Search Results for author:
Found 24 papers, 17 papers with code
Small Model and In-Domain Data Are All You Need
I participated in the WMT shared news translation task and focus on one high resource language pair: English and Chinese (two directions, Chinese to English and English to Chinese).
Everywhere Attack: Attacking Locally and Globally to Boost Targeted Transferability
Extensive experiments on ImageNet demonstrate that the proposed approach universally improves the state-of-the-art targeted attacks by a clear margin, e. g., the transferability of the widely adopted Logit attack can be improved by 28. 8%-300%. We also evaluate the crafted AEs on a real-world platform: Google Cloud Vision.
Two Heads Are Better Than One: Averaging along Fine-Tuning to Improve Targeted Transferability
We compare the proposed method with existing fine-tuning schemes by integrating them with state-of-the-art targeted attacks in various attacking scenarios.
MetaTrading: An Immersion-Aware Model Trading Framework for Vehicular Metaverse Services
To comprehensively evaluate the contribution of locally trained learning models provided by MUs to AR services, we design a new immersion metric that captures service immersion by considering the freshness and accuracy of learning models, as well as the amount and potential value of raw data used for training.
NTIRE 2024 Restore Any Image Model (RAIM) in the Wild Challenge
In this paper, we review the NTIRE 2024 challenge on Restore Any Image Model (RAIM) in the Wild.
Enhancing targeted transferability via feature space fine-tuning
Adversarial examples (AEs) have been extensively studied due to their potential for privacy protection and inspiring robust neural networks.
Guided Image Restoration via Simultaneous Feature and Image Guided Fusion
Currently, joint image filtering-inspired deep learning-based methods represent the state-of-the-art for GIR tasks.
Evaluating the Generation Capabilities of Large Chinese Language Models
This paper unveils CG-Eval, the first-ever comprehensive and automated evaluation framework designed for assessing the generative capabilities of large Chinese language models across a spectrum of academic disciplines.
Measuring Massive Multitask Chinese Understanding
Across the four major domains, the highest average zero-shot accuracy of all models is 0. 512.
Human Guided Ground-truth Generation for Realistic Image Super-resolution
A human guided GT image dataset with both positive and negative samples is then constructed, and a loss function is proposed to train the Real-ISR models.
Joint HDR Denoising and Fusion: A Real-World Mobile HDR Image Dataset
In this work, we develop, for the first time to our best knowledge, an HDR image dataset by using mobile phone cameras, namely Mobile-HDR dataset.
Efficient and Degradation-Adaptive Network for Real-World Image Super-Resolution
Specifically, a tiny regression network is employed to predict the degradation parameters of the input image, while several convolutional experts with the same topology are jointly optimized to specify the network parameters via a non-linear mixture of experts.
Details or Artifacts: A Locally Discriminative Learning Approach to Realistic Image Super-Resolution
In this paper, we demonstrate that it is possible to train a GAN-based SISR model which can stably generate perceptually realistic details while inhibiting visual artifacts.
Efficient Long-Range Attention Network for Image Super-resolution
A highly efficient long-range attention block (ELAB) is then built by simply cascading two shift-conv with a GMSA module, which is further accelerated by using a shared attention mechanism.
Ranked #15 on
Image Super-Resolution
on Manga109 - 4x upscaling
A comparison study of CNN denoisers on PRNU extraction
In this paper, a comparative evaluation of such CNN denoisers on SCI performance is carried out on the public "Dresden Image Database".
PPR10K: A Large-Scale Portrait Photo Retouching Dataset with Human-Region Mask and Group-Level Consistency
HRP requires that more attention should be paid to human regions, while GLC requires that a group of portrait photos should be retouched to a consistent tone.
High-Resolution Photorealistic Image Translation in Real-Time: A Laplacian Pyramid Translation Network
Existing image-to-image translation (I2IT) methods are either constrained to low-resolution images or long inference time due to their heavy computational burden on the convolution of high-resolution feature maps.
Ranked #1 on
Photo Retouching
on MIT-Adobe 5k (1080p)
Real-Time Quantized Image Super-Resolution on Mobile NPUs, Mobile AI 2021 Challenge: Report
Image super-resolution is one of the most popular computer vision problems with many important applications to mobile devices.
Real-World Video Super-Resolution: A Benchmark Dataset and a Decomposition Based Learning Scheme
Existing VSR methods are mostly trained and evaluated on synthetic datasets, where the LR videos are uniformly downsampled from their high-resolution (HR) counterparts by some simple operators (e. g., bicubic downsampling).
Learning Image-adaptive 3D Lookup Tables for High Performance Photo Enhancement in Real-time
The small CNN works on the down-sampled version of the input image to predict content-dependent weights to fuse the multiple basis 3D LUTs into an image-adaptive one, which is employed to transform the color and tone of source images efficiently.
Ranked #5 on
Image Enhancement
on MIT-Adobe 5k
(SSIM on proRGB metric)
Grid Anchor based Image Cropping: A New Benchmark and An Efficient Model
The employed evaluation metrics such as intersection-over-union cannot reliably reflect the real performance of a cropping model, either.
Reliable and Efficient Image Cropping: A Grid Anchor based Approach
Consequently, a grid anchor based cropping benchmark is constructed, where all crops of each image are annotated and more reliable evaluation metrics are defined.
Toward Real-World Single Image Super-Resolution: A New Benchmark and A New Model
Most of the existing learning-based single image superresolution (SISR) methods are trained and evaluated on simulated datasets, where the low-resolution (LR) images are generated by applying a simple and uniform degradation (i. e., bicubic downsampling) to their high-resolution (HR) counterparts.
A Probabilistic Quality Representation Approach to Deep Blind Image Quality Prediction
Recognizing this, we propose a new representation of perceptual image quality, called probabilistic quality representation (PQR), to describe the image subjective score distribution, whereby a more robust loss function can be employed to train a deep BIQA model.
