Transformers have been recently adapted for large scale image classification, achieving high scores shaking up the long supremacy of convolutional neural networks. However the optimization of image transformers has been little studied so far. In this work, we build and optimize deeper transformer networks for image classification. In particular, we investigate the interplay of architecture and optimization of such dedicated transformers. We make two transformers architecture changes that significantly improve the accuracy of deep transformers. This leads us to produce models whose performance does not saturate early with more depth, for instance we obtain 86.5% top-1 accuracy on Imagenet when training with no external data, we thus attain the current SOTA with less FLOPs and parameters. Moreover, our best model establishes the new state of the art on Imagenet with Reassessed labels and Imagenet-V2 / match frequency, in the setting with no additional training data. We share our code and models.
University of Moratuwa（莫拉图瓦大学）；University of Sydney（悉尼大学）
Capsule Network is a promising concept in deep learning, yet its true potential is not fully realized thus far, providing sub-par performance on several key benchmark datasets with complex data. Drawing intuition from the success achieved by Convolutional Neural Networks (CNNs) by going deeper, we introduce DeepCaps1, a deep capsule network architecture which uses a novel 3D convolution based dynamic routing algorithm. With DeepCaps, we surpass the state-of-the-art results in the capsule network domain on CIFAR10, SVHN and Fashion MNIST, while achieving a 68% reduction in the number of paramet…
Over the past few years, Spiking Neural Networks (SNNs) have become popular as a possible pathway to enable low-power event-driven neuromorphic hardware. However, their application in machine learning have largely been limited to very shallow neural network architectures for simple problems. In this paper, we propose a novel algorithmic technique for generating an SNN with a deep architecture, and demonstrate its effectiveness on complex visual recognition problems such as CIFAR-10 and ImageNet. Our technique applies to both VGG and Residual network architectures, with significantly better acc…
Google Inc.（谷歌公司）；University of North Carolina, Chapel Hill（北卡罗来纳大学教堂山分校）；University of Michigan（密歇根大学）
We propose a deep convolutional neural network architecture codenamed "Inception", which was responsible for setting the new state of the art for classification and detection in the ImageNet Large-Scale Visual Recognition Challenge 2014 (ILSVRC 2014). The main hallmark of this architecture is the improved utilization of the computing resources inside the network. This was achieved by a carefully crafted design that allows for increasing the depth and width of the network while keeping the computational budget constant. To optimize quality, the architectural decisions were based on the Hebbian …
KTH Royal Institute of Technology（瑞典皇家理工学院）；University of Haifa（海法大学）；University of São Paulo（圣保罗大学）；Swedish University of Agricultural Sciences（瑞典农业科学大学）；Universiteit Utrecht（乌得勒支大学）；University of Glasgow（格拉斯哥大学）；Silo AI；Boğaziçi University（博阿齐奇大学）
Advances in animal motion tracking and pose recognition have been a game changer in the study of animal behavior. Recently, an increasing number of works go 'deeper' than tracking, and address automated recognition of animals' internal states such as emotions and pain with the aim of improving animal welfare, making this a timely moment for a systematization of the field. This paper provides a comprehensive survey of computer vision-based research on recognition of affective states and pain in animals, addressing both facial and bodily behavior analysis. We summarize the efforts that have been…
A deeper understanding of video activities extends beyond recognition of underlying concepts such as actions and objects: constructing deep semantic representations requires reasoning about the semantic relationships among these concepts, often beyond what is directly observed in the data. To this end, we propose an energy minimization framework that leverages large-scale commonsense knowledge bases, such as ConceptNet, to provide contextual cues to establish semantic relationships among entities directly hypothesized from video signal. We mathematically express this using the language of Gren…
Peking University（北京大学）；Sinovation Ventures（创新工场）；School of Data Science, Fudan University（复旦大学数据科学学院）；University of Chinese Academy of Sciences（中国科学院大学）
Significant progress has been achieved in Computer Vision by leveraging large-scale image datasets. However, large-scale datasets for complex Computer Vision tasks beyond classification are still limited. This paper proposed a large-scale dataset named AIC (AI Challenger) with three sub-datasets, human keypoint detection (HKD), large-scale attribute dataset (LAD) and image Chinese captioning (ICC). In this dataset, we annotate class labels (LAD), keypoint coordinate (HKD), bounding box (HKD and LAD), attribute (LAD) and caption (ICC). These rich annotations bridge the semantic gap between low-…
Australian National University（澳大利亚国立大学）；Data61, CSIRO（澳大利亚联邦科学与工业研究组织Data61）
Understanding human actions in visual data is tied to advances in complementary research areas including object recognition, human dynamics, domain adaptation and semantic segmentation. Over the last decade, human action analysis evolved from earlier schemes that are often limited to controlled environments to nowadays advanced solutions that can learn from millions of videos and apply to almost all daily activities. Given the broad range of applications from video surveillance to human-computer interaction, scientific milestones in action recognition are achieved more rapidly, eventually lead…
University College London（伦敦大学学院）；Ariel AI（艾瑞尔人工智能公司）；Adobe Research（奥多比研究院）
In this work we introduce Lean Point Networks (LPNs) to train deeper and more accurate point processing networks by relying on three novel point processing blocks that improve memory consumption, inference time, and accuracy: a convolution-type block for point sets that blends neighborhood information in a memory-efficient manner; a crosslink block that efficiently shares information across low- and high-resolution processing branches; and a multiresolution point cloud processing block for faster diffusion of information. By combining these blocks, we design wider and deeper point-based archit…
In this paper, we design a simple yet powerful deep network architecture, U$^2$-Net, for salient object detection (SOD). The architecture of our U$^2$-Net is a two-level nested U-structure. The design has the following advantages: (1) it is able to capture more contextual information from different scales thanks to the mixture of receptive fields of different sizes in our proposed ReSidual U-blocks (RSU), (2) it increases the depth of the whole architecture without significantly increasing the computational cost because of the pooling operations used in these RSU blocks. This architecture enab…
Snap Inc.（Snap 公司）；University of Hong Kong（香港大学）；Adobe Research（Adobe 研究院）；University of Notre Dame（圣母大学）
Face detection is a crucial first step in many facial recognition and face analysis systems. Early approaches for face detection were mainly based on classifiers built on top of hand-crafted features extracted from local image regions, such as Haar Cascades and Histogram of Oriented Gradients. However, these approaches were not powerful enough to achieve a high accuracy on images of from uncontrolled environments. With the breakthrough work in image classification using deep neural networks in 2012, there has been a huge paradigm shift in face detection. Inspired by the rapid progress of deep …
We bring together ideas from recent work on feature design for egocentric action recognition under one framework by exploring the use of deep convolutional neural networks (CNN). Recent work has shown that features such as hand appearance, object attributes, local hand motion and camera ego-motion are important for characterizing first-person actions. To integrate these ideas under one framework, we propose a twin stream network architecture, where one stream analyzes appearance information and the other stream analyzes motion information. Our appearance stream encodes prior knowledge of the e…
Queensland University of Technology（昆士兰科技大学）；The University of Queensland（昆士兰大学）
Person re-identification is the challenging task of identifying a person across different camera views. Training a convolutional neural network (CNN) for this task requires annotating a large dataset, and hence, it involves the time-consuming manual matching of people across cameras. To reduce the need for labeled data, we focus on a semi-supervised approach that requires only a subset of the training data to be labeled. We conduct a comprehensive survey in the area of person re-identification with limited labels. Existing works in this realm are limited in the sense that they utilize features…
National University of Singapore（新加坡国立大学）；ByteDance US AI Lab（字节跳动美国人工智能实验室）
Vision transformers (ViTs) have been successfully applied in image classification tasks recently. In this paper, we show that, unlike convolution neural networks (CNNs)that can be improved by stacking more convolutional layers, the performance of ViTs saturate fast when scaled to be deeper. More specifically, we empirically observe that such scaling difficulty is caused by the attention collapse issue: as the transformer goes deeper, the attention maps gradually become similar and even much the same after certain layers. In other words, the feature maps tend to be identical in the top layers o…
Booz Allen Hamilton Inc.（博思艾伦咨询公司）；Army Research Laboratory（陆军研究实验室）
In this paper, we describe a novel deep convolutional neural network (CNN) that is deeper and wider than other existing deep networks for hyperspectral image classification. Unlike current state-of-the-art approaches in CNN-based hyperspectral image classification, the proposed network, called contextual deep CNN, can optimally explore local contextual interactions by jointly exploiting local spatio-spectral relationships of neighboring individual pixel vectors. The joint exploitation of the spatio-spectral information is achieved by a multi-scale convolutional filter bank used as an initial c…
Going Deeper into Recognizing Actions in Dark Environments: A Comprehensive Benchmark Study
Institute for Infocomm Research, A*STAR（新加坡科技研究局资讯通信研究院）；School of Electrical and Electronic Engineering, Nanyang Technological University（南洋理工大学电气与电子工程学院）；NVIDIA AI Tech Centre（英伟达人工智能技术中心）；Department of Electric Power and Energy Systems, KTH Royal Institute of Technology（瑞典皇家理工学院电力与能源系统系）
CSIRO Health and Biosecurity（联邦科学与工业研究组织健康与生物安全部门）；The Australian eHealth Research Centre（澳大利亚电子健康研究中心）；CSIRO Data61（联邦科学与工业研究组织数据61所）
Brain morphometry from magnetic resonance imaging (MRI) is a consolidated biomarker for many neurodegenerative diseases. Recent advances in this domain indicate that deep convolutional neural networks can infer morphometric measurements within a few seconds. Nevertheless, the accuracy of the devised model for insightful bio-markers (mean curvature and thickness) remains unsatisfactory. In this paper, we propose a more accurate and efficient neural network model for brain morphometry named HerstonNet. More specifically, we develop a 3D ResNet-based neural network to learn rich features directly…
Automated Facial Expression Recognition (FER) has remained a challenging and interesting problem. Despite efforts made in developing various methods for FER, existing approaches traditionally lack generalizability when applied to unseen images or those that are captured in wild setting. Most of the existing approaches are based on engineered features (e.g. HOG, LBPH, and Gabor) where the classifier's hyperparameters are tuned to give best recognition accuracies across a single database, or a small collection of similar databases. Nevertheless, the results are not significant when they are appl…
This technical report details several improvements to the visual concept detector banks built on images from the Multilingual Visual Sentiment Ontology (MVSO). The detector banks are trained to detect a total of 9,918 sentiment-biased visual concepts from six major languages: English, Spanish, Italian, French, German and Chinese. In the original MVSO release, adjective-noun pair (ANP) detectors were trained for the six languages using an AlexNet-styled architecture by fine-tuning from DeepSentiBank. Here, through a more extensive set of experiments, parameter tuning, and training runs, we deta…
National University of Singapore（新加坡国立大学）；University of Cambridge（剑桥大学）
Indirect image registration is a promising technique to improve image reconstruction quality by providing a shape prior for the reconstruction task. In this paper, we propose a novel hybrid method that seeks to reconstruct high quality images from few measurements whilst requiring low computational cost. With this purpose, our framework intertwines indirect registration and reconstruction tasks is a single functional. It is based on two major novelties. Firstly, we introduce a model based on deep nets to solve the indirect registration problem, in which the inversion and registration mappings …
Nanjing University（南京大学）；Shanghai AI Laboratory（上海人工智能实验室）；The University of Hong Kong（香港大学）；NVIDIA（英伟达）；Caltech（加州理工学院）
Panoptic segmentation involves a combination of joint semantic segmentation and instance segmentation, where image contents are divided into two types: things and stuff. We present Panoptic SegFormer, a general framework for panoptic segmentation with transformers. It contains three innovative components: an efficient deeply-supervised mask decoder, a query decoupling strategy, and an improved post-processing method. We also use Deformable DETR to efficiently process multi-scale features, which is a fast and efficient version of DETR. Specifically, we supervise the attention modules in the mas…
Going Beyond U-Net: Assessing Vision Transformers for Semantic Segmentation in Microscopy Image Analysis
Institute of Computer Science, University of Tartu（塔尔图大学计算机科学研究所）；Center for Artificial Intelligence, Technical University of Applied Sciences Würzburg-Schweinfurt（维尔茨堡-施韦因富特应用技术大学人工智能中心）；STACC
Universitat Politècnica de València（瓦伦西亚理工大学）；University Clinical Hospital of Valencia（瓦伦西亚大学临床医院）；University of Granada（格拉纳达大学）
The Gleason scoring system is the primary diagnostic and prognostic tool for prostate cancer. In recent years, with the development of digitisation devices, the use of computer vision techniques for the analysis of biopsies has increased. However, to the best of the authors' knowledge, the development of algorithms to automatically detect individual cribriform patterns belonging to Gleason grade 4 has not yet been studied in the literature. The objective of the work presented in this paper is to develop a deep-learning-based system able to support pathologists in the daily analysis of prostate…
Dalian University of Technology（大连理工大学）；Tianjin University（天津大学）；MEGVII Technology（旷视科技）
Transformer models are not only successful in natural language processing (NLP) but also demonstrate high potential in computer vision (CV). Despite great advance, most of works only focus on improvement of architectures but pay little attention to the classification head. For years transformer models base exclusively on classification token to construct the final classifier, without explicitly harnessing high-level word tokens. In this paper, we propose a novel transformer model called second-order transformer (SoT), exploiting simultaneously the classification token and word tokens for the c…
Vision Transformer (ViT) demonstrates that Transformer for natural language processing can be applied to computer vision tasks and result in comparable performance to convolutional neural networks (CNN), which have been studied and adopted in computer vision for years. This naturally raises the question of how the performance of ViT can be advanced with design techniques of CNN. To this end, we propose to incorporate two techniques and present ViT-ResNAS, an efficient multi-stage ViT architecture designed with neural architecture search (NAS). First, we propose residual spatial reduction to de…
Graph Convolutional Networks (GCNs) have been drawing significant attention with the power of representation learning on graphs. Unlike Convolutional Neural Networks (CNNs), which are able to take advantage of stacking very deep layers, GCNs suffer from vanishing gradient, over-smoothing and over-fitting issues when going deeper. These challenges limit the representation power of GCNs on large-scale graphs. This paper proposes DeeperGCN that is capable of successfully and reliably training very deep GCNs. We define differentiable generalized aggregation functions to unify different message agg…
More transformer blocks with residual connections have recently achieved impressive results on various tasks. To achieve better performance with fewer trainable parameters, recent methods are proposed to go shallower by parameter sharing or model compressing along with the depth. However, weak modeling capacity limits their performance. Contrastively, going wider by inducing more trainable matrixes and parameters would produce a huge model requiring advanced parallelism to train and inference. In this paper, we propose a parameter-efficient framework, going wider instead of deeper. Specially, …
The design of more complex and powerful neural network models has significantly advanced the state-of-the-art in visual object tracking. These advances can be attributed to deeper networks, or the introduction of new building blocks, such as transformers. However, in the pursuit of increased tracking performance, runtime is often hindered. Furthermore, efficient tracking architectures have received surprisingly little attention. In this paper, we introduce the Exemplar Transformer, a transformer module utilizing a single instance level attention layer for realtime visual object tracking. E.T.T…
Institute of Information Science and Technologies (ISTI), Italian National Research Council (CNR)（意大利国家研究理事会信息科学与技术研究所）
Although convolutional neural networks (CNNs) showed remarkable results in many vision tasks, they are still strained by simple yet challenging visual reasoning problems. Inspired by the recent success of the Transformer network in computer vision, in this paper, we introduce the Recurrent Vision Transformer (RViT) model. Thanks to the impact of recurrent connections and spatial attention in reasoning tasks, this network achieves competitive results on the same-different visual reasoning problems from the SVRT dataset. The weight-sharing both in spatial and depth dimensions regularizes the mod…
Fudan University（复旦大学）；Microsoft Research Asia（微软亚洲研究院）
With Vision Transformers (ViTs) making great advances in a variety of computer vision tasks, recent literature have proposed various variants of vanilla ViTs to achieve better efficiency and efficacy. However, it remains unclear how their unique architecture impact robustness towards common corruptions. In this paper, we make the first attempt to probe into the robustness gap among ViT variants and explore underlying designs that are essential for robustness. Through an extensive and rigorous benchmarking, we demonstrate that simple architecture designs such as overlapping patch embedding and …
Towards Deeper Emotional Reflection: Crafting Affective Image Filters with Generative Priors
School of Artificial Intelligence, Beijing University of Posts and Telecommunications（北京邮电大学人工智能学院）；Beijing Academy of Artificial Intelligence（北京人工智能研究院）；State Key Laboratory of Multimedia Information Processing and National Engineering Research Center of Visual Technology, School of Computer Science, Peking University（北京大学多媒体信息处理国家重点实验室和视觉技术国家工程研究中心）
ICMC – Universidade de São Paulo (USP)（圣保罗大学ICMC学院）
Training deep neural networks may be challenging in real world data. Using models as black-boxes, even with transfer learning, can result in poor generalization or inconclusive results when it comes to small datasets or specific applications. This tutorial covers the basic steps as well as more recent options to improve models, in particular, but not restricted to, supervised learning. It can be particularly useful in datasets that are not as well-prepared as those in challenges, and also under scarce annotation and/or small data. We describe basic procedures: as data preparation, optimization…
The majority of current research in deep learning based image registration addresses inter-patient brain registration with moderate deformation magnitudes. The recent Learn2Reg medical registration benchmark has demonstrated that single-scale U-Net architectures, such as VoxelMorph that directly employ a spatial transformer loss, often do not generalise well beyond the cranial vault and fall short of state-of-the-art performance for abdominal or intra-patient lung registration. Here, we propose two straightforward steps that greatly reduce this gap in accuracy. First, we employ keypoint self-s…
Deep neural networks are widely used for understanding 3D point clouds. At each point convolution layer, features are computed from local neighborhoods of 3D points and combined for subsequent processing in order to extract semantic information. Existing methods adopt the same individual point neighborhoods throughout the network layers, defined by the same metric on the fixed input point coordinates. This common practice is easy to implement but not necessarily optimal. Ideally, local neighborhoods should be different at different layers, as more latent information is extracted at deeper laye…
SpectralKD: A Unified Framework for Interpreting and Distilling Vision Transformers via Spectral Analysis
College of Computer Science and Technology, Zhejiang University（浙江大学计算机科学与技术学院）；School of Aeronautics and Astronautics, Zhejiang University（浙江大学航空航天学院）
We present Reversible Vision Transformers, a memory efficient architecture design for visual recognition. By decoupling the GPU memory requirement from the depth of the model, Reversible Vision Transformers enable scaling up architectures with efficient memory usage. We adapt two popular models, namely Vision Transformer and Multiscale Vision Transformers, to reversible variants and benchmark extensively across both model sizes and tasks of image classification, object detection and video classification. Reversible Vision Transformers achieve a reduced memory footprint of up to 15.5x at roughl…
Facebook AI Research（Facebook AI研究院）；UC Berkeley（加州大学伯克利分校）
We present Multiscale Vision Transformers (MViT) for video and image recognition, by connecting the seminal idea of multiscale feature hierarchies with transformer models. Multiscale Transformers have several channel-resolution scale stages. Starting from the input resolution and a small channel dimension, the stages hierarchically expand the channel capacity while reducing the spatial resolution. This creates a multiscale pyramid of features with early layers operating at high spatial resolution to model simple low-level visual information, and deeper layers at spatially coarse, but complex, …
Dealicious Inc.（Dealicious公司）；Institute of Advanced Research on Artificial Intelligence (IARAI)（人工智能高等研究院）；Athena RC（雅典娜研究中心）
Vision transformers have achieved remarkable progress in vision tasks such as image classification and detection. However, in instance-level image retrieval, transformers have not yet shown good performance compared to convolutional networks. We propose a number of improvements that make transformers outperform the state of the art for the first time. (1) We show that a hybrid architecture is more effective than plain transformers, by a large margin. (2) We introduce two branches collecting global (classification token) and local (patch tokens) information, from which we form a global image re…
Object trackers deployed on low-power devices need to be light-weight, however, most of the current state-of-the-art (SOTA) methods rely on using compute-heavy backbones built using CNNs or transformers. Large sizes of such models do not allow their deployment in low-power conditions and designing compressed variants of large tracking models is of great importance. This paper demonstrates how highly compressed light-weight object trackers can be designed using neural architectural pruning of large CNN and transformer based trackers. Further, a comparative study on architectural choices best su…
