Class incremental learning (CIL) aims to solve the notorious forgetting problem, which refers to the fact that once the network is updated on a new task, its performance on previously-learned tasks degenerates catastrophically. Most successful CIL methods store exemplars (samples of learned tasks) to train a feature extractor incrementally, or store prototypes (features of learned tasks) to estimate the incremental feature distribution. However, the stored exemplars would violate the data privacy concerns, while the fixed prototypes might not reasonably be consistent with the incremental feature distribution, hindering the exploration of real-world CIL applications. In this paper, we propose a data-free CIL method with embedding distillation and Task-oriented generation (eTag), which requires neither exemplar nor prototype. Embedding distillation prevents the feature extractor from forgetting by distilling the outputs from the networks' intermediate blocks. Task-oriented generation enables a lightweight generator to produce dynamic features, fitting the needs of the top incremental classifier. Experimental results confirm that the proposed eTag considerably outperforms state-of-the-art methods on several benchmark datasets.

Although the diffusion model has achieved remarkable performance in the field of image generation, its high inference delay hinders its wide application in edge devices with scarce computing resources. Therefore, many training-free sampling methods have been proposed to reduce the number of sampling steps required for diffusion models. However, they perform poorly under a very small number of sampling steps. Thanks to the emergence of knowledge distillation technology, the existing training scheme methods have achieved excellent results at very low step numbers. However, the current methods mainly focus on designing novel diffusion model sampling methods with knowledge distillation. How to transfer better diffusion knowledge from teacher models is a more valuable problem but rarely studied. Therefore, we propose Relational Diffusion Distillation (RDD), a novel distillation method tailored specifically for distilling diffusion models. Unlike existing methods that simply align teacher and student models at pixel level or feature distributions, our method introduces cross-sample relationship interaction during the distillation process and alleviates the memory constraints induced by multiple sample interactions. Our RDD significantly enhances the effectiveness of the progressive distillation framework within the diffusion model. Extensive experiments on several datasets (e.g., CIFAR-10 and ImageNet) demonstrate that our proposed RDD leads to 1.47 FID decrease under 1 sampling step compared to state-of-the-art diffusion distillation methods and achieving 256x speed-up compared to DDIM strategy. Code is available at https://github.com/cantbebetter2/RDD.

Diffusion models have received wide attention in generation tasks. However, the expensive computation cost prevents the application of diffusion models in resource-constrained scenarios. Quantization emerges as a practical solution that significantly saves storage and computation by reducing the bit-width of parameters. However, the existing quantization methods for diffusion models still cause severe degradation in performance, especially under extremely low bit-widths (2-4 bit). The primary decrease in performance comes from the significant discretization of activation values at low bit quantization. Too few activation candidates are unfriendly for outlier significant weight channel quantization, and the discretized features prevent stable learning over different time steps of the diffusion model. This paper presents MPQ-DM, a Mixed-Precision Quantization method for Diffusion Models. The proposed MPQ-DM mainly relies on two techniques: (1) To mitigate the quantization error caused by outlier severe weight channels, we propose an Outlier-Driven Mixed Quantization (OMQ) technique that uses Kurtosis to quantify outlier salient channels and apply optimized intra-layer mixed-precision bit-width allocation to recover accuracy performance within target efficiency. (2) To robustly learn representations crossing time steps, we construct a Time-Smoothed Relation Distillation (TRD) scheme between the quantized diffusion model and its full-precision counterpart, transferring discrete and continuous latent to a unified relation space to reduce the representation inconsistency. Comprehensive experiments demonstrate that MPQ-DM achieves significant accuracy gains under extremely low bit-widths compared with SOTA quantization methods. MPQ-DM achieves a 58% FID decrease under W2A4 setting compared with baseline, while all other methods even collapse.

GEMM (General Matrix Multiplication) serves as a fundamental operator for deep learning computations. Especially in attention-based deep learning models, such as Bert, GPT, and SAM, the sizes of matrices involved in GEMMs exhibit an unbalanced distribution due to the variable input, resulting in the low utilization of hardware resources. To address the issue, this paper proposes inserting a novel GEMM processing layer into the deep learning inference stack and using an adaptive load balancing method to partition and schedule GEMM computation tasks. The method is implemented with hardware runtime resource information, such as the occupancy of computing units, etc. Experiment results show the remarkable performance of our method in unbalanced input GEMM scenarios, achieving an average performance improvement of 2.3x. The method also performs well in attention-based models (GPT-2 and SAM), achieving an average inference speed improvement of 1.1x. These findings highlight the effectiveness of resource-aware algorithm optimization, especially for computation task scheduling.