Search Results for author:
Found 6 papers, 3 papers with code
Building Optimal Neural Architectures using Interpretable Knowledge
Neural Architecture Search is a costly practice.
CascadedGaze: Efficiency in Global Context Extraction for Image Restoration
Image restoration tasks traditionally rely on convolutional neural networks.
Ranked #1 on
Image Denoising
on SIDD
Q-Boost: On Visual Quality Assessment Ability of Low-level Multi-Modality Foundation Models
Recent advancements in Multi-modality Large Language Models (MLLMs) have demonstrated remarkable capabilities in complex high-level vision tasks.
Exploring the Naturalness of AI-Generated Images
In this paper, we take the first step to benchmark and assess the visual naturalness of AI-generated images.
RepQ: Generalizing Quantization-Aware Training for Re-Parametrized Architectures
However, there are various methods to improve their efficiency.
Ternary Singular Value Decomposition as a Better Parameterized Form in Linear Mapping
We present a simple yet novel parameterized form of linear mapping to achieves remarkable network compression performance: a pseudo SVD called Ternary SVD (TSVD).
