More Like this

1. TPrune: Efficient Transformer Pruning for Mobile Devices

   https://doi.org/10.1145/3446640  

   Mao, Jiachen; Yang, Huanrui; Li, Ang; Li, Hai; Chen, Yiran (July 2021, ACM Transactions on Cyber-Physical Systems)

   null (Ed.)

   The invention of Transformer model structure boosts the performance of Neural Machine Translation (NMT) tasks to an unprecedented level. Many previous works have been done to make the Transformer model more execution-friendly on resource-constrained platforms. These researches can be categorized into three key fields: Model Pruning, Transfer Learning, and Efficient Transformer Variants. The family of model pruning methods are popular for their simplicity in practice and promising compression rate and have achieved great success in the field of convolution neural networks (CNNs) for many vision tasks. Nonetheless, previous Transformer pruning works did not perform a thorough model analysis and evaluation on each Transformer component on off-the-shelf mobile devices. In this work, we analyze and prune transformer models at the line-wise granularity and also implement our pruning method on real mobile platforms. We explore the properties of all Transformer components as well as their sparsity features, which are leveraged to guide Transformer model pruning. We name our whole Transformer analysis and pruning pipeline as TPrune. In TPrune, we first propose Block-wise Structured Sparsity Learning (BSSL) to analyze Transformer model property. Then, based on the characters derived from BSSL, we apply Structured Hoyer Square (SHS) to derive the final pruned models. Comparing with the state-of-the-art Transformer pruning methods, TPrune is able to achieve a higher model compression rate with less performance degradation. Experimental results show that our pruned models achieve 1.16×–1.92× speedup on mobile devices with 0%–8% BLEU score degradation compared with the original Transformer model. 

   more » « less
2. AttCAT: Explaining Transformers via Attentive Class Activation Tokens

   Qiang, Y (January 2022, Advances in neural information processing systems)

   Transformers have improved the state-of-the-art in various natural language processing and computer vision tasks. However, the success of the Transformer model has not yet been duly explained. Current explanation techniques, which dissect either the self-attention mechanism or gradient-based attribution, do not necessarily provide a faithful explanation of the inner workings of Transformers due to the following reasons: first, attention weights alone without considering the magnitudes of feature values are not adequate to reveal the self-attention mechanism; second, whereas most Transformer explanation techniques utilize self-attention module, the skip-connection module, contributing a significant portion of information flows in Transformers, has not yet been sufficiently exploited in explanation; third, the gradient-based attribution of individual feature does not incorporate interaction among features in explaining the model’s output. In order to tackle the above problems, we propose a novel Transformer explanation technique via attentive class activation tokens, aka, AttCAT, leveraging encoded features, their gradients, and their attention weights to generate a faithful and confident explanation for Transformer’s output. Extensive experiments are conducted to demonstrate the superior performance of AttCAT, which generalizes well to different Transformer architectures, evaluation metrics, datasets, and tasks, to the baseline methods. Our code is available at: https://github.com/qiangyao1988/AttCAT. 

   more » « less
3. Coarse-to-Fine Vision-Language Pre-training with Fusion in the Backbone

   Dou, Zi-Yi; Kamath, Aishwarya; Gan, Zhe; Zhang, Pengchuan; Wang, Jianfeng; Li, Linjie; Liu, Zicheng; Liu, Ce; LeCun, Yann; Peng, Nanyun; et al (October 2022, NeurIPS)

   Vision-language (VL) pre-training has recently received considerable attention. However, most existing end-to-end pre-training approaches either only aim to tackle VL tasks such as image-text retrieval, visual question answering (VQA) and image captioning that test high-level understanding of images, or only target region-level understanding for tasks such as phrase grounding and object detection. We present FIBER (Fusion-In-the-Backbone-based transformER), a new VL model architecture that can seamlessly handle both these types of tasks. Instead of having dedicated transformer layers for fusion after the uni-modal backbones, FIBER pushes multimodal fusion deep into the model by inserting cross-attention into the image and text backbones to better capture multimodal interactions. In addition, unlike previous work that is either only pre-trained on image-text data or on fine-grained data with box-level annotations, we present a two-stage pre-training strategy that uses both these kinds of data efficiently: (i) coarse-grained pre-training based on image-text data; followed by (ii) fine-grained pre-training based on image-text-box data. We conduct comprehensive experiments on a wide range of VL tasks, ranging from VQA, image captioning, and retrieval, to phrase grounding, referring expression comprehension, and object detection. Using deep multimodal fusion coupled with the two-stage pre-training, FIBER provides consistent performance improvements over strong baselines across all tasks, often outperforming methods using magnitudes more data. Code is released at https://github.com/microsoft/FIBER. 

   more » « less
4. Pruning Parameterization with Bi-level Optimization for Efficient Semantic Segmentation on the Edge

   Yang, Changdi; Zhao, Pu; Li, Yanyu; Niu, Wei; Guan, Jiexiong; Tang, Hao; Qin, Minghai; Ren, Bin; Lin, Xue; Wang, Yanzhi (June 2023, The IEEE / CVF Computer Vision and Pattern Recognition Conference (CVPR))

   With the ever-increasing popularity of edge devices, it is necessary to implement real-time segmentation on the edge for autonomous driving and many other applications. Vision Transformers (ViTs) have shown considerably stronger results for many vision tasks. However, ViTs with the fullattention mechanism usually consume a large number of computational resources, leading to difficulties for realtime inference on edge devices. In this paper, we aim to derive ViTs with fewer computations and fast inference speed to facilitate the dense prediction of semantic segmentation on edge devices. To achieve this, we propose a pruning parameterization method to formulate the pruning problem of semantic segmentation. Then we adopt a bi-level optimization method to solve this problem with the help of implicit gradients. Our experimental results demonstrate that we can achieve 38.9 mIoU on ADE20K val with a speed of 56.5 FPS on Samsung S21, which is the highest mIoU under the same computation constraint with real-time inference. 

   more » « less
5. ViTCoD: Vision Transformer Acceleration via Dedicated Algorithm and Accelerator Co-Design

   https://doi.org/10.1109/HPCA56546.2023.10071027  

   You, Haoran; Sun, Zhanyi; Shi, Huihong; Yu, Zhongzhi; Zhao, Yang; Zhang, Yongan; Li, Chaojian; Li, Baopu; Lin, Yingyan (February 2023, 2023 IEEE International Symposium on High-Performance Computer Architecture (HPCA))

   Vision Transformers (ViTs) have achieved state-of-the-art performance on various vision tasks. However, ViTs’ self-attention module is still arguably a major bottleneck, limiting their achievable hardware efficiency and more extensive applications to resource constrained platforms. Meanwhile, existing accelerators dedicated to NLP Transformers are not optimal for ViTs. This is because there is a large difference between ViTs and Transformers for natural language processing (NLP) tasks: ViTs have a relatively fixed number of input tokens, whose attention maps can be pruned by up to 90% even with fixed sparse patterns, without severely hurting the model accuracy (e.g., <=1.5% under 90% pruning ratio); while NLP Transformers need to handle input sequences of varying numbers of tokens and rely on on-the-fly predictions of dynamic sparse attention patterns for each input to achieve a decent sparsity (e.g., >=50%). To this end, we propose a dedicated algorithm and accelerator co-design framework dubbed ViTCoD for accelerating ViTs. Specifically, on the algorithm level, ViTCoD prunes and polarizes the attention maps to have either denser or sparser fixed patterns for regularizing two levels of workloads without hurting the accuracy, largely reducing the attention computations while leaving room for alleviating the remaining dominant data movements; on top of that, we further integrate a lightweight and learnable auto-encoder module to enable trading the dominant high-cost data movements for lower-cost computations. On the hardware level, we develop a dedicated accelerator to simultaneously coordinate the aforementioned enforced denser and sparser workloads for boosted hardware utilization, while integrating on-chip encoder and decoder engines to leverage ViTCoD’s algorithm pipeline for much reduced data movements. Extensive experiments and ablation studies validate that ViTCoD largely reduces the dominant data movement costs, achieving speedups of up to 235.3×, 142.9×, 86.0×, 10.1×, and 6.8× over general computing platforms CPUs, EdgeGPUs, GPUs, and prior-art Transformer accelerators SpAtten and Sanger under an attention sparsity of 90%, respectively. Our code implementation is available at https://github.com/GATECH-EIC/ViTCoD. 

   more » « less