Vision transformers (ViTs) have gained popularity recently. Even without customized image operators such as convolutions, ViTs can yield competitive performance when properly trained on massive data. However, the computational overhead of ViTs remains prohibitive, due to stacking multi-head self-attention modules and else. Compared to the vast literature and prevailing success in compressing convolutional neural networks, the study of Vision Transformer compression has also just emerged, and existing works focused on one or two aspects of compression. This paper proposes a unified ViT compression framework that seamlessly assembles three effective techniques: pruning, layer skipping, and knowledge distillation. We formulate a budget-constrained, end-to-end optimization framework, targeting jointly learning model weights, layer-wise pruning ratios/masks, and skip configurations, under a distillation loss. The optimization problem is then solved using the primal-dual algorithm. Experiments are conducted with several ViT variants, e.g. DeiT and T2T-ViT backbones on the ImageNet dataset, and our approach consistently outperforms recent competitors. For example, DeiT-Tiny can be trimmed down to 50\% of the original FLOPs almost without losing accuracy. Codes are available online:~\url{https://github.com/VITA-Group/UVC}.
Transformer architecture has gained popularity due to its ability to scale with large dataset. Consequently, there is a need to reduce the model size and latency, especially for on-device deployment. We focus on vision transformer proposed for image recognition task (Dosovitskiy et al., 2021), and explore the application of different compression techniques such as low rank approximation and pruning for this purpose. Specifically, we investigate a structured pruning method proposed recently in Zhu et al. (2021) and find that mostly feedforward blocks are pruned with this approach, that too, wit…
LIB-KD: Teaching Inductive Bias for Efficient Vision Transformer Distillation and Compression
Department of Electrical Engineering Indian Institute of Technology Delhi（电子工程系印度理工学院德里）；Yogananda School of AI, Computers and Data Sciences（Yoganananda人工智能、计算机与数据科学学院）
Extreme compression, particularly ultra-low bit precision (binary/ternary) quantization, has been proposed to fit large NLP models on resource-constraint devices. However, to preserve the accuracy for such aggressive compression schemes, cutting-edge methods usually introduce complicated compression pipelines, e.g., multi-stage expensive knowledge distillation with extensive hyperparameter tuning. Also, they oftentimes focus less on smaller transformer models that have already been heavily compressed via knowledge distillation and lack a systematic study to show the effectiveness of their meth…
Modular Transformers: Compressing Transformers into Modularized Layers for Flexible Efficient Inference
ETH Zurich（苏黎世联邦理工学院）；Allen Institute for AI（艾伦人工智能研究所）；Paul G. Allen School of Computer Science & Engineering, University of Washington（华盛顿大学保罗·G·艾伦计算机科学与工程学院）
Transformer models have been developed in molecular science with excellent performance in applications including quantitative structure-activity relationship (QSAR) and virtual screening (VS). Compared with other types of models, however, they are large, which results in a high hardware requirement to abridge time for both training and inference processes. In this work, cross-layer parameter sharing (CLPS), and knowledge distillation (KD) are used to reduce the sizes of transformers in molecular science. Both methods not only have competitive QSAR predictive performance as compared to the orig…
In recent years, the fields of natural language processing (NLP) and information retrieval (IR) have made tremendous progress thanksto deep learning models like Recurrent Neural Networks (RNNs), Gated Recurrent Units (GRUs) and Long Short-Term Memory (LSTMs)networks, and Transformer [120] based models like Bidirectional Encoder Representations from Transformers (BERT) [24], GenerativePre-training Transformer (GPT-2) [94], Multi-task Deep Neural Network (MT-DNN) [73], Extra-Long Network (XLNet) [134], Text-to-text transfer transformer (T5) [95], T-NLG [98] and GShard [63]. But these models are …
Transformer-Based Autonomous Driving Models and Deployment-Oriented Compression: A Survey
Renmin University of China（中国人民大学）；Artificial Intelligence Innovation and Incubation Institute, Fudan University（复旦大学人工智能创新与孵化院）；Shanghai Academy of AI for Science（上海人工智能科学研究院）；Department of houmo.ai（houmo.ai部门）
Time and Memory Trade-off of KV-Cache Compression in Tensor Transformer Decoding
The University of Chicago（芝加哥大学）；Stevens Institute of Technology（史蒂文斯理工学院）；The University of Hong Kong（香港大学）；University of Wisconsin-Madison（威斯康星大学麦迪逊分校）；The Simons Institute for the Theory of Computing at UC Berkeley（加州大学伯克利分校西蒙斯理论计算研究所）
University of Arkansas（阿肯色大学）；Carnegie Mellon University（卡内基梅隆大学）；Mohammed bin Zayed University of AI（穆罕默德·本·扎耶德人工智能大学）
Video paragraph captioning aims to generate a multi-sentence description of an untrimmed video with several temporal event locations in coherent storytelling. Following the human perception process, where the scene is effectively understood by decomposing it into visual (e.g. human, animal) and non-visual components (e.g. action, relations) under the mutual influence of vision and language, we first propose a visual-linguistic (VL) feature. In the proposed VL feature, the scene is modeled by three modalities including (i) a global visual environment; (ii) local visual main agents; (iii) lingui…
Transformers have attained superior performance in natural language processing and computer vision. Their self-attention and feedforward layers are overparameterized, limiting inference speed and energy efficiency. Tensor decomposition is a promising technique to reduce parameter redundancy by leveraging tensor algebraic properties to express the parameters in a factorized form. Prior efforts used manual or heuristic factorization settings without hardware-aware customization, resulting in poor hardware efficiencies and large performance degradation. In this work, we propose a hardware-aware t…
Is Smaller Always Faster? Tradeoffs in Compressing Self-Supervised Speech Transformers
Graduate Institute of Communication Engineering, National Taiwan University, Taiwan（台湾国立台湾大学通信工程研究所）；University of California, Los Angeles, United States（美国加州大学洛杉矶分校）；University of Washington, United States（美国华盛顿大学）；University of Edinburgh, United Kingdom（英国爱丁堡大学）
We show how transformers can be used to vastly simplify neural video compression. Previous methods have been relying on an increasing number of architectural biases and priors, including motion prediction and warping operations, resulting in complex models. Instead, we independently map input frames to representations and use a transformer to model their dependencies, letting it predict the distribution of future representations given the past. The resulting video compression transformer outperforms previous methods on standard video compression data sets. Experiments on synthetic data show th…
Vision transformers (ViT) have recently attracted considerable attentions, but the huge computational cost remains an issue for practical deployment. Previous ViT pruning methods tend to prune the model along one dimension solely, which may suffer from excessive reduction and lead to sub-optimal model quality. In contrast, we advocate a multi-dimensional ViT compression paradigm, and propose to harness the redundancy reduction from attention head, neuron and sequence dimensions jointly. We firstly propose a statistical dependence based pruning criterion that is generalizable to different dimen…
Institute for AI Industry Research (AIR), Tsinghua University（清华大学人工智能产业研究院（AIR））；Beijing University of Posts and Telecommunications（北京邮电大学）；University of Science and Technology of China（中国科学技术大学）
With the development of gene sequencing technology, an explosive growth of gene data has been witnessed. And the storage of gene data has become an important issue. Traditional gene data compression methods rely on general software like G-zip, which fails to utilize the interrelation of nucleotide sequence. Recently, many researchers begin to investigate deep learning based gene data compression method. In this paper, we propose a transformer-based gene compression method named GeneFormer. Specifically, we first introduce a modified transformer structure to fully explore the nucleotide sequenc…
Vision Transformers are increasingly embedded in industrial systems due to their superior performance, but their memory and power requirements make deploying them to edge devices a challenging task. Hence, model compression techniques are now widely used to deploy models on edge devices as they decrease the resource requirements and make model inference very fast and efficient. But their reliability and robustness from a security perspective is another major issue in safety-critical applications. Adversarial attacks are like optical illusions for ML algorithms and they can severely impact the …
City University of Hong Kong（香港城市大学）；National Taiwan University（台湾大学）
Deep-learning-based compressor has received interests recently due to much improved compression ratio. However, modern approaches suffer from long execution time. To ease this problem, this paper targets on cutting down the execution time of deep-learning-based compressors. Building history-dependencies sequentially (e.g., recurrent neural networks) is responsible for long inference latency. Instead, we introduce transformer into deep learning compressors to build history-dependencies in parallel. However, existing transformer is too heavy in computation and incompatible to compression tasks. …
Easz: An Agile Transformer-based Image Compression Framework for Resource-constrained IoTs
Mohamed bin Zayed University of Artificial Intelligence（Mohamed bin Zayed大学人工智能学院）；The Hang Seng University of Hong Kong（恒生大学）；City University of Hong Kong（城市大学）；The Chinese University of Hong Kong（香港中文大学）；National Taiwan University（台湾国立台湾大学）
Modern search systems use several large ranker models with transformer architectures. These models require large computational resources and are not suitable for usage on devices with limited computational resources. Knowledge distillation is a popular compression technique that can reduce the resource needs of such models, where a large teacher model transfers knowledge to a small student model. To drastically reduce memory requirements and energy consumption, we propose two extensions for a popular sentence-transformer distillation procedure: generation of an optimal size vocabulary and dime…
ChWDTA: Channel-wise Wavelet-Domain Transformer Attention and Entropy Modeling for Learned Image Compression
Electrical and Computer Engineering Department, The University of British Columbia（英属哥伦比亚大学电气与计算机工程系）；School of Engineering Science, Simon Fraser University（西蒙弗雷泽大学工程科学学院）；School of Electronic Science and Technology, Eastern Institute of Technology（电子科学与技术学院，东部技术学院）；Google LLC（谷歌公司）
