相关论文: PRANCE: Joint Token-Optimization and Structural Ch…

Large Vision-Language Models (VLMs) achieve strong multimodal understanding capabilities by leveraging high-resolution visual inputs, but the resulting large number of visual tokens creates a major computational bottleneck. Recent work…

The success of convolutional neural networks (CNNs) in various applications is accompanied by a significant increase in computation and parameter storage costs. Recent efforts to reduce these overheads involve pruning and compressing the…

Semantic segmentation for scene understanding is nowadays widely demanded, raising significant challenges for the algorithm efficiency, especially its applications on resource-limited platforms. Current segmentation models are trained and…

Vision Transformers (ViTs) have demonstrated strong performance across a wide range of vision tasks, yet their substantial computational and memory demands hinder efficient deployment on resource-constrained mobile and edge devices. Pruning…

Channel Pruning is one of the most widespread techniques used to compress deep neural networks while maintaining their performances. Currently, a typical pruning algorithm leverages neural architecture search to directly find networks with…

The computational overhead of Vision Transformers in practice stems fundamentally from their deep architectures, yet existing acceleration strategies have primarily targeted algorithmic-level optimizations such as token pruning and…

Vision-Language Models (VLMs) have advanced rapidly within the unified Transformer architecture, yet their deployment on resource-constrained devices remains challenging due to high computational complexity. While pruning has emerged as an…

Diffusion Transformers (DiTs) deliver state-of-the-art generative performance but their quadratic training cost with sequence length makes large-scale pretraining prohibitively expensive. Token dropping can reduce training cost, yet na\"ive…

Transfer learning has become a popular task adaptation method in the era of foundation models. However, many foundation models require large storage and computing resources, which makes off-the-shelf deployment impractical. Post-training…

The Vision Transformer architecture is a deep learning model inspired by the success of the Transformer model in Natural Language Processing. However, the self-attention mechanism, large number of parameters, and the requirement for a…

Image Coding for Machines (ICM) focuses on optimizing image compression for AI-driven analysis rather than human perception. Existing ICM frameworks often rely on separate codecs for specific tasks, leading to significant storage…

This paper presents a novel approach to neural network pruning by integrating a graph-based observation space into an AutoML framework to address the limitations of existing methods. Traditional pruning approaches often depend on…

Token compression aims to speed up large-scale vision transformers (e.g. ViTs) by pruning (dropping) or merging tokens. It is an important but challenging task. Although recent advanced approaches achieved great success, they need to…

The resurgence of convolutional neural networks (CNNs) in visual recognition tasks, exemplified by ConvNeXt, has demonstrated their capability to rival transformer-based architectures through advanced training methodologies and ViT-inspired…

Channel (or 3D filter) pruning serves as an effective way to accelerate the inference of neural networks. There has been a flurry of algorithms that try to solve this practical problem, each being claimed effective in some ways. Yet, a…

Vision Transformer (ViT) has emerged as a powerful architecture in the realm of modern computer vision. However, its application in certain imaging fields, such as microscopy and satellite imaging, presents unique challenges. In these…

The demand for edge AI in vision-language tasks requires models that achieve real-time performance on resource-constrained devices with limited power and memory. This paper proposes two adaptive compression techniques -- Sparse Temporal…

Lightweight and effective models are essential for devices with limited resources, such as intelligent vehicles. Structured pruning offers a promising approach to model compression and efficiency enhancement. However, existing methods often…

Channel pruning is a promising method for accelerating and compressing convolutional neural networks. However, current pruning algorithms still remain unsolved problems that how to assign layer-wise pruning ratios properly and discard the…

The unstructured sparsity after pruning poses a challenge to the efficient implementation of deep learning models in existing regular architectures like systolic arrays. On the other hand, coarse-grained structured pruning is suitable for…