups after projecting into a higher dimensional latent space. To address this issu…
The objective of this paper is to be able to separate a video into its natural layers, and to control which of the separated layers to attend to. For example, to be able to separate reflections, transparency or object motion. We make the following three contributions: (i) we introduce a new structured neural network architecture that explicitly incorporates layers (as spatial masks) into its design. This improves separation performance over previous general purpose networks for this task; (ii) we demonstrate that we can augment the architecture to leverage external cues such as audio for contr…
Variational Auto-Encoders have often been used for unsupervised pretraining, feature extraction and out-of-distribution and anomaly detection in the medical field. However, VAEs often lack the ability to produce sharp images and learn high-level features. We propose to alleviate these issues by adding a new branch to conditional hierarchical VAEs. This enforces a division between higher-level and lower-level features. Despite the additional computational overhead compared to a normal VAE it results in sharper and better reconstructions and can capture the data distribution similarly well (indi…
The University of Sydney（悉尼大学）；BAIDU USA LLC（百度美国有限责任公司）；SenseTime Group Limited（商汤集团有限公司）；University of Oxford（牛津大学）
In this paper, we observe two levels of redundancies when applying vision transformers (ViT) for image recognition. First, fixing the number of tokens through the whole network produces redundant features at the spatial level. Second, the attention maps among different transformer layers are redundant. Based on the observations above, we propose a PSViT: a ViT with token Pooling and attention Sharing to reduce the redundancy, effectively enhancing the feature representation ability, and achieving a better speed-accuracy trade-off. Specifically, in our PSViT, token pooling can be defined as the…
Tsinghua Shenzhen International Graduate School, Tsinghua University（清华大学深圳国际研究生院）；University College London（伦敦大学学院）
Image quality assessment (IQA) algorithm aims to quantify the human perception of image quality. Unfortunately, there is a performance drop when assessing the distortion images generated by generative adversarial network (GAN) with seemingly realistic texture. In this work, we conjecture that this maladaptation lies in the backbone of IQA models, where patch-level prediction methods use independent image patches as input to calculate their scores separately, but lack spatial relationship modeling among image patches. Therefore, we propose an Attention-based Hybrid Image Quality Assessment Netw…
Towards Better Multi-head Attention via Channel-wise Sample Permutation
Gaoling School of Artificial Intelligence, Renmin University of China（中国人民大学高瓴人工智能学院）；Beijing Key Laboratory of Big Data Management and Analysis Methods（北京大数据管理与分析方法重点实验室）
Pay Attention and Move Better: Harnessing Attention for Interactive Motion Generation and Training-free Editing
Tsinghua University（清华大学）；The Chinese University of Hong Kong, Shenzhen（香港中文大学（深圳））；The University of Hong Kong（香港大学）；Shanghai AI Laboratory（上海人工智能实验室）
