7 papers
ChWDTA: Channel-wise Wavelet-Domain Transformer Attention and Entropy Modeling for Learned Image Compression
Haisheng Fu, Runyu Yang, Feng Ding +5
State-of-the-art learned image compression (LIC) schemes are increasingly based on hybrid CNN-transformer architectures. To further improve rate-distortion performance, we introduc…
NSC-SL: A Bandwidth-Aware Neural Subspace Compression for Communication-Efficient Split Learning
Zhen Fang, Miao Yang, Zehang Lin +6
The expanding scale of neural networks poses a major challenge for distributed machine learning, particularly under limited communication resources. While split learning (SL) allev…
3DM-WeConvene: Learned Image Compression with 3D Multi-Level Wavelet-Domain Convolution and Entropy Model
Haisheng Fu, Jie Liang, Feng Liang +3
Learned image compression (LIC) has recently made significant progress, surpassing traditional methods. However, most LIC approaches operate mainly in the spatial domain and lack m…
SELIC: Semantic-Enhanced Learned Image Compression via High-Level Textual Guidance
Haisheng Fu, Jie Liang, Zhenman Fang +1
Learned image compression (LIC) techniques have achieved remarkable progress; however, effectively integrating high-level semantic information remains challenging. In this work, we…
FEDS: Feature and Entropy-Based Distillation Strategy for Efficient Learned Image Compression
Haisheng Fu, Jie Liang, Zhenman Fang +1
Learned image compression (LIC) methods have recently outperformed traditional codecs such as VVC in rate-distortion performance. However, their large models and high computational…
Quasar-ViT: Hardware-Oriented Quantization-Aware Architecture Search for Vision Transformers
Zhengang Li, Alec Lu, Yanyue Xie +9
Vision transformers (ViTs) have demonstrated their superior accuracy for computer vision tasks compared to convolutional neural networks (CNNs). However, ViT models are often compu…