scispace - formally typeset
Open accessPosted Content

Perceiver: General Perception with Iterative Attention

Abstract: Biological systems perceive the world by simultaneously processing high-dimensional inputs from modalities as diverse as vision, audition, touch, proprioception, etc. The perception models used in deep learning on the other hand are designed for individual modalities, often relying on domain-specific assumptions such as the local grid structures exploited by virtually all existing vision models. These priors introduce helpful inductive biases, but also lock models to individual modalities. In this paper we introduce the Perceiver - a model that builds upon Transformers and hence makes few architectural assumptions about the relationship between its inputs, but that also scales to hundreds of thousands of inputs, like ConvNets. The model leverages an asymmetric attention mechanism to iteratively distill inputs into a tight latent bottleneck, allowing it to scale to handle very large inputs. We show that this architecture is competitive with or outperforms strong, specialized models on classification tasks across various modalities: images, point clouds, audio, video, and video+audio. The Perceiver obtains performance comparable to ResNet-50 and ViT on ImageNet without 2D convolutions by directly attending to 50,000 pixels. It is also competitive in all modalities in AudioSet.

... read more

Citations
  More

45 results found


Open accessPosted Content
Abstract: Astounding results from Transformer models on natural language tasks have intrigued the vision community to study their application to computer vision problems. Among their salient benefits, Transformers enable modeling long dependencies between input sequence elements and support parallel processing of sequence as compared to recurrent networks e.g., Long short-term memory (LSTM). Different from convolutional networks, Transformers require minimal inductive biases for their design and are naturally suited as set-functions. Furthermore, the straightforward design of Transformers allows processing multiple modalities (e.g., images, videos, text and speech) using similar processing blocks and demonstrates excellent scalability to very large capacity networks and huge datasets. These strengths have led to exciting progress on a number of vision tasks using Transformer networks. This survey aims to provide a comprehensive overview of the Transformer models in the computer vision discipline. We start with an introduction to fundamental concepts behind the success of Transformers i.e., self-attention, large-scale pre-training, and bidirectional encoding. We then cover extensive applications of transformers in vision including popular recognition tasks (e.g., image classification, object detection, action recognition, and segmentation), generative modeling, multi-modal tasks (e.g., visual-question answering, visual reasoning, and visual grounding), video processing (e.g., activity recognition, video forecasting), low-level vision (e.g., image super-resolution, image enhancement, and colorization) and 3D analysis (e.g., point cloud classification and segmentation). We compare the respective advantages and limitations of popular techniques both in terms of architectural design and their experimental value. Finally, we provide an analysis on open research directions and possible future works.

... read more

125 Citations


Open accessPosted Content
Abstract: Following their success in natural language processing, transformers have recently shown much promise for computer vision. The self-attention operation underlying transformers yields global interactions between all tokens ,i.e. words or image patches, and enables flexible modelling of image data beyond the local interactions of convolutions. This flexibility, however, comes with a quadratic complexity in time and memory, hindering application to long sequences and high-resolution images. We propose a "transposed" version of self-attention that operates across feature channels rather than tokens, where the interactions are based on the cross-covariance matrix between keys and queries. The resulting cross-covariance attention (XCA) has linear complexity in the number of tokens, and allows efficient processing of high-resolution images. Our cross-covariance image transformer (XCiT) is built upon XCA. It combines the accuracy of conventional transformers with the scalability of convolutional architectures. We validate the effectiveness and generality of XCiT by reporting excellent results on multiple vision benchmarks, including image classification and self-supervised feature learning on ImageNet-1k, object detection and instance segmentation on COCO, and semantic segmentation on ADE20k.

... read more

Topics: Feature (computer vision) (57%), Object detection (57%), Contextual image classification (55%) ... read more

20 Citations


Open accessPosted Content
Chen Zhu1, Wei Ping2, Chaowei Xiao2, Mohammad Shoeybi2  +3 moreInstitutions (3)
Abstract: Transformers have achieved success in both language and vision domains. However, it is prohibitively expensive to scale them to long sequences such as long documents or high-resolution images, because self-attention mechanism has quadratic time and memory complexities with respect to the input sequence length. In this paper, we propose Long-Short Transformer (Transformer-LS), an efficient self-attention mechanism for modeling long sequences with linear complexity for both language and vision tasks. It aggregates a novel long-range attention with dynamic projection to model distant correlations and a short-term attention to capture fine-grained local correlations. We propose a dual normalization strategy to account for the scale mismatch between the two attention mechanisms. Transformer-LS can be applied to both autoregressive and bidirectional models without additional complexity. Our method outperforms the state-of-the-art models on multiple tasks in language and vision domains, including the Long Range Arena benchmark, autoregressive language modeling, and ImageNet classification. For instance, Transformer-LS achieves 0.97 test BPC on enwik8 using half the number of parameters than previous method, while being faster and is able to handle 3x as long sequences compared to its full-attention version on the same hardware. On ImageNet, it can obtain the state-of-the-art results (e.g., a moderate size of 55.8M model solely trained on 224x224 ImageNet-1K can obtain Top-1 accuracy 84.1%), while being more scalable on high-resolution images. The source code and models are released at this https URL .

... read more

Topics: Language model (54%), Transformer (machine learning model) (53%), Source code (52%) ... read more

6 Citations


Open accessPosted ContentDOI: 10.1101/2021.05.29.446297
30 May 2021-bioRxiv
Abstract: Inferotemporal cortex (IT) in humans and other primates is topographically organized, with multiple domain-selective areas and other general patterns of functional organization. What factors underlie this organization, and what can this neural arrangement tell us about the mechanisms of high level vision? Here, we present an account of topographic organization involving a computational model with two components: 1) a feature-extracting encoder model of early visual processes, followed by 2) a model of high-level hierarchical visual processing in IT subject to specific biological constraints. In particular, minimizing the wiring cost on spatially organized feedforward and lateral connections within IT, combined with constraining the feedforward processing to be strictly excitatory, results in a hierarchical, topographic organization. This organization replicates a number of key properties of primate IT cortex, including the presence of domain-selective spatial clusters preferentially involved in the representation of faces, objects, and scenes, within-domain topographic organization such as animacy and indoor/outdoor distinctions, and generic spatial organization whereby the response correlation of pairs of units falls off with their distance. The model supports a view in which both domain-specific and domain-general topographic organization arise in the visual system from an optimization process that maximizes behavioral performance while minimizing wiring costs.

... read more

Topics: Spatial organization (53%), Visual processing (53%), Visual cortex (52%)

3 Citations


Open accessPosted Content
Abstract: We gratefully acknowledge the following colleagues for valuable discussions and support of our project: Aaron Adcock, Andrew Allen, Behrouz Behmardi, Serge Belongie, Mark Broyles, Xiao Chu, Samuel Clapp, Irene D’Ambra, Peter Dodds, Jacob Donley, Ruohan Gao, Tal Hassner, EthanHenderson, Jiabo Hu, Guillaume Jeanneret, Sanjana Krishnan, Tsung-Yi Lin, Bobby Otillar, Manohar Paluri, Maja Pantic, Lucas Pinto, Vivek Roy, Jerome Pesenti, Joelle Pineau, Luca Sbordone, Rajan Subramanian, Helen Sun, Mary Williamson, and Bill Wu. We also acknowledge Jacob Chalk for setting up the Ego4D AWS backend and Prasanna Sridhar for developing the Ego4D website. Thank you to the Common Visual Data Foundation (CVDF) for hosting the Ego4D dataset. The universities acknowledge the usage of commercial software for de-identification of video. brighter.ai was used for redacting videos by some of the universities. Personal data from the University of Bristol was protected by Primloc’s Secure Redact software suite. UNICT is supported by MIUR AIM - Attrazione eMobilitaInternazionale Linea 1 - AIM1893589 - CUP E64118002540007. Bristol is supported by UKRIEngineering and Physical Sciences Research Council (EPSRC) Doctoral Training Program (DTP), EPSRC Fellowship UMPIRE (EP/T004991/1). KAUST is supported by the KAUST Office of Sponsored Research through the Visual Computing Center (VCC) funding. National University of Singapore is supported by Mike Shou’s Start-Up Grant. Georgia Tech is supported in part by NSF award 2033413 and NIH award R01MH114999.

... read more

3 Citations


References
  More

91 results found


Open accessProceedings ArticleDOI: 10.1109/CVPR.2016.90
Kaiming He1, Xiangyu Zhang1, Shaoqing Ren1, Jian Sun1Institutions (1)
27 Jun 2016-
Abstract: Deeper neural networks are more difficult to train. We present a residual learning framework to ease the training of networks that are substantially deeper than those used previously. We explicitly reformulate the layers as learning residual functions with reference to the layer inputs, instead of learning unreferenced functions. We provide comprehensive empirical evidence showing that these residual networks are easier to optimize, and can gain accuracy from considerably increased depth. On the ImageNet dataset we evaluate residual nets with a depth of up to 152 layers—8× deeper than VGG nets [40] but still having lower complexity. An ensemble of these residual nets achieves 3.57% error on the ImageNet test set. This result won the 1st place on the ILSVRC 2015 classification task. We also present analysis on CIFAR-10 with 100 and 1000 layers. The depth of representations is of central importance for many visual recognition tasks. Solely due to our extremely deep representations, we obtain a 28% relative improvement on the COCO object detection dataset. Deep residual nets are foundations of our submissions to ILSVRC & COCO 2015 competitions1, where we also won the 1st places on the tasks of ImageNet detection, ImageNet localization, COCO detection, and COCO segmentation.

... read more

Topics: Deep learning (53%), Residual (53%), Convolutional neural network (53%) ... read more

93,356 Citations


Open accessProceedings Article
03 Dec 2012-
Abstract: We trained a large, deep convolutional neural network to classify the 1.2 million high-resolution images in the ImageNet LSVRC-2010 contest into the 1000 different classes. On the test data, we achieved top-1 and top-5 error rates of 37.5% and 17.0% which is considerably better than the previous state-of-the-art. The neural network, which has 60 million parameters and 650,000 neurons, consists of five convolutional layers, some of which are followed by max-pooling layers, and three fully-connected layers with a final 1000-way softmax. To make training faster, we used non-saturating neurons and a very efficient GPU implementation of the convolution operation. To reduce overriding in the fully-connected layers we employed a recently-developed regularization method called "dropout" that proved to be very effective. We also entered a variant of this model in the ILSVRC-2012 competition and achieved a winning top-5 test error rate of 15.3%, compared to 26.2% achieved by the second-best entry.

... read more

Topics: Convolutional neural network (61%), Deep learning (59%), Dropout (neural networks) (54%) ... read more

73,871 Citations


Open accessProceedings Article
Karen Simonyan1, Andrew Zisserman1Institutions (1)
01 Jan 2015-
Abstract: In this work we investigate the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting. Our main contribution is a thorough evaluation of networks of increasing depth using an architecture with very small (3x3) convolution filters, which shows that a significant improvement on the prior-art configurations can be achieved by pushing the depth to 16-19 weight layers. These findings were the basis of our ImageNet Challenge 2014 submission, where our team secured the first and the second places in the localisation and classification tracks respectively. We also show that our representations generalise well to other datasets, where they achieve state-of-the-art results. We have made our two best-performing ConvNet models publicly available to facilitate further research on the use of deep visual representations in computer vision.

... read more

49,857 Citations


Journal ArticleDOI: 10.1162/NECO.1997.9.8.1735
Sepp Hochreiter1, Jürgen Schmidhuber2Institutions (2)
01 Nov 1997-Neural Computation
Abstract: Learning to store information over extended time intervals by recurrent backpropagation takes a very long time, mostly because of insufficient, decaying error backflow. We briefly review Hochreiter's (1991) analysis of this problem, then address it by introducing a novel, efficient, gradient based method called long short-term memory (LSTM). Truncating the gradient where this does not do harm, LSTM can learn to bridge minimal time lags in excess of 1000 discrete-time steps by enforcing constant error flow through constant error carousels within special units. Multiplicative gate units learn to open and close access to the constant error flow. LSTM is local in space and time; its computational complexity per time step and weight is O. 1. Our experiments with artificial data involve local, distributed, real-valued, and noisy pattern representations. In comparisons with real-time recurrent learning, back propagation through time, recurrent cascade correlation, Elman nets, and neural sequence chunking, LSTM leads to many more successful runs, and learns much faster. LSTM also solves complex, artificial long-time-lag tasks that have never been solved by previous recurrent network algorithms.

... read more

49,735 Citations


Journal ArticleDOI: 10.1109/5.726791
Yann LeCun1, Léon Bottou2, Léon Bottou3, Yoshua Bengio3  +3 moreInstitutions (5)
01 Jan 1998-
Abstract: Multilayer neural networks trained with the back-propagation algorithm constitute the best example of a successful gradient based learning technique. Given an appropriate network architecture, gradient-based learning algorithms can be used to synthesize a complex decision surface that can classify high-dimensional patterns, such as handwritten characters, with minimal preprocessing. This paper reviews various methods applied to handwritten character recognition and compares them on a standard handwritten digit recognition task. Convolutional neural networks, which are specifically designed to deal with the variability of 2D shapes, are shown to outperform all other techniques. Real-life document recognition systems are composed of multiple modules including field extraction, segmentation recognition, and language modeling. A new learning paradigm, called graph transformer networks (GTN), allows such multimodule systems to be trained globally using gradient-based methods so as to minimize an overall performance measure. Two systems for online handwriting recognition are described. Experiments demonstrate the advantage of global training, and the flexibility of graph transformer networks. A graph transformer network for reading a bank cheque is also described. It uses convolutional neural network character recognizers combined with global training techniques to provide record accuracy on business and personal cheques. It is deployed commercially and reads several million cheques per day.

... read more

Topics: Neocognitron (64%), Intelligent character recognition (64%), Artificial neural network (60%) ... read more

34,930 Citations


Performance
Metrics
No. of citations received by the Paper in previous years
YearCitations
202144
20201
Network Information
Related Papers (5)
Attention is All you Need12 Jun 2017

Ashish Vaswani, Noam Shazeer +6 more

Deep Residual Learning for Image Recognition27 Jun 2016

Kaiming He, Xiangyu Zhang +2 more

An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale03 May 2021

Alexey Dosovitskiy, Lucas Beyer +10 more

ImageNet: A large-scale hierarchical image database20 Jun 2009

Jia Deng, Wei Dong +4 more