Deep neural networks with lower precision weights and operations at inference time have advantages in terms of the cost of memory space and accelerator power. The main challenge associated with the quantization algorithm is maintaining accuracy at low bit-widths. We propose learned gradient linear symmetric quantization (LG-LSQ) as a method for quantizing weights and activation functions to low bit-widths with high accuracy in integer neural network processors. First, we introduce the scaling simulated gradient (SSG) method for determining the appropriate gradient for the scaling factor of the linear quantizer during the training process. Second, we introduce the arctangent soft round (ASR) method, which differs from the straight-through estimator (STE) method in its ability to prevent the gradient from becoming zero, thereby solving the discrete problem caused by the rounding process. Finally, to bridge the gap between full-precision and low-bit quantization networks, we propose the minimize discretization error (MDE) method to determine an accurate gradient in backpropagation. The ASR+MDE method is a simple alternative to the STE method and is practical for use in different uniform quantization methods. In our evaluation, the proposed quantizer achieved full-precision baseline accuracy in various 3-bit networks, including ResNet18, ResNet34, and ResNet50, and an accuracy drop of less than 1% in the quantization of 4-bit weights and 4-bit activations in lightweight models such as MobileNetV2 and ShuffleNetV2.
Qualcomm AI Research, Qualcomm Technologies, Inc.（高通AI研究，高通技术公司）；Qualcomm AI Research, Qualcomm Technologies Netherlands B.V.（高通AI研究，高通技术荷兰有限公司）；Seoul National University（首尔大学）
Unlike ReLU, newer activation functions (like Swish, H-swish, Mish) that are frequently employed in popular efficient architectures can also result in negative activation values, with skewed positive and negative ranges. Typical learnable quantization schemes [PACT, LSQ] assume unsigned quantization for activations and quantize all negative activations to zero which leads to significant loss in performance. Naively using signed quantization to accommodate these negative values requires an extra sign bit which is expensive for low-bit (2-, 3-, 4-bit) quantization. To solve this problem, we prop…
Task-Aware QUBO Allocation for Mixed-Precision Quantization
Innopolis University（因诺波利斯大学）；Q Deep；Moscow Independent Research Institute of Artificial Intelligence (MIRAI)（莫斯科独立人工智能研究院（MIRAI））；Sirius University of Science and Technology（天狼星科技大学）
Recent advance of large scale similarity search involves using deeply learned representations to improve the search accuracy and use vector quantization methods to increase the search speed. However, how to learn deep representations that strongly preserve similarities between data pairs and can be accurately quantized via vector quantization remains a challenging task. Existing methods simply leverage quantization loss and similarity loss, which result in unexpectedly biased back-propagating gradients and affect the search performances. To this end, we propose a novel gradient snapping layer …
Xidian University（西安电子科技大学）；Tencent AI Lab（腾讯人工智能实验室）；The University of Sydney（悉尼大学）
With explosive growth of data volume and ever-increasing diversity of data modalities, cross-modal similarity search, which conducts nearest neighbor search across different modalities, has been attracting increasing interest. This paper presents a deep compact code learning solution for efficient cross-modal similarity search. Many recent studies have proven that quantization-based approaches perform generally better than hashing-based approaches on single-modal similarity search. In this paper, we propose a deep quantization approach, which is among the early attempts of leveraging deep neur…
Although weight and activation quantization is an effective approach for Deep Neural Network (DNN) compression and has a lot of potentials to increase inference speed leveraging bit-operations, there is still a noticeable gap in terms of prediction accuracy between the quantized model and the full-precision model. To address this gap, we propose to jointly train a quantized, bit-operation-compatible DNN and its associated quantizers, as opposed to using fixed, handcrafted quantization schemes such as uniform or logarithmic quantization. Our method for learning the quantizers applies to both ne…
Samsung R&D Institute India- Bangalore（三星印度班加罗尔研发中心）；Indian Institute of Technology Guwahati（印度理工学院古瓦哈提分校）；TensorTour Inc.（TensorTour公司）
Quantizing the floating-point weights and activations of deep convolutional neural networks to fixed-point representation yields reduced memory footprints and inference time. Recently, efforts have been afoot towards zero-shot quantization that does not require original unlabelled training samples of a given task. These best-published works heavily rely on the learned batch normalization (BN) parameters to infer the range of the activations for quantization. In particular, these methods are built upon either empirical estimation framework or the data distillation approach, for computing the ra…
Tsinghua University（清华大学）；Peng Cheng Laboratory（鹏城实验室）；Shanghai Jiao Tong University（上海交通大学）；Institute of Computing Technology, Chinese Academy of Sciences（中国科学院计算技术研究所）
The exponentially large discrete search space in mixed-precision quantization (MPQ) makes it hard to determine the optimal bit-width for each layer. Previous works usually resort to iterative search methods on the training set, which consume hundreds or even thousands of GPU-hours. In this study, we reveal that some unique learnable parameters in quantization, namely the scale factors in the quantizer, can serve as importance indicators of a layer, reflecting the contribution of that layer to the final accuracy at certain bit-widths. These importance indicators naturally perceive the numerical…
MEC-Quant: Maximum Entropy Coding for Extremely Low Bit Quantization-Aware Training
Faculty of Information Technology, Beijing University of Technology（信息技术学院，北京理工大学）；University of Chinese Academy of Sciences, Chinese Academy of Sciences (CAS)（中国科学院大学，中国科学院）；Institute of Computing Technology, CAS（计算技术研究所，中国科学院）
McGill（麦吉尔大学）；Mila（米拉研究所）；Facebook AI Research（Facebook人工智能研究院）；University of Montreal（蒙特利尔大学）；ElementAI（ElementAI公司）
We introduce and study the problem of Online Continual Compression, where one attempts to simultaneously learn to compress and store a representative dataset from a non i.i.d data stream, while only observing each sample once. A naive application of auto-encoders in this setting encounters a major challenge: representations derived from earlier encoder states must be usable by later decoder states. We show how to use discrete auto-encoders to effectively address this challenge and introduce Adaptive Quantization Modules (AQM) to control variation in the compression ability of the module at any…
Beijing Jiaotong University（北京交通大学）；Taiyuan University of Science and Technology（太原科技大学）
In this paper, we propose a deep multiple description coding framework, whose quantizers are adaptively learned via the minimization of multiple description compressive loss. Firstly, our framework is built upon auto-encoder networks, which have multiple description multi-scale dilated encoder network and multiple description decoder networks. Secondly, two entropy estimation networks are learned to estimate the informative amounts of the quantized tensors, which can further supervise the learning of multiple description encoder network to represent the input image delicately. Thirdly, a pair …
ProtoQuant: Quantization of Prototypical Parts For General and Fine-Grained Image Classification
Jagiellonian University, Faculty of Mathematics and Computer Science（杰洛尼莫夫大学数学与计算机科学系）；Jagiellonian University, Doctoral School of Exact and Natural Sciences（杰洛尼莫夫大学精确与自然科学研究博士学院）
Tel Aviv University（特拉维夫大学）；Facebook AI Research（Facebook人工智能研究院）
Product Quantization, a dictionary based hashing method, is one of the leading unsupervised hashing techniques. While it ignores the labels, it harnesses the features to construct look up tables that can approximate the feature space. In recent years, several works have achieved state of the art results on hashing benchmarks by learning binary representations in a supervised manner. This work presents Deep Product Quantization (DPQ), a technique that leads to more accurate retrieval and classification than the latest state of the art methods, while having similar computational complexity and m…
Sony Group Corporation（索尼集团公司）；Sony Corporation of America（美国索尼公司）
One noted issue of vector-quantized variational autoencoder (VQ-VAE) is that the learned discrete representation uses only a fraction of the full capacity of the codebook, also known as codebook collapse. We hypothesize that the training scheme of VQ-VAE, which involves some carefully designed heuristics, underlies this issue. In this paper, we propose a new training scheme that extends the standard VAE via novel stochastic dequantization and quantization, called stochastically quantized variational autoencoder (SQ-VAE). In SQ-VAE, we observe a trend that the quantization is stochastic at the …
Cross-modal retrieval aims to search for data with similar semantic meanings across different content modalities. However, cross-modal retrieval requires huge amounts of storage and retrieval time since it needs to process data in multiple modalities. Existing works focused on learning single-source compact features such as binary hash codes that preserve similarities between different modalities. In this work, we propose a jointly learned deep hashing and quantization network (HQ) for cross-modal retrieval. We simultaneously learn binary hash codes and quantization codes to preserve semantic …
Image hashing is a principled approximate nearest neighbor approach to find similar items to a query in a large collection of images. Hashing aims to learn a binary-output function that maps an image to a binary vector. For optimal retrieval performance, producing balanced hash codes with low-quantization error to bridge the gap between the learning stage's continuous relaxation and the inference stage's discrete quantization is important. However, in the existing deep supervised hashing methods, coding balance and low-quantization error are difficult to achieve and involve several losses. We …
Taiyuan University of Science and Technology（太原科技大学）；Beijing Jiaotong University（北京交通大学）
In this paper, we introduce a deep multiple description coding (MDC) framework optimized by minimizing multiple description (MD) compressive loss. First, MD multi-scale-dilated encoder network generates multiple description tensors, which are discretized by scalar quantizers, while these quantized tensors are decompressed by MD cascaded-ResBlock decoder networks. To greatly reduce the total amount of artificial neural network parameters, an auto-encoder network composed of these two types of network is designed as a symmetrical parameter sharing structure. Second, this autoencoder network and …
Stanford University（斯坦福大学）；University of New South Wales（新南威尔士大学）
In this paper, we compress convolutional neural network (CNN) weights post-training via transform quantization. Previous CNN quantization techniques tend to ignore the joint statistics of weights and activations, producing sub-optimal CNN performance at a given quantization bit-rate, or consider their joint statistics during training only and do not facilitate efficient compression of already trained CNN models. We optimally transform (decorrelate) and quantize the weights post-training using a rate-distortion framework to improve compression at any given quantization bit-rate. Transform quant…
Deep neural networks are vulnerable to Trojan attacks. Existing attacks use visible patterns (e.g., a patch or image transformations) as triggers, which are vulnerable to human inspection. In this paper, we propose stealthy and efficient Trojan attacks, BppAttack. Based on existing biology literature on human visual systems, we propose to use image quantization and dithering as the Trojan trigger, making imperceptible changes. It is a stealthy and efficient attack without training auxiliary models. Due to the small changes made to images, it is hard to inject such triggers during training. To …
Convolutional Neural Networks (CNN) are very popular in many fields including computer vision, speech recognition, natural language processing, to name a few. Though deep learning leads to groundbreaking performance in these domains, the networks used are very demanding computationally and are far from real-time even on a GPU, which is not power efficient and therefore does not suit low power systems such as mobile devices. To overcome this challenge, some solutions have been proposed for quantizing the weights and activations of these networks, which accelerate the runtime significantly. Yet,…
Tsinghua Shenzhen International Graduate School, Tsinghua University（清华大学深圳国际研究生院）；Harbin Institute of Technology, Shenzhen（哈尔滨工业大学深圳）；Research Center of Artificial Intelligence, Peng Cheng Laboratory（鹏城实验室人工智能研究中心）；Data Quality Team, Wechat Group, Tencent Inc.（腾讯公司微信团队数据质量组）；Wechat Group, Tencent Inc.（腾讯公司微信团队）；Tencent Inc.（腾讯公司）；Tsinghua University（清华大学）；Harbin Institute of Technology（哈尔滨工业大学）；Peng Cheng Laboratory（鹏城实验室）
With the recent boom of video-based social platforms (e.g., YouTube and TikTok), video retrieval using sentence queries has become an important demand and attracts increasing research attention. Despite the decent performance, existing text-video retrieval models in vision and language communities are impractical for large-scale Web search because they adopt brute-force search based on high-dimensional embeddings. To improve efficiency, Web search engines widely apply vector compression libraries (e.g., FAISS) to post-process the learned embeddings. Unfortunately, separate compression from fea…
It has been witnessed that learned image compression has outperformed conventional image coding techniques and tends to be practical in industrial applications. One of the most critical issues that need to be considered is the non-deterministic calculation, which makes the probability prediction cross-platform inconsistent and frustrates successful decoding. We propose to solve this problem by introducing well-developed post-training quantization and making the model inference integer-arithmetic-only, which is much simpler than presently existing training and fine-tuning based approaches yet s…
Learning-based image compression has improved to a level where it can outperform traditional image codecs such as HEVC and VVC in terms of coding performance. In addition to good compression performance, device interoperability is essential for a compression codec to be deployed, i.e., encoding and decoding on different CPUs or GPUs should be error-free and with negligible performance reduction. In this paper, we present a method to solve the device interoperability problem of a state-of-the-art image compression network. We implement quantization to entropy networks which output entropy param…
Interleaved Block-based Learned Image Compression with Feature Enhancement and Quantization Error Compensation
School of software, Shandong University（山东大学软件学院）；School of Control Science and Engineering, Shandong University（山东大学控制科学与工程学院）；School of Engineering and Sustainable Development, De Montfort University（德蒙福特大学工程与可持续发展学院）；College of Computer Science and Software Engineering, Shenzhen University（深圳大学计算机与软件学院）；School of Telecommunications Engineering, Xidian University（西安电子科技大学通信工程学院）
In this paper, we introduce a method to compress intermediate feature maps of deep neural networks (DNNs) to decrease memory storage and bandwidth requirements during inference. Unlike previous works, the proposed method is based on converting fixed-point activations into vectors over the smallest GF(2) finite field followed by nonlinear dimensionality reduction (NDR) layers embedded into a DNN. Such an end-to-end learned representation finds more compact feature maps by exploiting quantization redundancies within the fixed-point activations along the channel or spatial dimensions. We apply th…
HAMP-LIC: Hessian-Aware Mixed-Precision Post-Training Quantization for Learned Image Compression
Beijing Institute of Computer Technology and Application（北京计算机技术及应用研究所）；School of Elite Engineering, Northwestern Polytechnical University（西北工业大学精英工程学院）
University of Science and Technology of China（中国科学技术大学）；Alibaba Group（阿里巴巴集团）；University of Southern California（南加州大学）
Although deep neural networks are highly effective, their high computational and memory costs severely challenge their applications on portable devices. As a consequence, low-bit quantization, which converts a full-precision neural network into a low-bitwidth integer version, has been an active and promising research topic. Existing methods formulate the low-bit quantization of networks as an approximation or optimization problem. Approximation-based methods confront the gradient mismatch problem, while optimization-based methods are only suitable for quantizing weights and could introduce hig…
Benefit from flexible network designs and end-to-end joint optimization approach, learned image compression (LIC) has demonstrated excellent coding performance and practical feasibility in recent years. However, existing compression models suffer from serious multi-generation loss, which always occurs during image editing and transcoding. During the process of repeatedly encoding and decoding, the quality of the image will rapidly degrade, resulting in various types of distortion, which significantly limits the practical application of LIC. In this paper, a thorough analysis is carried out to …
Graz University of Technology（格拉茨理工大学）；Infineon Technologies Austria AG（英飞凌科技奥地利股份公司）
Radar sensors are crucial for environment perception of driver assistance systems as well as autonomous vehicles. With a rising number of radar sensors and the so far unregulated automotive radar frequency band, mutual interference is inevitable and must be dealt with. Algorithms and models operating on radar data are required to run the early processing steps on specialized radar sensor hardware. This specialized hardware typically has strict resource-constraints, i.e. a low memory capacity and low computational power. Convolutional Neural Network (CNN)-based approaches for denoising and inte…
Simon Fraser University（西蒙弗雷泽大学）；Google Inc.（谷歌公司）；Tencent Technologies（腾讯科技）
Recently it has been shown that deep learning-based image compression has shown the potential to outperform traditional codecs. However, most existing methods train multiple networks for multiple bit rates, which increases the implementation complexity. In this paper, we propose a variable-rate image compression framework, which employs more Generalized Divisive Normalization (GDN) layers than previous GDN-based methods. Novel GDN-based residual sub-networks are also developed in the encoder and decoder networks. Our scheme also uses a stochastic rounding-based scalable quantization. To furthe…
