Related papers: Diversity-aware Channel Pruning for StyleGAN Compr…
Network pruning is one of the most dominant methods for reducing the heavy inference cost of deep neural networks. Existing methods often iteratively prune networks to attain high compression ratio without incurring significant loss in…
We present the first neural video compression method based on generative adversarial networks (GANs). Our approach significantly outperforms previous neural and non-neural video compression methods in a user study, setting a new…
We propose a framework for the automatic one-shot segmentation of synthetic images generated by a StyleGAN. Our framework is based on the observation that the multi-scale hidden features in the GAN generator hold useful semantic information…
In this work, we propose a new layer-by-layer channel pruning method called Channel Pruning guided by classification Loss and feature Importance (CPLI). In contrast to the existing layer-by-layer channel pruning approaches that only…
Pixel-level fine-grained image editing remains an open challenge. Previous works fail to achieve an ideal trade-off between control granularity and inference speed. They either fail to achieve pixel-level fine-grained control, or their…
Despite the strong performance of Transformers, their quadratic computation complexity presents challenges in applying them to vision tasks. Automatic pruning is one of effective methods for reducing computation complexity without heuristic…
Current approaches for compressing the Segment Anything Model (SAM) yield commendable results, yet necessitate extensive data to train a new network from scratch. Employing conventional pruning techniques can remarkably reduce data…
Self-supervised speech representation learning (SSL) has shown to be effective in various downstream tasks, but SSL models are usually large and slow. Model compression techniques such as pruning aim to reduce the model size and computation…
Recently, many neural network-based image compression methods have shown promising results superior to the existing tool-based conventional codecs. However, most of them are often trained as separate models for different target bit rates,…
The semantic controllability of StyleGAN is enhanced by unremitting research. Although the existing weak supervision methods work well in manipulating the style codes along one attribute, the accuracy of manipulating multiple attributes is…
Channel, as the medium for the propagation of electromagnetic waves, is one of the most important parts of a communication system. Being aware of how the channel affects the propagation waves is essential for designing, optimization and…
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…
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…
Latent Diffusion Models (LDMs) have emerged as powerful generative models, known for delivering remarkable results under constrained computational resources. However, deploying LDMs on resource-limited devices remains a complex issue,…
This work integrates StyleGAN, DragGAN and Principal Component Analysis (PCA) to enhance the latent space efficiency and controllability of GAN-generated images. Style-GAN provides a structured latent space, DragGAN enables intuitive image…
To address the limitations of existing magnitude-based pruning algorithms in cases where model weights or activations are of large and similar magnitude, we propose a novel perspective to discover parameter redundancy among channels and…
Potential radioactive hazards in full-dose positron emission tomography (PET) imaging remain a concern, whereas the quality of low-dose images is never desirable for clinical use. So it is of great interest to translate low-dose PET images…
Recent works have indicated redundancy across transformer blocks, prompting the research of depth compression to prune less crucial blocks. However, current ways of entire-block pruning suffer from risks of discarding meaningful cues…
Channel-based pruning has achieved significant successes in accelerating deep convolutional neural network, whose pipeline is an iterative three-step procedure: ranking, pruning and fine-tuning. However, this iterative procedure is…
Text-driven image manipulation is developed since the vision-language model (CLIP) has been proposed. Previous work has adopted CLIP to design a text-image consistency-based objective to address this issue. However, these methods require…