Yuan Meng

Ye Li, Chen Tang, Yuan Meng et al.

We introduce PRANCE, a Vision Transformer compression framework that jointly optimizes the activated channels and reduces tokens, based on the characteristics of inputs. Specifically, PRANCE~ leverages adaptive token optimization strategies for a certain computational budget, aiming to accelerate ViTs' inference from a unified data and architectural perspective. However, the joint framework poses challenges to both architectural and decision-making aspects. Firstly, while ViTs inherently support variable-token inference, they do not facilitate dynamic computations for variable channels. To overcome this limitation, we propose a meta-network using weight-sharing techniques to support arbitrary channels of the Multi-head Self-Attention and Multi-layer Perceptron layers, serving as a foundational model for architectural decision-making. Second, simultaneously optimizing the structure of the meta-network and input data constitutes a combinatorial optimization problem with an extremely large decision space, reaching up to around $10^{14}$, making supervised learning infeasible. To this end, we design a lightweight selector employing Proximal Policy Optimization for efficient decision-making. Furthermore, we introduce a novel "Result-to-Go" training mechanism that models ViTs' inference process as a Markov decision process, significantly reducing action space and mitigating delayed-reward issues during training. Extensive experiments demonstrate the effectiveness of PRANCE~ in reducing FLOPs by approximately 50\%, retaining only about 10\% of tokens while achieving lossless Top-1 accuracy. Additionally, our framework is shown to be compatible with various token optimization techniques such as pruning, merging, and sequential pruning-merging strategies. The code is available at \href{https://github.com/ChildTang/PRANCE}{https://github.com/ChildTang/PRANCE}.

Chen Tang, Yuan Meng, Jiacheng Jiang et al.

Quantization is of significance for compressing the over-parameterized deep neural models and deploying them on resource-limited devices. Fixed-precision quantization suffers from performance drop due to the limited numerical representation ability. Conversely, mixed-precision quantization (MPQ) is advocated to compress the model effectively by allocating heterogeneous bit-width for layers. MPQ is typically organized into a searching-retraining two-stage process. In this paper, we devise a one-shot training-searching paradigm for mixed-precision model compression. Specifically, in the first stage, all potential bit-width configurations are coupled and thus optimized simultaneously within a set of shared weights. However, our observations reveal a previously unseen and severe bit-width interference phenomenon among highly coupled weights during optimization, leading to considerable performance degradation under a high compression ratio. To tackle this problem, we first design a bit-width scheduler to dynamically freeze the most turbulent bit-width of layers during training, to ensure the rest bit-widths converged properly. Then, taking inspiration from information theory, we present an information distortion mitigation technique to align the behavior of the bad-performing bit-widths to the well-performing ones. In the second stage, an inference-only greedy search scheme is devised to evaluate the goodness of configurations without introducing any additional training costs. Extensive experiments on three representative models and three datasets demonstrate the effectiveness of the proposed method. Code can be available on \href{https://www.github.com/1hunters/retraining-free-quantization}{https://github.com/1hunters/retraining-free-quantization}.

Lei Chen, Yuan Meng, Chen Tang et al.

Recent advancements in diffusion models, particularly the architectural transformation from UNet-based models to Diffusion Transformers (DiTs), significantly improve the quality and scalability of image and video generation. However, despite their impressive capabilities, the substantial computational costs of these large-scale models pose significant challenges for real-world deployment. Post-Training Quantization (PTQ) emerges as a promising solution, enabling model compression and accelerated inference for pretrained models, without the costly retraining. However, research on DiT quantization remains sparse, and existing PTQ frameworks, primarily designed for traditional diffusion models, tend to suffer from biased quantization, leading to notable performance degradation. In this work, we identify that DiTs typically exhibit significant spatial variance in both weights and activations, along with temporal variance in activations. To address these issues, we propose Q-DiT, a novel approach that seamlessly integrates two key techniques: automatic quantization granularity allocation to handle the significant variance of weights and activations across input channels, and sample-wise dynamic activation quantization to adaptively capture activation changes across both timesteps and samples. Extensive experiments conducted on ImageNet and VBench demonstrate the effectiveness of the proposed Q-DiT. Specifically, when quantizing DiT-XL/2 to W6A8 on ImageNet ($256 \times 256$), Q-DiT achieves a remarkable reduction in FID by 1.09 compared to the baseline. Under the more challenging W4A8 setting, it maintains high fidelity in image and video generation, establishing a new benchmark for efficient, high-quality quantization in DiTs. Code is available at \href{https://github.com/Juanerx/Q-DiT}{https://github.com/Juanerx/Q-DiT}.

Qun Li, Yuan Meng, Chen Tang et al.

Quantization is a promising technique for reducing the bit-width of deep models to improve their runtime performance and storage efficiency, and thus becomes a fundamental step for deployment. In real-world scenarios, quantized models are often faced with adversarial attacks which cause the model to make incorrect inferences by introducing slight perturbations. However, recent studies have paid less attention to the impact of quantization on the model robustness. More surprisingly, existing studies on this topic even present inconsistent conclusions, which prompted our in-depth investigation. In this paper, we conduct a first-time analysis of the impact of the quantization pipeline components that can incorporate robust optimization under the settings of Post-Training Quantization and Quantization-Aware Training. Through our detailed analysis, we discovered that this inconsistency arises from the use of different pipelines in different studies, specifically regarding whether robust optimization is performed and at which quantization stage it occurs. Our research findings contribute insights into deploying more secure and robust quantized networks, assisting practitioners in reference for scenarios with high-security requirements and limited resources.

Haojun Sun, Chen Tang, Zhi Wang et al.

Diffusion models have emerged as preeminent contenders in the realm of generative models. Distinguished by their distinctive sequential generative processes, characterized by hundreds or even thousands of timesteps, diffusion models progressively reconstruct images from pure Gaussian noise, with each timestep necessitating full inference of the entire model. However, the substantial computational demands inherent to these models present challenges for deployment, quantization is thus widely used to lower the bit-width for reducing the storage and computing overheads. Current quantization methodologies primarily focus on model-side optimization, disregarding the temporal dimension, such as the length of the timestep sequence, thereby allowing redundant timesteps to continue consuming computational resources, leaving substantial scope for accelerating the generative process. In this paper, we introduce TMPQ-DM, which jointly optimizes timestep reduction and quantization to achieve a superior performance-efficiency trade-off, addressing both temporal and model optimization aspects. For timestep reduction, we devise a non-uniform grouping scheme tailored to the non-uniform nature of the denoising process, thereby mitigating the explosive combinations of timesteps. In terms of quantization, we adopt a fine-grained layer-wise approach to allocate varying bit-widths to different layers based on their respective contributions to the final generative performance, thus rectifying performance degradation observed in prior studies. To expedite the evaluation of fine-grained quantization, we further devise a super-network to serve as a precision solver by leveraging shared quantization results. These two design components are seamlessly integrated within our framework, enabling rapid joint exploration of the exponentially large decision space via a gradient-free evolutionary search algorithm.

Jiacheng Jiang, Yuan Meng, Chen Tang et al.

Research on loss surface geometry, such as Sharpness-Aware Minimization (SAM), shows that flatter minima improve generalization. Recent studies further reveal that flatter minima can also reduce the domain generalization (DG) gap. However, existing flatness-based DG techniques predominantly operate within a full-precision training process, which is impractical for deployment on resource-constrained edge devices that typically rely on lower bit-width representations (e.g., 4 bits, 3 bits). Consequently, low-precision quantization-aware training is critical for optimizing these techniques in real-world applications. In this paper, we observe a significant degradation in performance when applying state-of-the-art DG-SAM methods to quantized models, suggesting that current approaches fail to preserve generalizability during the low-precision training process. To address this limitation, we propose a novel Gradient-Adaptive Quantization-Aware Training (GAQAT) framework for DG. Our approach begins by identifying the scale-gradient conflict problem in low-precision quantization, where the task loss and smoothness loss induce conflicting gradients for the scaling factors of quantizers, with certain layers exhibiting opposing gradient directions. This conflict renders the optimization of quantized weights highly unstable. To mitigate this, we further introduce a mechanism to quantify gradient inconsistencies and selectively freeze the gradients of scaling factors, thereby stabilizing the training process and enhancing out-of-domain generalization. Extensive experiments validate the effectiveness of the proposed GAQAT framework. On PACS, our 3-bit and 4-bit models outperform direct DG-QAT integration by up to 4.5%. On DomainNet, the 4-bit model achieves near-lossless performance compared to full precision, with improvements of 1.39% (4-bit) and 1.06% (3-bit) over the SOTA QAT baseline.