3D human pose and shape estimation (HPE) aims to reconstruct the 3D human body, face, and hands from a single image. Although powerful deep learning models have achieved accurate estimation in this task, they require enormous memory and computational resources. Consequently, these methods can hardly be deployed on resource-limited edge devices. In this work, we propose BinaryHPE, a novel binarization method designed to estimate the 3D human body, face, and hands parameters efficiently. Specifically, we propose a novel binary backbone called Binarized Dual Residual Network (BiDRN), designed to retain as much full-precision information as possible. Furthermore, we propose the Binarized BoxNet, an efficient sub-network for predicting face and hands bounding boxes, which further reduces model redundancy. Comprehensive quantitative and qualitative experiments demonstrate the effectiveness of BinaryHPE, which has a significant improvement over state-of-the-art binarization algorithms. Moreover, our BinaryHPE achieves comparable performance with the full-precision method Hand4Whole while using only 22.1% parameters and 14.8% operations. We will release all the code and pretrained models.
Neural Radiance Fields (NeRFs) have demonstrated remarkable potential in capturing complex 3D scenes with high fidelity. However, one persistent challenge that hinders the widespread adoption of NeRFs is the computational bottleneck due to the volumetric rendering. On the other hand, 3D Gaussian splatting (3DGS) has recently emerged as an alternative representation that leverages a 3D Gaussisan-based representation and adopts the rasterization pipeline to render the images rather than volumetric rendering, achieving very fast rendering speed and promising image quality. However, a significant drawback arises as 3DGS entails a substantial number of 3D Gaussians to maintain the high fidelity of the rendered images, which requires a large amount of memory and storage. To address this critical issue, we place a specific emphasis on two key objectives: reducing the number of Gaussian points without sacrificing performance and compressing the Gaussian attributes, such as view-dependent color and covariance. To this end, we propose a learnable mask strategy that significantly reduces the number of Gaussians while preserving high performance. In addition, we propose a compact but effective representation of view-dependent color by employing a grid-based neural field rather than relying on spherical harmonics. Finally, we learn codebooks to compactly represent the geometric attributes of Gaussian by vector quantization. With model compression techniques such as quantization and entropy coding, we consistently show over 25$\times$ reduced storage and enhanced rendering speed, while maintaining the quality of the scene representation, compared to 3DGS. Our work provides a comprehensive framework for 3D scene representation, achieving high performance, fast training, compactness, and real-time rendering. Our project page is available at https://maincold2.github.io/c3dgs/.
Parameter-efficient fine-tuning (PEFT) techniques make it possible to efficiently adapt a language model to create "expert" models that specialize to new tasks or domains. Recent techniques in model merging and compositional generalization leverage these expert models by dynamically composing modules to improve zero/few-shot generalization. Despite the efficiency of PEFT methods, the size of expert models can make it onerous to retrieve expert models per query over high-latency networks like the Internet or serve multiple experts on a single GPU. To address these issues, we present ComPEFT, a novel method for compressing fine-tuning residuals (task vectors) of PEFT based models. ComPEFT employs sparsification and ternary quantization to reduce the size of the PEFT module without performing any additional retraining while preserving or enhancing model performance. In extensive evaluation across T5, T0, and LLaMA-based models with 200M - 65B parameters, ComPEFT achieves compression ratios of 8x - 50x. In particular, we show that ComPEFT improves with scale - stronger models exhibit higher compressibility and better performance. For example, we show that ComPEFT applied to LLaMA outperforms QLoRA by 4.16% on MMLU with a storage size reduction of up to 26x. In addition, we show that the compressed experts produced by ComPEFT maintain few-shot compositional generalization capabilities, facilitate efficient communication and computation, and exhibit enhanced performance when merged. Lastly, we provide an analysis of different method components, compare it with other PEFT methods, and test ComPEFT's efficacy for compressing the residual of full-finetuning. Our code is available at https://github.com/prateeky2806/compeft.
Sound Source Localization (SSL) involves estimating the Direction of Arrival (DOA) of sound sources. Since the DOA estimation output space is continuous, regression might be more suitable for DOA, offering higher precision. However, in practice, classification often outperforms regression, exhibiting greater robustness to interference. Conversely, classification's drawback is inherent quantization error. Within the classification paradigm, the DOA output space is discretized into intervals, each treated as a class. These classes show strong inter-class correlations, being inherently ordered, with higher similarity as intervals grow closer. Nevertheless, this has not been fully exploited. To address this, we propose an Unbiased Label Distribution (ULD) to eliminate quantization error in training targets. Furthermore, we tailor two loss functions for the soft label family: Negative Log Absolute Error (NLAE) and Mean Squared Error without activation (MSE(wo)). Finally, we introduce Weighted Adjacent Decoding (WAD) to overcome quantization error during model prediction decoding. Experimental results demonstrate our approach surpasses classification quantization limits, achieving state-of-the-art performance. Our code and supplementary materials are available at https://github.com/linfeng-feng/ULD.
We propose a simple approach for memory-efficient adaptation of pretrained language models. Our approach uses an iterative algorithm to decompose each pretrained matrix into a high-precision low-rank component and a memory-efficient quantized component. During finetuning, the quantized component remains fixed and only the low-rank component is updated. We present an integer linear programming formulation of the quantization component which enables dynamic configuration of quantization parameters (e.g., bit-width, block size) for each matrix given an overall target memory budget. We further explore a data-aware version of the algorithm which uses an approximation of the Fisher information matrix to weight the reconstruction objective during matrix decomposition. Experiments on finetuning RoBERTa and LLaMA-2 (7B and 70B) demonstrate that our low-rank plus quantized matrix decomposition approach (LQ-LoRA) outperforms strong QLoRA and GPTQ-LoRA baselines and enables aggressive quantization to sub-3 bits with only minor performance degradations. When finetuned on a language modeling calibration dataset, LQ-LoRA can also be used for model compression; in this setting our 2.75-bit LLaMA-2-70B model (which has 2.85 bits on average when including the low-rank components and requires 27GB of GPU memory) performs respectably compared to the 16-bit baseline.
From classical HPC to deep learning, MatMul is at the heart of today's computing. The recent Maddness method approximates MatMul without the need for multiplication by using a hash-based version of product quantization (PQ) indexing into a look-up table (LUT). Stella Nera is the first Maddness accelerator and it achieves 15x higher area efficiency (GMAC/s/mm^2) and more than 25x higher energy efficiency (TMAC/s/W) than direct MatMul accelerators implemented in the same technology. The hash function is a decision tree, which allows for an efficient hardware implementation as the multiply-accumulate operations are replaced by decision tree passes and LUT lookups. The entire Maddness MatMul can be broken down into parts that allow an effective implementation with small computing units and memories, allowing it to reach extreme efficiency while remaining generically applicable for MatMul tasks. In a commercial 14nm technology and scaled to 3nm, we achieve an energy efficiency of 161 [email omitted] with a Top-1 accuracy on CIFAR-10 of more than 92.5% using ResNet9.
Albeit the scalable performance of vision transformers (ViTs), the dense computational costs (training & inference) undermine their position in industrial applications. Post-training quantization (PTQ), tuning ViTs with a tiny dataset and running in a low-bit format, well addresses the cost issue but unluckily bears more performance drops in lower-bit cases. In this paper, we introduce I&S-ViT, a novel method that regulates the PTQ of ViTs in an inclusive and stable fashion. I&S-ViT first identifies two issues in the PTQ of ViTs: (1) Quantization inefficiency in the prevalent log2 quantizer for post-Softmax activations; (2) Rugged and magnified loss landscape in coarse-grained quantization granularity for post-LayerNorm activations. Then, I&S-ViT addresses these issues by introducing: (1) A novel shift-uniform-log2 quantizer (SULQ) that incorporates a shift mechanism followed by uniform quantization to achieve both an inclusive domain representation and accurate distribution approximation; (2) A three-stage smooth optimization strategy (SOS) that amalgamates the strengths of channel-wise and layer-wise quantization to enable stable learning. Comprehensive evaluations across diverse vision tasks validate I&S-ViT' superiority over existing PTQ of ViTs methods, particularly in low-bit scenarios. For instance, I&S-ViT elevates the performance of 3-bit ViT-B by an impressive 50.68%.
Recently, large language models (LLMs) have shown great potential in recommender systems, either improving existing recommendation models or serving as the backbone. However, there exists a large semantic gap between LLMs and recommender systems, since items to be recommended are often indexed by discrete identifiers (item ID) out of the LLM's vocabulary. In essence, LLMs capture language semantics while recommender systems imply collaborative semantics, making it difficult to sufficiently leverage the model capacity of LLMs for recommendation. To address this challenge, in this paper, we propose a new LLM-based recommendation model called LC-Rec, which can better integrate language and collaborative semantics for recommender systems. Our approach can directly generate items from the entire item set for recommendation, without relying on candidate items. Specifically, we make two major contributions in our approach. For item indexing, we design a learning-based vector quantization method with uniform semantic mapping, which can assign meaningful and non-conflicting IDs (called item indices) for items. For alignment tuning, we propose a series of specially designed tuning tasks to enhance the integration of collaborative semantics in LLMs. Our fine-tuning tasks enforce LLMs to deeply integrate language and collaborative semantics (characterized by the learned item indices), so as to achieve an effective adaptation to recommender systems. Extensive experiments demonstrate the effectiveness of our method, showing that our approach can outperform a number of competitive baselines including traditional recommenders and existing LLM-based recommenders. Our code is available at https://github.com/RUCAIBox/LC-Rec/.
Spiking Neural Networks (SNNs) have garnered substantial attention in brain-like computing for their biological fidelity and the capacity to execute energy-efficient spike-driven operations. As the demand for heightened performance in SNNs surges, the trend towards training deeper networks becomes imperative, while residual learning stands as a pivotal method for training deep neural networks. In our investigation, we identified that the SEW-ResNet, a prominent representative of deep residual spiking neural networks, incorporates non-event-driven operations. To rectify this, we propose a novel training paradigm that first accumulates a large amount of redundant information through OR Residual Connection (ORRC), and then filters out the redundant information using the Synergistic Attention (SynA) module, which promotes feature extraction in the backbone while suppressing the influence of noise and useless features in the shortcuts. When integrating SynA into the network, we observed the phenomenon of "natural pruning", where after training, some or all of the shortcuts in the network naturally drop out without affecting the model's classification accuracy. This significantly reduces computational overhead and makes it more suitable for deployment on edge devices. Experimental results on various public datasets confirmed that the SynA-ResNet achieved single-sample classification with as little as 0.8 spikes per neuron. Moreover, when compared to other residual SNN models, it exhibited higher accuracy and up to a 28-fold reduction in energy consumption.
High computational overhead is a troublesome problem for diffusion models. Recent studies have leveraged post-training quantization (PTQ) to compress diffusion models. However, most of them only focus on unconditional models, leaving the quantization of widely-used pretrained text-to-image models, e.g., Stable Diffusion, largely unexplored. In this paper, we propose a novel post-training quantization method PCR (Progressive Calibration and Relaxing) for text-to-image diffusion models, which consists of a progressive calibration strategy that considers the accumulated quantization error across timesteps, and an activation relaxing strategy that improves the performance with negligible cost. Additionally, we demonstrate the previous metrics for text-to-image diffusion model quantization are not accurate due to the distribution gap. To tackle the problem, we propose a novel QDiffBench benchmark, which utilizes data in the same domain for more accurate evaluation. Besides, QDiffBench also considers the generalization performance of the quantized model outside the calibration dataset. Extensive experiments on Stable Diffusion and Stable Diffusion XL demonstrate the superiority of our method and benchmark. Moreover, we are the first to achieve quantization for Stable Diffusion XL while maintaining the performance.
Deep learning-based models are at the forefront of most driver observation benchmarks due to their remarkable accuracies but are also associated with high computational costs. This is challenging, as resources are often limited in real-world driving scenarios. This paper introduces a lightweight framework for resource-efficient driver activity recognition. The framework enhances 3D MobileNet, a neural architecture optimized for speed in video classification, by incorporating knowledge distillation and model quantization to balance model accuracy and computational efficiency. Knowledge distillation helps maintain accuracy while reducing the model size by leveraging soft labels from a larger teacher model (I3D), instead of relying solely on original ground truth data. Model quantization significantly lowers memory and computation demands by using lower precision integers for model weights and activations. Extensive testing on a public dataset for in-vehicle monitoring during autonomous driving demonstrates that this new framework achieves a threefold reduction in model size and a 1.4-fold improvement in inference time, compared to an already optimized architecture. The code for this study is available at https://github.com/calvintanama/qd-driver-activity-reco.
Large pre-trained sequence models, such as transformer-based architectures, have been recently shown to have the capacity to carry out in-context learning (ICL). In ICL, a decision on a new input is made via a direct mapping of the input and of a few examples from the given task, serving as the task's context, to the output variable. No explicit updates of the model parameters are needed to tailor the decision to a new task. Pre-training, which amounts to a form of meta-learning, is based on the observation of examples from several related tasks. Prior work has shown ICL capabilities for linear regression. In this study, we leverage ICL to address the inverse problem of multiple-input and multiple-output (MIMO) equalization based on a context given by pilot symbols. A task is defined by the unknown fading channel and by the signal-to-noise ratio (SNR) level, which may be known. To highlight the practical potential of the approach, we allow the presence of quantization of the received signals. We demonstrate via numerical results that transformer-based ICL has a threshold behavior, whereby, as the number of pre-training tasks grows, the performance switches from that of a minimum mean squared error (MMSE) equalizer with a prior determined by the pre-trained tasks to that of an MMSE equalizer with the true data-generating prior.
Inference optimizations are critical for improving user experience and reducing infrastructure costs and power consumption. In this article, we illustrate a form of dynamic execution known as speculative sampling to reduce the overall latency of text generation and compare it with standard autoregressive sampling. This can be used together with model-based optimizations (e.g. quantization) to provide an optimized solution. Both sampling methods make use of KV caching. A Jupyter notebook and some sample executions are provided.
Hashing is at the heart of large-scale image similarity search, and recent methods have been substantially improved through deep learning techniques. Such algorithms typically learn continuous embeddings of the data. To avoid a subsequent costly binarization step, a common solution is to employ loss functions that combine a similarity learning term (to ensure similar images are grouped to nearby embeddings) and a quantization penalty term (to ensure that the embedding entries are close to binarized entries, e.g., -1 or 1). Still, the interaction between these two terms can make learning harder and the embeddings worse. We propose an alternative quantization strategy that decomposes the learning problem in two stages: first, perform similarity learning over the embedding space with no quantization; second, find an optimal orthogonal transformation of the embeddings so each coordinate of the embedding is close to its sign, and then quantize the transformed embedding through the sign function. In the second step, we parametrize orthogonal transformations using Householder matrices to efficiently leverage stochastic gradient descent. Since similarity measures are usually invariant under orthogonal transformations, this quantization strategy comes at no cost in terms of performance. The resulting algorithm is unsupervised, fast, hyperparameter-free and can be run on top of any existing deep hashing or metric learning algorithm. We provide extensive experimental results showing that this approach leads to state-of-the-art performance on widely used image datasets, and, unlike other quantization strategies, brings consistent improvements in performance to existing deep hashing algorithms.
Large language models (LLMs) show great performance in various tasks, but face deployment challenges from limited memory capacity and bandwidth. Low-bit weight quantization can save memory and accelerate inference. Although floating-point (FP) formats show good performance in LLM quantization, they tend to perform poorly with small group sizes or sub-4 bits. We find the reason is that the absence of asymmetry in previous FP quantization makes it unsuitable for handling asymmetric value distribution of LLM weight tensors. In this work, we propose asymmetric FP quantization (AFPQ), which sets separate scales for positive and negative values. Our method leads to large accuracy improvements and can be easily plugged into other quantization methods, including GPTQ and AWQ, for better performance. Besides, no additional storage is needed compared with asymmetric integer (INT) quantization. The code is available at https://github.com/zhangsichengsjtu/AFPQ.
Large language models (LLMs) have demonstrated remarkable performance and tremendous potential across a wide range of tasks. However, deploying these models has been challenging due to the astronomical amount of model parameters, which requires a demand for large memory capacity and high memory bandwidth. In this paper, we propose an effective approach that can make the deployment of LLMs more efficiently. We support an automatic INT4 weight-only quantization flow and design a special LLM runtime with highly-optimized kernels to accelerate the LLM inference on CPUs. We demonstrate the general applicability of our approach on popular LLMs including Llama2, Llama, GPT-NeoX, and showcase the extreme inference efficiency on CPUs. The code is publicly available at: https://github.com/intel/intel-extension-for-transformers.
Recent advancements in unsupervised protein language models (ProteinLMs), like ESM-1b and ESM-2, have shown promise in different protein prediction tasks. However, these models face challenges due to their high computational demands, significant memory needs, and latency, restricting their usage on devices with limited resources. To tackle this, we explore post-training quantization (PTQ) for ProteinLMs, focusing on ESMFold, a simplified version of AlphaFold based on ESM-2 ProteinLM. Our study is the first attempt to quantize all weights and activations of ProteinLMs. We observed that the typical uniform quantization method performs poorly on ESMFold, causing a significant drop in TM-Score when using 8-bit quantization. We conducted extensive quantization experiments, uncovering unique challenges associated with ESMFold, particularly highly asymmetric activation ranges before Layer Normalization, making representation difficult using low-bit fixed-point formats. To address these challenges, we propose a new PTQ method for ProteinLMs, utilizing piecewise linear quantization for asymmetric activation values to ensure accurate approximation. We demonstrated the effectiveness of our method in protein structure prediction tasks, demonstrating that ESMFold can be accurately quantized to low-bit widths without compromising accuracy. Additionally, we applied our method to the contact prediction task, showcasing its versatility. In summary, our study introduces an innovative PTQ method for ProteinLMs, addressing specific quantization challenges and potentially leading to the development of more efficient ProteinLMs with significant implications for various protein-related applications.
This work addresses the need for efficient waste sorting strategies in Materials Recovery Facilities to minimize the environmental impact of rising waste. We propose resource-constrained semantic segmentation models for segmenting recyclable waste in industrial settings. Our goal is to develop models that fit within a 10MB memory constraint, suitable for edge applications with limited processing capacity. We perform the experiments on three networks: ICNet, BiSeNet (Xception39 backbone), and ENet. Given the aforementioned limitation, we implement quantization and pruning techniques on the broader nets, achieving positive results while marginally impacting the Mean IoU metric. Furthermore, we propose a combination of Focal and Lov\'asz loss that addresses the implicit class imbalance resulting in better performance compared with the Cross-entropy loss function.
The growing demand for Large Language Models (LLMs) in applications such as content generation, intelligent chatbots, and sentiment analysis poses considerable challenges for LLM service providers. To efficiently use GPU resources and boost throughput, batching multiple requests has emerged as a popular paradigm; to further speed up batching, LLM quantization techniques reduce memory consumption and increase computing capacity. However, prevalent quantization schemes (e.g., 8-bit weight-activation quantization) cannot fully leverage the capabilities of modern GPUs, such as 4-bit integer operators, resulting in sub-optimal performance. To maximize LLMs' serving throughput, we introduce Atom, a low-bit quantization method that achieves high throughput improvements with negligible accuracy loss. Atom significantly boosts serving throughput by using low-bit operators and considerably reduces memory consumption via low-bit quantization. It attains high accuracy by applying a novel mixed-precision and fine-grained quantization process. We evaluate Atom on 4-bit weight-activation quantization in the serving context. Atom improves end-to-end throughput (token/s) by up to $7.7\times$ compared to the FP16 and by $2.5\times$ compared to INT8 quantization, while maintaining the same latency target.
In this paper, we present an efficient solution for weed classification in agriculture. We focus on optimizing model performance at inference while respecting the constraints of the agricultural domain. We propose a Quantized Deep Neural Network model that classifies a dataset of 9 weed classes using 8-bit integer (int8) quantization, a departure from standard 32-bit floating point (fp32) models. Recognizing the hardware resource limitations in agriculture, our model balances model size, inference time, and accuracy, aligning with practical requirements. We evaluate the approach on ResNet-50 and InceptionV3 architectures, comparing their performance against their int8 quantized versions. Transfer learning and fine-tuning are applied using the DeepWeeds dataset. The results show staggering model size and inference time reductions while maintaining accuracy in real-world production scenarios like Desktop, Mobile and Raspberry Pi. Our work sheds light on a promising direction for efficient AI in agriculture, holding potential for broader applications. Code: https://github.com/parikshit14/QNN-for-weed