Qingyi Gu

Zhikai Li, Qingyi Gu

Vision Transformers (ViTs) have achieved state-of-the-art performance on various computer vision applications. However, these models have considerable storage and computational overheads, making their deployment and efficient inference on edge devices challenging. Quantization is a promising approach to reducing model complexity, and the dyadic arithmetic pipeline can allow the quantized models to perform efficient integer-only inference. Unfortunately, dyadic arithmetic is based on the homogeneity condition in convolutional neural networks, which is not applicable to the non-linear components in ViTs, making integer-only inference of ViTs an open issue. In this paper, we propose I-ViT, an integer-only quantization scheme for ViTs, to enable ViTs to perform the entire computational graph of inference with integer arithmetic and bit-shifting, and without any floating-point arithmetic. In I-ViT, linear operations (e.g., MatMul and Dense) follow the integer-only pipeline with dyadic arithmetic, and non-linear operations (e.g., Softmax, GELU, and LayerNorm) are approximated by the proposed light-weight integer-only arithmetic methods. More specifically, I-ViT applies the proposed Shiftmax and ShiftGELU, which are designed to use integer bit-shifting to approximate the corresponding floating-point operations. We evaluate I-ViT on various benchmark models and the results show that integer-only INT8 quantization achieves comparable (or even slightly higher) accuracy to the full-precision (FP) baseline. Furthermore, we utilize TVM for practical hardware deployment on the GPU's integer arithmetic units, achieving 3.72$\sim$4.11$\times$ inference speedup compared to the FP model. Code of both Pytorch and TVM is released at https://github.com/zkkli/I-ViT.

Zhikai Li, Junrui Xiao, Lianwei Yang et al.

Post-training quantization (PTQ), which only requires a tiny dataset for calibration without end-to-end retraining, is a light and practical model compression technique. Recently, several PTQ schemes for vision transformers (ViTs) have been presented; unfortunately, they typically suffer from non-trivial accuracy degradation, especially in low-bit cases. In this paper, we propose RepQ-ViT, a novel PTQ framework for ViTs based on quantization scale reparameterization, to address the above issues. RepQ-ViT decouples the quantization and inference processes, where the former employs complex quantizers and the latter employs scale-reparameterized simplified quantizers. This ensures both accurate quantization and efficient inference, which distinguishes it from existing approaches that sacrifice quantization performance to meet the target hardware. More specifically, we focus on two components with extreme distributions: post-LayerNorm activations with severe inter-channel variation and post-Softmax activations with power-law features, and initially apply channel-wise quantization and log$\sqrt{2}$ quantization, respectively. Then, we reparameterize the scales to hardware-friendly layer-wise quantization and log2 quantization for inference, with only slight accuracy or computational costs. Extensive experiments are conducted on multiple vision tasks with different model variants, proving that RepQ-ViT, without hyperparameters and expensive reconstruction procedures, can outperform existing strong baselines and encouragingly improve the accuracy of 4-bit PTQ of ViTs to a usable level. Code is available at https://github.com/zkkli/RepQ-ViT.

Zhikai Li, Liping Ma, Mengjuan Chen et al.

Vision transformers have recently gained great success on various computer vision tasks; nevertheless, their high model complexity makes it challenging to deploy on resource-constrained devices. Quantization is an effective approach to reduce model complexity, and data-free quantization, which can address data privacy and security concerns during model deployment, has received widespread interest. Unfortunately, all existing methods, such as BN regularization, were designed for convolutional neural networks and cannot be applied to vision transformers with significantly different model architectures. In this paper, we propose PSAQ-ViT, a Patch Similarity Aware data-free Quantization framework for Vision Transformers, to enable the generation of "realistic" samples based on the vision transformer's unique properties for calibrating the quantization parameters. Specifically, we analyze the self-attention module's properties and reveal a general difference (patch similarity) in its processing of Gaussian noise and real images. The above insights guide us to design a relative value metric to optimize the Gaussian noise to approximate the real images, which are then utilized to calibrate the quantization parameters. Extensive experiments and ablation studies are conducted on various benchmarks to validate the effectiveness of PSAQ-ViT, which can even outperform the real-data-driven methods. Code is available at: https://github.com/zkkli/PSAQ-ViT.

Zhikai Li, Mengjuan Chen, Junrui Xiao et al.

Data-free quantization can potentially address data privacy and security concerns in model compression, and thus has been widely investigated. Recently, PSAQ-ViT designs a relative value metric, patch similarity, to generate data from pre-trained vision transformers (ViTs), achieving the first attempt at data-free quantization for ViTs. In this paper, we propose PSAQ-ViT V2, a more accurate and general data-free quantization framework for ViTs, built on top of PSAQ-ViT. More specifically, following the patch similarity metric in PSAQ-ViT, we introduce an adaptive teacher-student strategy, which facilitates the constant cyclic evolution of the generated samples and the quantized model (student) in a competitive and interactive fashion under the supervision of the full-precision model (teacher), thus significantly improving the accuracy of the quantized model. Moreover, without the auxiliary category guidance, we employ the task- and model-independent prior information, making the general-purpose scheme compatible with a broad range of vision tasks and models. Extensive experiments are conducted on various models on image classification, object detection, and semantic segmentation tasks, and PSAQ-ViT V2, with the naive quantization strategy and without access to real-world data, consistently achieves competitive results, showing potential as a powerful baseline on data-free quantization for ViTs. For instance, with Swin-S as the (backbone) model, 8-bit quantization reaches 82.13 top-1 accuracy on ImageNet, 50.9 box AP and 44.1 mask AP on COCO, and 47.2 mIoU on ADE20K. We hope that accurate and general PSAQ-ViT V2 can serve as a potential and practice solution in real-world applications involving sensitive data. Code is released and merged at: https://github.com/zkkli/PSAQ-ViT.

Zhikai Li, Xiaoxuan Liu, Banghua Zhu et al. · berkeley

Large Language Models (LLMs) have showcased remarkable impacts across a wide spectrum of natural language processing tasks. Fine-tuning these pretrained models on downstream datasets provides further significant performance gains; however, this process typically requires a large number of expensive, high-end GPUs. Although there have been efforts focused on parameter-efficient fine-tuning, they cannot fully unlock the powerful potential of full-parameter fine-tuning. In this paper, we propose QFT, a Quantized Full-parameter Tuning framework for LLMs that quantizes and stores all training states, including weights, gradients, and optimizer states, in INT8 format to reduce training memory, thereby enabling full-parameter fine-tuning on existing GPUs at an affordable cost. To ensure training performance, we make two key efforts: i) for quantized gradients and optimizer states, we theoretically prove that the Lion optimizer, with its property of consistent update magnitudes, is highly robust to quantization; ii) and for quantized weights, we employ the hybrid feature quantizer, which identifies and protects a small subset of sparse critical features while quantizing the remaining dense features, thus ensuring accurate weight updates without FP32 backups. Moreover, to support backpropagation in the integer context, we develop a stack-based gradient flow scheme with O(1) complexity, forming a unified integer training pipeline. As a result, QFT reduces the model state memory to 21% of the standard solution while achieving comparable performance, e.g., tuning a LLaMA-7B model requires only <30GB of memory, making it feasible on a single A6000 GPU.

Zhikai Li, Xuewen Liu, Dongrong Joe Fu et al.

The rapid advancement of visual generative models necessitates efficient and reliable evaluation methods. Arena platform, which gathers user votes on model comparisons, can rank models with human preferences. However, traditional Arena methods, while established, require an excessive number of comparisons for ranking to converge and are vulnerable to preference noise in voting, suggesting the need for better approaches tailored to contemporary evaluation challenges. In this paper, we introduce K-Sort Arena, an efficient and reliable platform based on a key insight: images and videos possess higher perceptual intuitiveness than texts, enabling rapid evaluation of multiple samples simultaneously. Consequently, K-Sort Arena employs K-wise comparisons, allowing K models to engage in free-for-all competitions, which yield much richer information than pairwise comparisons. To enhance the robustness of the system, we leverage probabilistic modeling and Bayesian updating techniques. We propose an exploration-exploitation-based matchmaking strategy to facilitate more informative comparisons. In our experiments, K-Sort Arena exhibits 16.3x faster convergence compared to the widely used ELO algorithm. To further validate the superiority and obtain a comprehensive leaderboard, we collect human feedback via crowdsourced evaluations of numerous cutting-edge text-to-image and text-to-video models. Thanks to its high efficiency, K-Sort Arena can continuously incorporate emerging models and update the leaderboard with minimal votes. Our project has undergone several months of internal testing and is now available at https://huggingface.co/spaces/ksort/K-Sort-Arena

Xuewen Liu, Zhikai Li, Minhao Jiang et al.

Model quantization is a promising method for accelerating and compressing diffusion models. Nevertheless, since post-training quantization (PTQ) fails catastrophically at low-bit cases, quantization-aware training (QAT) is essential. Unfortunately, the wide range and time-varying activations in diffusion models sharply increase the complexity of quantization, making existing QAT methods inefficient. Equivalent scaling can effectively reduce activation range, but previous methods remain the overall quantization error unchanged. More critically, these methods significantly disrupt the original weight distribution, resulting in poor weight initialization and challenging convergence during QAT training. In this paper, we propose a novel QAT framework for diffusion models, called DilateQuant. Specifically, we propose Weight Dilation (WD) that maximally dilates the unsaturated in-channel weights to a constrained range through equivalent scaling. WD decreases the activation range while preserving the original weight range, which steadily reduces the quantization error and ensures model convergence. To further enhance accuracy and efficiency, we design a Temporal Parallel Quantizer (TPQ) to address the time-varying activations and introduce a Block-wise Knowledge Distillation (BKD) to reduce resource consumption in training. Extensive experiments demonstrate that DilateQuant significantly outperforms existing methods in terms of accuracy and efficiency. Code is available at http://github.com/BienLuky/DilateQuant .

Xuewen Liu, Zhikai Li, Jing Zhang et al.

AutoRegressive Visual Generation (ARVG) models retain an architecture compatible with language models, while achieving performance comparable to diffusion-based models. Quantization is commonly employed in neural networks to reduce model size and computational latency. However, applying quantization to ARVG remains largely underexplored, and existing quantization methods fail to generalize effectively to ARVG models. In this paper, we explore this issue and identify three key challenges: (1) severe outliers at channel-wise level, (2) highly dynamic activations at token-wise level, and (3) mismatched distribution information at sample-wise level. To these ends, we propose PTQ4ARVG, a training-free post-training quantization (PTQ) framework consisting of: (1) Gain-Projected Scaling (GPS) mitigates the channel-wise outliers, which expands the quantization loss via a Taylor series to quantify the gain of scaling for activation-weight quantization, and derives the optimal scaling factor through differentiation.(2) Static Token-Wise Quantization (STWQ) leverages the inherent properties of ARVG, fixed token length and position-invariant distribution across samples, to address token-wise variance without incurring dynamic calibration overhead.(3) Distribution-Guided Calibration (DGC) selects samples that contribute most to distributional entropy, eliminating the sample-wise distribution mismatch. Extensive experiments show that PTQ4ARVG can effectively quantize the ARVG family models to 8-bit and 6-bit while maintaining competitive performance. Code is available at http://github.com/BienLuky/PTQ4ARVG .

Zhikai Li, Zhen Dong, Xuewen Liu et al.

Large Language Models (LLMs) have demonstrated remarkable capabilities. However, their massive parameter scale leads to significant resource consumption and latency during inference. Post-training weight-only quantization offers a promising solution by reducing model size and accelerating token generation through alleviating the memory-bound issue. Nevertheless, the presence of inherent systematic outliers in weights continues to be a major obstacle. While existing methods, such as scaling and rotation, attempt to address this issue, the performance remains unsatisfactory. In this paper, we propose Outlier Self-Absorption Quantization (OSAQ), which performs additive weight suppression guided by the second-order low-rank property for low-bit weight-only quantization of LLMs. Specifically, we observe that the Hessian exhibits low-rank consistency across different inputs, with certain directions consistently showing vanishing curvature. Leveraging this property, we identify a stable null space of the Hessian and then construct an additive weight transformation by linearly combining the vectors within this null space, thereby suppressing weight outliers without affecting the task loss. This additive transformation can be absorbed into the weights offline, requiring no inter-layer transformations and introducing no inference overhead. Moreover, the construction is efficiently achieved by a closed-form solution, without resource-intensive training or iterative procedures. Extensive experiments demonstrate that OSAQ effectively suppresses outliers and enhances low-bit quantization performance. For instance, in 2-bit quantization, OSAQ, when integrated with GPTQ, achieves over 40% lower perplexity compared to vanilla GPTQ.

Zhihang Yuan, Yuzhang Shang, Yang Zhou et al.

The field of efficient Large Language Model (LLM) inference is rapidly evolving, presenting a unique blend of opportunities and challenges. Although the field has expanded and is vibrant, there hasn't been a concise framework that analyzes the various methods of LLM Inference to provide a clear understanding of this domain. Our survey stands out from traditional literature reviews by not only summarizing the current state of research but also by introducing a framework based on roofline model for systematic analysis of LLM inference techniques. This framework identifies the bottlenecks when deploying LLMs on hardware devices and provides a clear understanding of practical problems, such as why LLMs are memory-bound, how much memory and computation they need, and how to choose the right hardware. We systematically collate the latest advancements in efficient LLM inference, covering crucial areas such as model compression (e.g., Knowledge Distillation and Quantization), algorithm improvements (e.g., Early Exit and Mixture-of-Expert), and both hardware and system-level enhancements. Our survey stands out by analyzing these methods with roofline model, helping us understand their impact on memory access and computation. This distinctive approach not only showcases the current research landscape but also delivers valuable insights for practical implementation, positioning our work as an indispensable resource for researchers new to the field as well as for those seeking to deepen their understanding of efficient LLM deployment. The analyze tool, LLM-Viewer, is open-sourced.

Zhikai Li, Jiatong Li, Xuewen Liu et al.

The rapid development of visual generative models raises the need for more scalable and human-aligned evaluation methods. While the crowdsourced Arena platforms offer human preference assessments by collecting human votes, they are costly and time-consuming, inherently limiting their scalability. Leveraging vision-language model (VLMs) as substitutes for manual judgments presents a promising solution. However, the inherent hallucinations and biases of VLMs hinder alignment with human preferences, thus compromising evaluation reliability. Additionally, the static evaluation approach lead to low efficiency. In this paper, we propose K-Sort Eval, a reliable and efficient VLM-based evaluation framework that integrates posterior correction and dynamic matching. Specifically, we curate a high-quality dataset from thousands of human votes in K-Sort Arena, with each instance containing the outputs and rankings of K models. When evaluating a new model, it undergoes (K+1)-wise free-for-all comparisons with existing models, and the VLM provide the rankings. To enhance alignment and reliability, we propose a posterior correction method, which adaptively corrects the posterior probability in Bayesian updating based on the consistency between the VLM prediction and human supervision. Moreover, we propose a dynamic matching strategy, which balances uncertainty and diversity to maximize the expected benefit of each comparison, thus ensuring more efficient evaluation. Extensive experiments show that K-Sort Eval delivers evaluation results consistent with K-Sort Arena, typically requiring fewer than 90 model runs, demonstrating both its efficiency and reliability.

Lianwei Yang, Haisong Gong, Haokun Lin et al.

Vision Transformers (ViTs) have gained significant attention, but their high computing cost limits the practical applications. While post-training quantization (PTQ) reduces model size and speeds up inference, it often degrades performance, especially in low-bit settings. We identify two key reasons for the performance degradation: 1) existing quantization methods fail to align with the power-law distribution of post-Softmax activations, and 2) reparameterizing post-LayerNorm activations leads to a performance drop due to the significant influence of outliers in the scaling factors. To address these challenges, we propose DopQ-ViT, a Distribution-friendly and Outlier-aware Post-training Quantization method for ViTs. First, DopQ-ViT introduces the Tan Quantizer (TanQ), which better preserves the power-law distribution of post-Softmax activations by focusing more on values near 1. Second, DopQ-ViT presents the MAD-guided Optimal Scaling Factor (MOSF), which selects the optimal scaling factor without introducing additional calculations. Extensive experiments across various ViT models and quantization settings demonstrate that DopQ-ViT, with the help of TanQ and MOSF, outperforms previous PTQ methods on both classification and detection tasks.

Zhikai Li, Jing Zhang, Qingyi Gu

The disparity in healthcare personnel expertise and medical resources across different regions of the world is a pressing social issue. Artificial intelligence technology offers new opportunities to alleviate this issue. Segment Anything Model (SAM), which excels in intelligent image segmentation, has demonstrated exceptional performance in medical monitoring and assisted diagnosis. Unfortunately, the huge computational and storage overhead of SAM poses significant challenges for deployment on resource-limited edge devices. Quantization is an effective solution for model compression; however, traditional methods rely heavily on original data for calibration, which raises widespread concerns about medical data privacy and security. In this paper, we propose a data-free quantization framework for SAM, called DFQ-SAM, which learns and calibrates quantization parameters without any original data, thus effectively preserving data privacy during model compression. Specifically, we propose pseudo-positive label evolution for segmentation, combined with patch similarity, to fully leverage the semantic and distribution priors in pre-trained models, which facilitates high-quality data synthesis as a substitute for real data. Furthermore, we introduce scale reparameterization to ensure the accuracy of low-bit quantization. We perform extensive segmentation experiments on various datasets, and DFQ-SAM consistently provides significant performance on low-bit quantization. DFQ-SAM eliminates the need for data transfer in cloud-edge collaboration, thereby protecting sensitive data from potential attacks. It enables secure, fast, and personalized healthcare services at the edge, which enhances system efficiency and optimizes resource allocation, and thus facilitating the pervasive application of artificial intelligence in worldwide healthcare.

Xuewen Liu, Zhikai Li, Junrui Xiao et al.

Diffusion models have achieved great success in image generation tasks. However, the lengthy denoising process and complex neural networks hinder their low-latency applications in real-world scenarios. Quantization can effectively reduce model complexity, and post-training quantization (PTQ), which does not require fine-tuning, is highly promising for compressing and accelerating diffusion models. Unfortunately, we find that due to the highly dynamic activations, existing PTQ methods suffer from distribution mismatch issues at both calibration sample level and reconstruction output level, which makes the performance far from satisfactory. In this paper, we propose EDA-DM, a standardized PTQ method that efficiently addresses the above issues. Specifically, at the calibration sample level, we extract information from the density and diversity of latent space feature maps, which guides the selection of calibration samples to align with the overall sample distribution; and at the reconstruction output level, we theoretically analyze the reasons for previous reconstruction failures and, based on this insight, optimize block reconstruction using the Hessian loss of layers, aligning the outputs of quantized model and full-precision model at different network granularity. Extensive experiments demonstrate that EDA-DM significantly outperforms the existing PTQ methods across various models and datasets. Our method achieves a 1.83 times speedup and 4 times compression for the popular Stable-Diffusion on MS-COCO, with only a 0.05 loss in CLIP score. Code is available at http://github.com/BienLuky/EDA-DM .

Jing Zhang, Zhikai Li, Xuewen Liu et al.

Segment Anything Model 2 (SAM2) shows excellent performance in video object segmentation tasks; however, the heavy computational burden hinders its application in real-time video processing. Although there have been efforts to improve the efficiency of SAM2, most of them focus on retraining a lightweight backbone, with little exploration into post-training acceleration. In this paper, we observe that SAM2 exhibits sparse perception pattern as biological vision, which provides opportunities for eliminating redundant computation and acceleration: i) In mask decoder, the attention primarily focuses on the foreground objects, whereas the image encoder in the earlier stage exhibits a broad attention span, which results in unnecessary computation to background regions. ii) In memory bank, only a small subset of tokens in each frame contribute significantly to memory attention, and the salient regions exhibit temporal consistency, making full-token computation redundant. With these insights, we propose Efficient-SAM2, which promotes SAM2 to adaptively focus on object regions while eliminating task-irrelevant computations, thereby significantly improving inference efficiency. Specifically, for image encoder, we propose object-aware Sparse Window Routing (SWR), a window-level computation allocation mechanism that leverages the consistency and saliency cues from the previous-frame decoder to route background regions into a lightweight shortcut branch. Moreover, for memory attention, we propose object-aware Sparse Memory Retrieval (SMR), which allows only the salient memory tokens in each frame to participate in computation, with the saliency pattern reused from their first recollection. With negligible additional parameters and minimal training overhead, Efficient-SAM2 delivers 1.68x speedup on SAM2.1-L model with only 1.0% accuracy drop on SA-V test set.

Minhao Jiang, Zhikai Li, Xuewen Liu et al.

Large language models have demonstrated capabilities in text generation, while their increasing parameter scales present challenges in computational and memory efficiency. Post-training sparsity (PTS), which reduces model cost by removing weights from dense networks, is an effective approach. However, native dense matrices lack high sparsity, making existing approaches that directly remove weights disrupt model states, resulting in unsatisfactory performance recovery even with post-tuning. We propose Sparsity Induction, which promotes models toward higher sparsity at both distribution and feature levels before pruning, to push the limits of PTS. At the distribution level, we enhance distributional sparsity through mathematically equivalent scaling transformations, which are fully absorbable and incur no extra parameters or inference-time overhead. At the feature level, we introduce Spectral Norm Loss to promote feature sparsity from a low-rank perspective. Experiments across diverse model architectures and tasks demonstrate that our method further enhances sparsity-friendliness, achieving superior pruning performance over existing approaches.

Xuewen Liu, Zhikai Li, Qingyi Gu

Diffusion models have gradually gained prominence in the field of image synthesis, showcasing remarkable generative capabilities. Nevertheless, the slow inference and complex networks, resulting from redundancy at both temporal and structural levels, hinder their low-latency applications in real-world scenarios. Current acceleration methods for diffusion models focus separately on temporal and structural levels. However, independent optimization at each level to further push the acceleration limits results in significant performance degradation. On the other hand, integrating optimizations at both levels can compound the acceleration effects. Unfortunately, we find that the optimizations at these two levels are not entirely orthogonal. Performing separate optimizations and then simply integrating them results in unsatisfactory performance. To tackle this issue, we propose CacheQuant, a novel training-free paradigm that comprehensively accelerates diffusion models by jointly optimizing model caching and quantization techniques. Specifically, we employ a dynamic programming approach to determine the optimal cache schedule, in which the properties of caching and quantization are carefully considered to minimize errors. Additionally, we propose decoupled error correction to further mitigate the coupled and accumulated errors step by step. Experimental results show that CacheQuant achieves a 5.18 speedup and 4 compression for Stable Diffusion on MS-COCO, with only a 0.02 loss in CLIP score. Our code are open-sourced: https://github.com/BienLuky/CacheQuant .

Xuewen Liu, Zhikai Li, Jing Zhang et al.

Diffusion Transformers dominate video generation, but the quadratic complexity of attention computation introduces substantial latency. Attention sparsity reduces computational costs by focusing on critical tokens while ignoring non-critical tokens. However, existing methods suffer from severe performance degradation. In this paper, we revisit attention sparsity and reveal that existing methods induce systematic biases in attention allocation: (1) excessive focus on critical tokens amplifies their attention weights; (2) complete neglect of non-critical tokens causes the loss of relevant attention weights. To address these issues, we propose Rectified SpaAttn, which rectifies attention allocation with implicit full attention reference, thereby enhancing the alignment between sparse and full attention maps. Specifically: (1) for critical tokens, we show that their bias is proportional to the sparse attention weights, with the ratio governed by the amplified weights. Accordingly, we propose Isolated-Pooling Attention Reallocation, which calculates accurate rectification factors by reallocating multimodal pooled weights. (2) for non-critical tokens, recovering attention weights from the pooled query-key yields attention gains but also introduces pooling errors. Therefore, we propose Gain-Aware Pooling Rectification, which ensures that the rectified gain consistently surpasses the induced error. Moreover, we customize and integrate the Rectified SpaAttn kernel using Triton, achieving up to 3.33 and 2.08 times speedups on HunyuanVideo and Wan 2.1, respectively, while maintaining high generation quality. We release Rectified SpaAttn as open-source at https://github.com/BienLuky/Rectified-SpaAttn .

Xianlei Long, Xiaxin Zhu, Fangming Guo et al.

Event-based semantic segmentation has great potential in autonomous driving and robotics due to the advantages of event cameras, such as high dynamic range, low latency, and low power cost. Unfortunately, current artificial neural network (ANN)-based segmentation methods suffer from high computational demands, the requirements for image frames, and massive energy consumption, limiting their efficiency and application on resource-constrained edge/mobile platforms. To address these problems, we introduce SLTNet, a spike-driven lightweight transformer-based network designed for event-based semantic segmentation. Specifically, SLTNet is built on efficient spike-driven convolution blocks (SCBs) to extract rich semantic features while reducing the model's parameters. Then, to enhance the long-range contextural feature interaction, we propose novel spike-driven transformer blocks (STBs) with binary mask operations. Based on these basic blocks, SLTNet employs a high-efficiency single-branch architecture while maintaining the low energy consumption of the Spiking Neural Network (SNN). Finally, extensive experiments on DDD17 and DSEC-Semantic datasets demonstrate that SLTNet outperforms state-of-the-art (SOTA) SNN-based methods by at most 9.06% and 9.39% mIoU, respectively, with extremely 4.58x lower energy consumption and 114 FPS inference speed. Our code is open-sourced and available at https://github.com/longxianlei/SLTNet-v1.0.

Fuqiang Gu, Yuanke Li, Xianlei Long et al.

Semantic segmentation is a fundamental task in computer vision with wide-ranging applications, including autonomous driving and robotics. While RGB-based methods have achieved strong performance with CNNs and Transformers, their effectiveness degrades under fast motion, low-light, or high dynamic range conditions due to limitations of frame cameras. Event cameras offer complementary advantages such as high temporal resolution and low latency, yet lack color and texture, making them insufficient on their own. To address this, recent research has explored multimodal fusion of RGB and event data; however, many existing approaches are computationally expensive and focus primarily on spatial fusion, neglecting the temporal dynamics inherent in event streams. In this work, we propose MambaSeg, a novel dual-branch semantic segmentation framework that employs parallel Mamba encoders to efficiently model RGB images and event streams. To reduce cross-modal ambiguity, we introduce the Dual-Dimensional Interaction Module (DDIM), comprising a Cross-Spatial Interaction Module (CSIM) and a Cross-Temporal Interaction Module (CTIM), which jointly perform fine-grained fusion along both spatial and temporal dimensions. This design improves cross-modal alignment, reduces ambiguity, and leverages the complementary properties of each modality. Extensive experiments on the DDD17 and DSEC datasets demonstrate that MambaSeg achieves state-of-the-art segmentation performance while significantly reducing computational cost, showcasing its promise for efficient, scalable, and robust multimodal perception.

Zhikai Li, Yue Zhao, Edward Zhongwei Zhang et al.

Reinforcement learning from human feedback (RLHF) effectively promotes preference alignment of text-to-image (T2I) diffusion models. To improve computational efficiency, direct preference optimization (DPO), which avoids explicit reward modeling, has been widely studied. However, its reliance on binary feedback limits it to coarse-grained modeling on chosen-rejected pairs, resulting in suboptimal optimization. In this paper, we propose ArenaPO, which leverages Arena scores as offline rewards to provide refined feedback, thus achieving efficient and fine-grained optimization without a reward model. This enables ArenaPO to benefit from both the rich rewards of traditional RLHF and the efficiency of DPO. Specifically, we first construct a model Arena in which each model's capability is represented as a Gaussian distribution, and infer these capabilities by traversing the annotated pairwise preferences. Each output image is treated as a sample from the corresponding capability distribution. Then, for a image pair, conditioned on the two capability distributions and the observed pairwise preference, the absolute quality gap is estimated using latent-variable inference based on truncated normal distribution, which serves as fine-grained feedback during training. It does not require a reward model and can be computed offline, thus introducing no additional training overhead. We conduct ArenaPO training on Pick-a-Pic v2 and HPD v3 datasets, showing that ArenaPO consistently outperforms existing baselines.

Zhikai Li, Xuewen Liu, Jing Zhang et al.

Large transformer models have demonstrated remarkable success. Post-training quantization (PTQ), which requires only a small dataset for calibration and avoids end-to-end retraining, is a promising solution for compressing these large models. Regrettably, existing PTQ methods typically exhibit non-trivial performance loss. We find that the performance bottleneck stems from over-consideration of hardware compatibility in the quantization process, compelling them to reluctantly employ simple quantizers, albeit at the expense of accuracy. With the above insights, we propose RepQuant, a novel PTQ framework with quantization-inference decoupling paradigm to address the above issues. RepQuant employs complex quantizers in the quantization process and simplified quantizers in the inference process, and performs mathematically equivalent transformations between the two through quantization scale reparameterization, thus ensuring both accurate quantization and efficient inference. More specifically, we focus on two components with extreme distributions: LayerNorm activations and Softmax activations. Initially, we apply channel-wise quantization and log$\sqrt{2}$ quantization, respectively, which are tailored to their distributions. In particular, for the former, we introduce a learnable per-channel dual clipping scheme, which is designed to efficiently identify outliers in the unbalanced activations with fine granularity. Then, we reparameterize the scales to hardware-friendly layer-wise quantization and log2 quantization for inference. Moreover, quantized weight reconstruction is seamlessly integrated into the above procedure to further push the performance limits. Extensive experiments are performed on different large-scale transformer variants on multiple tasks, including vision, language, and multi-modal transformers, and RepQuant encouragingly demonstrates significant performance advantages.

Xianlei Long, Hui Zhao, Chao Chen et al.

In recent years, wide-area visual surveillance systems have been widely applied in various industrial and transportation scenarios. These systems, however, face significant challenges when implementing multi-object detection due to conflicts arising from the need for high-resolution imaging, efficient object searching, and accurate localization. To address these challenges, this paper presents a hybrid system that incorporates a wide-angle camera, a high-speed search camera, and a galvano-mirror. In this system, the wide-angle camera offers panoramic images as prior information, which helps the search camera capture detailed images of the targeted objects. This integrated approach enhances the overall efficiency and effectiveness of wide-area visual detection systems. Specifically, in this study, we introduce a wide-angle camera-based method to generate a panoramic probability map (PPM) for estimating high-probability regions of target object presence. Then, we propose a probability searching module that uses the PPM-generated prior information to dynamically adjust the sampling range and refine target coordinates based on uncertainty variance computed by the object detector. Finally, the integration of PPM and the probability searching module yields an efficient hybrid vision system capable of achieving 120 fps multi-object search and detection. Extensive experiments are conducted to verify the system's effectiveness and robustness.

Junrui Xiao, Zhikai Li, Lianwei Yang et al.

Post-training quantization (PTQ) reduces excessive hardware cost by quantizing full-precision models into lower bit representations on a tiny calibration set, without retraining. Despite the remarkable progress made through recent efforts, traditional PTQ methods typically encounter failure in dynamic and ever-changing real-world scenarios, involving unpredictable data streams and continual domain shifts, which poses greater challenges. In this paper, we propose a novel and stable quantization process for test-time adaptation (TTA), dubbed TTAQ, to address the performance degradation of traditional PTQ in dynamically evolving test domains. To tackle domain shifts in quantizer, TTAQ proposes the Perturbation Error Mitigation (PEM) and Perturbation Consistency Reconstruction (PCR). Specifically, PEM analyzes the error propagation and devises a weight regularization scheme to mitigate the impact of input perturbations. On the other hand, PCR introduces consistency learning to ensure that quantized models provide stable predictions for same sample. Furthermore, we introduce Adaptive Balanced Loss (ABL) to adjust the logits by taking advantage of the frequency and complexity of the class, which can effectively address the class imbalance caused by unpredictable data streams during optimization. Extensive experiments are conducted on multiple datasets with generic TTA methods, proving that TTAQ can outperform existing baselines and encouragingly improve the accuracy of low bit PTQ models in continually changing test domains. For instance, TTAQ decreases the mean error of 2-bit models on ImageNet-C dataset by an impressive 10.1\%.

Lianwei Yang, Haokun Lin, Tianchen Zhao et al. · tsinghua

Diffusion Transformers (DiTs) have achieved impressive performance in text-to-image and text-to-video generation. However, their high computational cost and large parameter sizes pose significant challenges for usage in resource-constrained scenarios. Effective compression of models has become a crucial issue that urgently needs to be addressed. Post-training quantization (PTQ) is a promising solution to reduce memory usage and accelerate inference, but existing PTQ methods suffer from severe performance degradation under extreme low-bit settings. After experiments and analysis, we identify two key obstacles to low-bit PTQ for DiTs: (1) the weights of DiT models follow a Gaussian-like distribution with long tails, causing uniform quantization to poorly allocate intervals and leading to significant quantization errors. This issue has been observed in the linear layer weights of different DiT models, which deeply limits the performance. (2) two types of activation outliers in DiT models: (i) Mild Outliers with slightly elevated values, and (ii) Salient Outliers with large magnitudes concentrated in specific channels, which disrupt activation quantization. To address these issues, we propose LRQ-DiT, an efficient and accurate post-training quantization framework for image and video generation. First, we introduce Twin-Log Quantization (TLQ), a log-based method that allocates more quantization intervals to the intermediate dense regions, effectively achieving alignment with the weight distribution and reducing quantization errors. Second, we propose an Adaptive Rotation Scheme (ARS) that dynamically applies Hadamard or outlier-aware rotations based on activation fluctuation, effectively mitigating the impact of both types of outliers. Extensive experiments on various text-to-image and text-to-video DiT models demonstrate that LRQ-DiT preserves high generation quality.

Jing Zhang, Zhikai Li, Chengzhi Hu et al.

Segment Anything Model (SAM) exhibits remarkable zero-shot segmentation capability; however, its prohibitive computational costs make edge deployment challenging. Although post-training quantization (PTQ) offers a promising compression solution, existing methods yield unsatisfactory results when applied to SAM, owing to its specialized model components and promptable workflow: (i) The mask decoder's attention exhibits extreme activation outliers, and we find that aggressive clipping (even 100x), without smoothing or isolation, is effective in suppressing outliers while maintaining performance. Unfortunately, traditional distribution-based metrics (e.g., MSE) fail to provide such large-scale clipping. (ii) Existing quantization reconstruction methods neglect semantic interactivity of SAM, leading to misalignment between image feature and prompt intention. To address the above issues, we propose SAQ-SAM in this paper, which boosts PTQ for SAM from the perspective of semantic alignment. Specifically, we propose Perceptual-Consistency Clipping, which exploits attention focus overlap to promote aggressive clipping while preserving semantic capabilities. Furthermore, we propose Prompt-Aware Reconstruction, which incorporates image-prompt interactions by leveraging cross-attention in mask decoder, thus facilitating alignment in both distribution and semantic. Moreover, to ensure the interaction efficiency, we design a layer-skipping strategy for image tokens in encoder. Extensive experiments are conducted on various SAM sizes and tasks, including instance segmentation, oriented object detection, and semantic segmentation, and the results show that our method consistently exhibits advantages. For example, when quantizing SAM-B to 4-bit, SAQ-SAM achieves 11.7% higher mAP than the baseline in instance segmentation task.

Lianwei Yang, Zhikai Li, Junrui Xiao et al.

Post-training quantization (PTQ) efficiently compresses vision models, but unfortunately, it accompanies a certain degree of accuracy degradation. Reconstruction methods aim to enhance model performance by narrowing the gap between the quantized model and the full-precision model, often yielding promising results. However, efforts to significantly improve the performance of PTQ through reconstruction in the Vision Transformer (ViT) have shown limited efficacy. In this paper, we conduct a thorough analysis of the reasons for this limited effectiveness and propose MGRQ (Mixed Granularity Reconstruction Quantization) as a solution to address this issue. Unlike previous reconstruction schemes, MGRQ introduces a mixed granularity reconstruction approach. Specifically, MGRQ enhances the performance of PTQ by introducing Extra-Block Global Supervision and Intra-Block Local Supervision, building upon Optimized Block-wise Reconstruction. Extra-Block Global Supervision considers the relationship between block outputs and the model's output, aiding block-wise reconstruction through global supervision. Meanwhile, Intra-Block Local Supervision reduces generalization errors by aligning the distribution of outputs at each layer within a block. Subsequently, MGRQ is further optimized for reconstruction through Mixed Granularity Loss Fusion. Extensive experiments conducted on various ViT models illustrate the effectiveness of MGRQ. Notably, MGRQ demonstrates robust performance in low-bit quantization, thereby enhancing the practicality of the quantized model.

Junrui Xiao, Zhikai Li, Lianwei Yang et al.

Vision Transformers (ViTs) have emerged as the fundamental architecture for most computer vision fields, but the considerable memory and computation costs hinders their application on resource-limited devices. As one of the most powerful compression methods, binarization reduces the computation of the neural network by quantizing the weights and activation values as $\pm$1. Although existing binarization methods have demonstrated excellent performance on Convolutional Neural Networks (CNNs), the full binarization of ViTs is still under-studied and suffering a significant performance drop. In this paper, we first argue empirically that the severe performance degradation is mainly caused by the weight oscillation in the binarization training and the information distortion in the activation of ViTs. Based on these analyses, we propose $\textbf{BinaryViT}$, an accurate full binarization scheme for ViTs, which pushes the quantization of ViTs to the limit. Specifically, we propose a novel gradient regularization scheme (GRS) for driving a bimodal distribution of the weights to reduce oscillation in binarization training. Moreover, we design an activation shift module (ASM) to adaptively tune the activation distribution to reduce the information distortion caused by binarization. Extensive experiments on ImageNet dataset show that our BinaryViT consistently surpasses the strong baseline by 2.05% and improve the accuracy of fully binarized ViTs to a usable level. Furthermore, our method achieves impressive savings of 16.2$\times$ and 17.7$\times$ in model size and OPs compared to the full-precision DeiT-S.

Junrui Xiao, Zhikai Li, Lianwei Yang et al.

As emerging hardware begins to support mixed bit-width arithmetic computation, mixed-precision quantization is widely used to reduce the complexity of neural networks. However, Vision Transformers (ViTs) require complex self-attention computation to guarantee the learning of powerful feature representations, which makes mixed-precision quantization of ViTs still challenging. In this paper, we propose a novel patch-wise mixed-precision quantization (PMQ) for efficient inference of ViTs. Specifically, we design a lightweight global metric, which is faster than existing methods, to measure the sensitivity of each component in ViTs to quantization errors. Moreover, we also introduce a pareto frontier approach to automatically allocate the optimal bit-precision according to the sensitivity. To further reduce the computational complexity of self-attention in inference stage, we propose a patch-wise module to reallocate bit-width of patches in each layer. Extensive experiments on the ImageNet dataset shows that our method greatly reduces the search cost and facilitates the application of mixed-precision quantization to ViTs.

Yiming Hu, Yuding Liang, Zichao Guo et al.

In this work, we present a simple and general search space shrinking method, called Angle-Based search space Shrinking (ABS), for Neural Architecture Search (NAS). Our approach progressively simplifies the original search space by dropping unpromising candidates, thus can reduce difficulties for existing NAS methods to find superior architectures. In particular, we propose an angle-based metric to guide the shrinking process. We provide comprehensive evidences showing that, in weight-sharing supernet, the proposed metric is more stable and accurate than accuracy-based and magnitude-based metrics to predict the capability of child models. We also show that the angle-based metric can converge fast while training supernet, enabling us to get promising shrunk search spaces efficiently. ABS can easily apply to most of NAS approaches (e.g. SPOS, FairNAS, ProxylessNAS, DARTS and PDARTS). Comprehensive experiments show that ABS can dramatically enhance existing NAS approaches by providing a promising shrunk search space.

Yiming Hu, Jianquan Li, Xianlei Long et al.

Deep neural networks (DNNs) have achieved great success in a wide range of computer vision areas, but the applications to mobile devices is limited due to their high storage and computational cost. Much efforts have been devoted to compress DNNs. In this paper, we propose a simple yet effective method for deep networks compression, named Cluster Regularized Quantization (CRQ), which can reduce the presentation precision of a full-precision model to ternary values without significant accuracy drop. In particular, the proposed method aims at reducing the quantization error by introducing a cluster regularization term, which is imposed on the full-precision weights to enable them naturally concentrate around the target values. Through explicitly regularizing the weights during the re-training stage, the full-precision model can achieve the smooth transition to the low-bit one. Comprehensive experiments on benchmark datasets demonstrate the effectiveness of the proposed method.

Yiming Hu, Siyang Sun, Jianquan Li et al.

Channel pruning, which seeks to reduce the model size by removing redundant channels, is a popular solution for deep networks compression. Existing channel pruning methods usually conduct layer-wise channel selection by directly minimizing the reconstruction error of feature maps between the baseline model and the pruned one. However, they ignore the feature and semantic distributions within feature maps and real contribution of channels to the overall performance. In this paper, we propose a new channel pruning method by explicitly using both intermediate outputs of the baseline model and the classification loss of the pruned model to supervise layer-wise channel selection. Particularly, we introduce an additional loss to encode the differences in the feature and semantic distributions within feature maps between the baseline model and the pruned one. By considering the reconstruction error, the additional loss and the classification loss at the same time, our approach can significantly improve the performance of the pruned model. Comprehensive experiments on benchmark datasets demonstrate the effectiveness of the proposed method.

Yiming Hu, Siyang Sun, Jianquan Li et al.

In recent years, deep neural networks have achieved great success in the field of computer vision. However, it is still a big challenge to deploy these deep models on resource-constrained embedded devices such as mobile robots, smart phones and so on. Therefore, network compression for such platforms is a reasonable solution to reduce memory consumption and computation complexity. In this paper, a novel channel pruning method based on genetic algorithm is proposed to compress very deep Convolution Neural Networks (CNNs). Firstly, a pre-trained CNN model is pruned layer by layer according to the sensitivity of each layer. After that, the pruned model is fine-tuned based on knowledge distillation framework. These two improvements significantly decrease the model redundancy with less accuracy drop. Channel selection is a combinatorial optimization problem that has exponential solution space. In order to accelerate the selection process, the proposed method formulates it as a search problem, which can be solved efficiently by genetic algorithm. Meanwhile, a two-step approximation fitness function is designed to further improve the efficiency of genetic process. The proposed method has been verified on three benchmark datasets with two popular CNN models: VGGNet and ResNet. On the CIFAR-100 and ImageNet datasets, our approach outperforms several state-of-the-art methods. On the CIFAR-10 and SVHN datasets, the pruned VGGNet achieves better performance than the original model with 8 times parameters compression and 3 times FLOPs reduction.