EfficientFormer: Vision Transformers at MobileNet Speed

Abstract

Vision Transformers (ViT) have shown rapid progress in computer vision tasks, achieving promising results on various benchmarks. However, due to the massive number of parameters and model design, e.g., attention mechanism, ViT-based models are generally times slower than lightweight convolutional networks. Therefore, the deployment of ViT for real-time applications is particularly challenging, especially on resource-constrained hardware such as mobile devices. Recent efforts try to reduce the computation complexity of ViT through network architecture search or hybrid design with MobileNet block, yet the inference speed is still unsatisfactory. This leads to an important question: can transformers run as fast as MobileNet while obtaining high performance? To answer this, we first revisit the network architecture and operators used in ViT-based models and identify inefficient designs. Then we introduce a dimension-consistent pure transformer (without MobileNet blocks) as a design paradigm. Finally, we perform latencydriven slimming to get a series of final models dubbed EfficientFormer. Extensive experiments show the superiority of EfficientFormer in performance and speed on mobile devices. Our fastest model, EfficientFormer-L1, achieves 79.2% top-1 accuracy on ImageNet-1K with only 1.6 ms inference latency on iPhone 12 (compiled with CoreML), which runs as fast as MobileNetV2×1.4 (1.6 ms, 74.7% top-1), and our largest model, EfficientFormer-L7, obtains 83.3% accuracy with only 7.0 ms latency. Our work proves that properly designed transformers can reach extremely low latency on mobile devices while maintaining high performance 1 .

Next-ViT: Next Generation Vision Transformer for Efficient Deployment in Realistic Industrial Scenarios

“…Hybrid Models. Recent works [7,17,23,29,35] have shown that combining convolution and Transformer as a hybrid architecture helps absorb the strengths of both architectures. BoTNet [29] replaces the spatial convolutions with global self-attention in the final three bottleneck blocks of ResNet.…”

“…Mobile-Former [2] combines with the proposed lightweight cross attention to model the bridge, which is not only computationally efficient, but also has more representation power. EfficientFormer [17] complies with a dimension consistent design that smoothly leverages hardware-friendly 4D MetaBlocks and powerful 3D MHSA blocks. In this paper, we design a family of Next-ViT models that adapt more to the realistic industrial scenarios.…”

“…Some recent works [4,17,23,36] have paid great efforts to combine CNN and Transformer for efficient deployment. As shown in Figure 4(b)(c), almost all of them monotonously adopt convolution blocks in the shallow stages and just stack Transformer blocks in the last one or two stages which presents effective results in the classification task.…”

“…For example, Swin Transformer [19] and PVT [34] try to design more efficient spatial attention mechanisms to alleviate the quadratic-increasing computation complexity of MHSA. The others [4,17,23] consider combining efficient convolution blocks and powerful Transformer blocks to design CNN-Transformer hybrid architecture to obtain a better trade-off between accuracy and latency. Coincidentally, almost all existing hybrid architectures [4,17,23] adopt convolution blocks in the shallow stages and just stack Transformer block in the last few stages.…”

“…The others [4,17,23] consider combining efficient convolution blocks and powerful Transformer blocks to design CNN-Transformer hybrid architecture to obtain a better trade-off between accuracy and latency. Coincidentally, almost all existing hybrid architectures [4,17,23] adopt convolution blocks in the shallow stages and just stack Transformer block in the last few stages. However, we observe that such a hybrid strategy is effortless to lead to performance saturation on downstream tasks (e.g.…”