相关论文: FADRM: Fast and Accurate Data Residual Matching fo…

Highly distributed training of Deep Neural Networks (DNNs) on future compute platforms (offering 100 of TeraOps/s of computational capacity) is expected to be severely communication constrained. To overcome this limitation, new gradient…

Dataset distillation reduces the network training cost by synthesizing small and informative datasets from large-scale ones. Despite the success of the recent dataset distillation algorithms, three drawbacks still limit their wider…

Knowledge Distillation is crucial for optimizing face recognition models for deployment in computationally limited settings, such as edge devices. Traditional KD methods, such as Raw L2 Feature Distillation or Feature Consistency loss,…

Knowledge distillation is an effective method for model compression. However, it is still a challenging topic to apply knowledge distillation to detection tasks. There are two key points resulting in poor distillation performance for…

Memory-efficient transfer learning (METL) approaches have recently achieved promising performance in adapting pre-trained models to downstream tasks. They avoid applying gradient backpropagation in large backbones, thus significantly…

Discrete diffusion models (DDMs) have shown powerful generation ability for discrete data modalities like text and molecules. However, their practical application is hindered by inefficient sampling, requiring a large number of sampling…

Diffusion models produce high-quality text-to-image results, but their iterative denoising is computationally expensive.Distribution Matching Distillation (DMD) emerges as a promising path to few-step distillation, but suffers from…

Dataset distillation has emerged as a strategy to compress real-world datasets for efficient training. However, it struggles with large-scale and high-resolution datasets, limiting its practicality. This paper introduces a novel…

Diffusion models have recently achieved remarkable performance in image super-resolution (SR), but their high computational cost limits practical deployment in remote sensing applications. To address this issue, we propose SlimDiffSR, a…

Dataset distillation, which condenses large-scale datasets into compact synthetic representations, has emerged as a critical solution for training modern deep learning models efficiently. While prior surveys focus on developments before…

We present an ultra-efficient post-training method for shortcutting large-scale pre-trained flow matching diffusion models into efficient few-step samplers, enabled by novel velocity field self-distillation. While shortcutting in flow…

Modern deep recommender models are trained under a continual learning paradigm, relying on massive and continuously growing streaming behavioral logs. In large-scale platforms, retraining models on full historical data for architecture…

Deep learning technology has developed unprecedentedly in the last decade and has become the primary choice in many application domains. This progress is mainly attributed to a systematic collaboration in which rapidly growing computing…

Few-shot class-incremental learning (FSCIL) receives significant attention from the public to perform classification continuously with a few training samples, which suffers from the key catastrophic forgetting problem. Existing methods…

High-performance Transformer trackers have shown excellent results, yet they often bear a heavy computational load. Observing that a smaller input can immediately and conveniently reduce computations without changing the model, an easy…

Diffusion distillation models effectively accelerate reverse sampling by compressing the process into fewer steps. However, these models still exhibit a performance gap compared to their pre-trained diffusion model counterparts, exacerbated…

Deep neural networks (DNNs) have achieved great success in the area of computer vision. The disparity estimation problem tends to be addressed by DNNs which achieve much better prediction accuracy in stereo matching than traditional…

Discrete diffusion models (DDMs) are a powerful class of generative models for categorical data, but they typically require many function evaluations for a single sample, making inference expensive. Existing acceleration methods either rely…

The inherent noisy and sparse characteristics of radar data pose challenges in finding effective representations for 3D object detection. In this paper, we propose RadarDistill, a novel knowledge distillation (KD) method, which can improve…

Residual connections are one of the most important components in neural network architectures for mitigating the vanishing gradient problem and facilitating the training of much deeper networks. One possible explanation for how residual…