In this paper, we present Vision Permutator, a conceptually simple and data efficient MLP-like architecture for visual recognition. By realizing the importance of the positional information carried by 2D feature representations, unlike recent MLP-like models that encode the spatial information along the flattened spatial dimensions, Vision Permutator separately encodes the feature representations along the height and width dimensions with linear projections. This allows Vision Permutator to capture long-range dependencies along one spatial direction and meanwhile preserve precise positional information along the other direction. The resulting position-sensitive outputs are then aggregated in a mutually complementing manner to form expressive representations of the objects of interest. We show that our Vision Permutators are formidable competitors to convolutional neural networks (CNNs) and vision transformers. Without the dependence on spatial convolutions or attention mechanisms, Vision Permutator achieves 81.5% top-1 accuracy on ImageNet without extra large-scale training data (e.g., ImageNet-22k) using only 25M learnable parameters, which is much better than most CNNs and vision transformers under the same model size constraint. When scaling up to 88M, it attains 83.2% top-1 accuracy. We hope this work could encourage research on rethinking the way of encoding spatial information and facilitate the development of MLP-like models. Code is available at //github.com/Andrew-Qibin/VisionPermutator.
相關內容
The recently developed vision transformer (ViT) has achieved promising results on image classification compared to convolutional neural networks. Inspired by this, in this paper, we study how to learn multi-scale feature representations in transformer models for image classification. To this end, we propose a dual-branch transformer to combine image patches (i.e., tokens in a transformer) of different sizes to produce stronger image features. Our approach processes small-patch and large-patch tokens with two separate branches of different computational complexity and these tokens are then fused purely by attention multiple times to complement each other. Furthermore, to reduce computation, we develop a simple yet effective token fusion module based on cross attention, which uses a single token for each branch as a query to exchange information with other branches. Our proposed cross-attention only requires linear time for both computational and memory complexity instead of quadratic time otherwise. Extensive experiments demonstrate that our approach performs better than or on par with several concurrent works on vision transformer, in addition to efficient CNN models. For example, on the ImageNet1K dataset, with some architectural changes, our approach outperforms the recent DeiT by a large margin of 2\% with a small to moderate increase in FLOPs and model parameters. Our source codes and models are available at \url{//github.com/IBM/CrossViT}.
Existing point-cloud based 3D object detectors use convolution-like operators to process information in a local neighbourhood with fixed-weight kernels and aggregate global context hierarchically. However, non-local neural networks and self-attention for 2D vision have shown that explicitly modeling long-range interactions can lead to more robust and competitive models. In this paper, we propose two variants of self-attention for contextual modeling in 3D object detection by augmenting convolutional features with self-attention features. We first incorporate the pairwise self-attention mechanism into the current state-of-the-art BEV, voxel and point-based detectors and show consistent improvement over strong baseline models of up to 1.5 3D AP while simultaneously reducing their parameter footprint and computational cost by 15-80% and 30-50%, respectively, on the KITTI validation set. We next propose a self-attention variant that samples a subset of the most representative features by learning deformations over randomly sampled locations. This not only allows us to scale explicit global contextual modeling to larger point-clouds, but also leads to more discriminative and informative feature descriptors. Our method can be flexibly applied to most state-of-the-art detectors with increased accuracy and parameter and compute efficiency. We show our proposed method improves 3D object detection performance on KITTI, nuScenes and Waymo Open datasets. Code is available at //github.com/AutoVision-cloud/SA-Det3D.
Convolutional Neural Networks (CNNs) are the go-to model for computer vision. Recently, attention-based networks, such as the Vision Transformer, have also become popular. In this paper we show that while convolutions and attention are both sufficient for good performance, neither of them are necessary. We present MLP-Mixer, an architecture based exclusively on multi-layer perceptrons (MLPs). MLP-Mixer contains two types of layers: one with MLPs applied independently to image patches (i.e. "mixing" the per-location features), and one with MLPs applied across patches (i.e. "mixing" spatial information). When trained on large datasets, or with modern regularization schemes, MLP-Mixer attains competitive scores on image classification benchmarks, with pre-training and inference cost comparable to state-of-the-art models. We hope that these results spark further research beyond the realms of well established CNNs and Transformers.
We propose RepMLP, a multi-layer-perceptron-style neural network building block for image recognition, which is composed of a series of fully-connected (FC) layers. Compared to convolutional layers, FC layers are more efficient, better at modeling the long-range dependencies and positional patterns, but worse at capturing the local structures, hence usually less favored for image recognition. We propose a structural re-parameterization technique that adds local prior into an FC to make it powerful for image recognition. Specifically, we construct convolutional layers inside a RepMLP during training and merge them into the FC for inference. On CIFAR, a simple pure-MLP model shows performance very close to CNN. By inserting RepMLP in traditional CNN, we improve ResNets by 1.8% accuracy on ImageNet, 2.9% for face recognition, and 2.3% mIoU on Cityscapes with lower FLOPs. Our intriguing findings highlight that combining the global representational capacity and positional perception of FC with the local prior of convolution can improve the performance of neural network with faster speed on both the tasks with translation invariance (e.g., semantic segmentation) and those with aligned images and positional patterns (e.g., face recognition). The code and models are available at //github.com/DingXiaoH/RepMLP.
Transformer is a type of deep neural network mainly based on self-attention mechanism which is originally applied in natural language processing field. Inspired by the strong representation ability of transformer, researchers propose to extend transformer for computer vision tasks. Transformer-based models show competitive and even better performance on various visual benchmarks compared to other network types such as convolutional networks and recurrent networks. In this paper we provide a literature review of these visual transformer models by categorizing them in different tasks and analyze the advantages and disadvantages of these methods. In particular, the main categories include the basic image classification, high-level vision, low-level vision and video processing. Self-attention in computer vision is also briefly revisited as self-attention is the base component in transformer. Efficient transformer methods are included for pushing transformer into real applications. Finally, we give a discussion about the further research directions for visual transformer.
In this work, we propose a generally applicable transformation unit for visual recognition with deep convolutional neural networks. This transformation explicitly models channel relationships with explainable control variables. These variables determine the neuron behaviors of competition or cooperation, and they are jointly optimized with the convolutional weight towards more accurate recognition. In Squeeze-and-Excitation (SE) Networks, the channel relationships are implicitly learned by fully connected layers, and the SE block is integrated at the block-level. We instead introduce a channel normalization layer to reduce the number of parameters and computational complexity. This lightweight layer incorporates a simple l2 normalization, enabling our transformation unit applicable to operator-level without much increase of additional parameters. Extensive experiments demonstrate the effectiveness of our unit with clear margins on many vision tasks, i.e., image classification on ImageNet, object detection and instance segmentation on COCO, video classification on Kinetics.
Transferring image-based object detectors to domain of videos remains a challenging problem. Previous efforts mostly exploit optical flow to propagate features across frames, aiming to achieve a good trade-off between performance and computational complexity. However, introducing an extra model to estimate optical flow would significantly increase the overall model size. The gap between optical flow and high-level features can hinder it from establishing the spatial correspondence accurately. Instead of relying on optical flow, this paper proposes a novel module called Progressive Sparse Local Attention (PSLA), which establishes the spatial correspondence between features across frames in a local region with progressive sparse strides and uses the correspondence to propagate features. Based on PSLA, Recursive Feature Updating (RFU) and Dense feature Transforming (DFT) are introduced to model temporal appearance and enrich feature representation respectively. Finally, a novel framework for video object detection is proposed. Experiments on ImageNet VID are conducted. Our framework achieves a state-of-the-art speed-accuracy trade-off with significantly reduced model capacity.
State-of-the-art deep convolutional networks (DCNs) such as squeeze-and- excitation (SE) residual networks implement a form of attention, also known as contextual guidance, which is derived from global image features. Here, we explore a complementary form of attention, known as visual saliency, which is derived from local image features. We extend the SE module with a novel global-and-local attention (GALA) module which combines both forms of attention -- resulting in state-of-the-art accuracy on ILSVRC. We further describe ClickMe.ai, a large-scale online experiment designed for human participants to identify diagnostic image regions to co-train a GALA network. Adding humans-in-the-loop is shown to significantly improve network accuracy, while also yielding visual features that are more interpretable and more similar to those used by human observers.
Videos are a rich source of high-dimensional structured data, with a wide range of interacting components at varying levels of granularity. In order to improve understanding of unconstrained internet videos, it is important to consider the role of labels at separate levels of abstraction. In this paper, we consider the use of the Bidirectional Inference Neural Network (BINN) for performing graph-based inference in label space for the task of video classification. We take advantage of the inherent hierarchy between labels at increasing granularity. The BINN is evaluated on the first and second release of the YouTube-8M large scale multilabel video dataset. Our results demonstrate the effectiveness of BINN, achieving significant improvements against baseline models.
In this paper, we propose the joint learning attention and recurrent neural network (RNN) models for multi-label classification. While approaches based on the use of either model exist (e.g., for the task of image captioning), training such existing network architectures typically require pre-defined label sequences. For multi-label classification, it would be desirable to have a robust inference process, so that the prediction error would not propagate and thus affect the performance. Our proposed model uniquely integrates attention and Long Short Term Memory (LSTM) models, which not only addresses the above problem but also allows one to identify visual objects of interests with varying sizes without the prior knowledge of particular label ordering. More importantly, label co-occurrence information can be jointly exploited by our LSTM model. Finally, by advancing the technique of beam search, prediction of multiple labels can be efficiently achieved by our proposed network model.
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191