Transformers [1] have become one of the most important architectural innovations in deep learning and have enabled many breakthroughs over the past few years. Here we propose a simple network architecture, gMLP, based on MLPs with gating, and show that it can perform as well as Transformers in key language and vision applications. Our comparisons show that self-attention is not critical for Vision Transformers, as gMLP can achieve the same accuracy. For BERT, our model achieves parity with Transformers on pretraining perplexity and is better on some downstream NLP tasks. On finetuning tasks where gMLP performs worse, making the gMLP model substantially larger can close the gap with Transformers. In general, our experiments show that gMLP can scale as well as Transformers over increased data and compute.

We perform finetuning with image-textcontrastiveand image-textmatching losses. During inference, VLMO is first used as a dual encoder to obtain top-k candidates, then the model is used as a fusionencoder torerankthecandidates. For the text-only pre-training data, we use English Wikipedia and BookCorpus [5]. Table 1: Ablation study of the shared self-attention module used in Multiway Transformer.

Multi-scene absolute pose regression addresses the demand for fast and memory-efficient camera pose estimation across various real-world environments.

Pre-trained language models (e.g., BERT (Devlin et al., 2018) and its variants) have achieved remarkable success in varieties of NLP tasks. However, these models usually consist of hundreds of millions of parameters which brings challenges for fine-tuning and online serving in real-life applications due to latency and capacity constraints. In this work, we present a simple and effective approach to compress large Transformer (Vaswani et al., 2017) based pre-trained models, termed as deep self-attention distillation. The small model (student) is trained by deeply mimicking the self-attention module, which plays a vital role in Transformer networks, of the large model (teacher). Specifically, we propose distilling the self-attention module of the last Transformer layer of the teacher, which is effective and flexible for the student. Furthermore, we introduce the scaled dot-product between values in the self-attention module as the new deep self-attention knowledge, in addition to the attention distributions (i.e., the scaled dot-product of queries and keys) that have been used in existing works.

Multi-scene absolute pose regression addresses the demand for fast and memory-efficient camera pose estimation across various real-world environments.

The small model (student) is trained by deeply mimicking the self-attention module, which plays a vital role in Transformer networks, of the large model (teacher).

We encode each channel's output dimension to a high dimension for better representation of the bits' information to be processed separately.

Pre-trained vision transformers have achieved remarkable performance across various visual tasks but suffer from expensive computational and memory costs. While model quantization reduces memory usage by lowering precision, these models still incur significant computational overhead due to the dequantization before matrix operations. In this work, we analyze the computation graph and propose an integerization process based on operation reordering. Specifically, the process delays dequantization until after matrix operations. This enables integerized matrix multiplication and linear module by directly processing the quantized input. To validate our approach, we synthesize the self-attention module of ViT on a systolic array-based hardware. Experimental results show that our low-bit inference reduces per-PE power consumption for linear layer and matrix multiplication, bridging the gap between quantized models and efficient inference.