Container: Context Aggregation Network

Abstract

Convolutional neural networks (CNNs) are ubiquitous in computer vision, with a myriad of effective and efficient variations. Recently, Transformers -- originally introduced in natural language processing -- have been increasingly adopted in computer vision. While early adopters continue to employ CNN backbones, the latest networks are end-to-end CNN-free Transformer solutions. A recent surprising finding shows that a simple MLP based solution without any traditional convolutional or Transformer components can produce effective visual representations. While CNNs, Transformers and MLP-Mixers may be considered as completely disparate architectures, we provide a unified view showing that they are in fact special cases of a more general method to aggregate spatial context in a neural network stack. We present the \model (CONText AggregatIon NEtwoRk), a general-purpose building block for multi-head context aggregation that can exploit long-range interactions \emph{a la} Transformers while still exploiting the inductive bias of the local convolution operation leading to faster convergence speeds, often seen in CNNs. In contrast to Transformer-based methods that do not scale well to downstream tasks that rely on larger input image resolutions, our efficient network, named \modellight, can be employed in object detection and instance segmentation networks such as DETR, RetinaNet and Mask-RCNN to obtain an impressive detection mAP of 38.9, 43.8, 45.1 and mask mAP of 41.3, providing large improvements of 6.6, 7.3, 6.9 and 6.6 pts respectively, compared to a ResNet-50 backbone with a comparable compute and parameter size. Our method also achieves promising results on self-supervised learning compared to DeiT on the DINO framework. Code is released at \url{https://github.com/allenai/container}.

NeuIPS 2021

References in corpus (10)

• Learning Transferable Visual Models From Natural Language Supervision
• MLP-Mixer: An all-MLP Architecture for Vision
• Linformer: Self-Attention with Linear Complexity
• Reformer: The Efficient Transformer
• Pay Less Attention with Lightweight and Dynamic Convolutions
• Transformers are RNNs: Fast Autoregressive Transformers with Linear Attention
• Depthwise Separable Convolutions for Neural Machine Translation
• MUSE: Parallel Multi-Scale Attention for Sequence to Sequence Learning
• ProTo: Program-Guided Transformer for Program-Guided Tasks
• Character Matters: Video Story Understanding with Character-Aware Relations

Cited by in corpus (4)

• S${}^2$-MLP: Spatial-Shift MLP Architecture for Vision
• MVT: Multi-view Vision Transformer for 3D Object Recognition
• Fast Convergence of DETR with Spatially Modulated Co-Attention
• Rethinking Token-Mixing MLP for MLP-based Vision Backbone