9.2k citations · 16.2k across the 175 of their papers we have counts for
37 papers · 1 filter
Position-Aware Contrastive Alignment for Referring Image Segmentation
Bo Chen, Zhiwei Hu, Zhilong Ji +2
Referring image segmentation aims to segment the target object described by a given natural language expression. Typically, referring expressions contain complex relationships betw…
Texts as Images in Prompt Tuning for Multi-Label Image Recognition
Zixian Guo, Bowen Dong, Zhilong Ji +3
Prompt tuning has been employed as an efficient way to adapt large vision-language pre-trained models (e.g. CLIP) to various downstream tasks in data-limited or label-limited setti…
Benchmark Dataset and Effective Inter-Frame Alignment for Real-World Video Super-Resolution
Ruohao Wang, Xiaohui Liu, Zhilu Zhang +4
Video super-resolution (VSR) aiming to reconstruct a high-resolution (HR) video from its low-resolution (LR) counterpart has made tremendous progress in recent years. However, it r…
HS-Diffusion: Semantic-Mixing Diffusion for Head Swapping
Qinghe Wang, Lijie Liu, Miao Hua +5
Image-based head swapping task aims to stitch a source head to another source body flawlessly. This seldom-studied task faces two major challenges: 1) Preserving the head and body…
Learning Single Image Defocus Deblurring with Misaligned Training Pairs
Yu Li, Dongwei Ren, Xinya Shu +1
By adopting popular pixel-wise loss, existing methods for defocus deblurring heavily rely on well aligned training image pairs. Although training pairs of ground-truth and blurry i…
Self-Supervised Image Restoration with Blurry and Noisy Pairs
Zhilu Zhang, Rongjian Xu, Ming Liu +2
When taking photos under an environment with insufficient light, the exposure time and the sensor gain usually require to be carefully chosen to obtain images with satisfying visua…
Reversed Image Signal Processing and RAW Reconstruction. AIM 2022 Challenge Report
Marcos V. Conde, Radu Timofte, Yibin Huang +40
Cameras capture sensor RAW images and transform them into pleasant RGB images, suitable for the human eyes, using their integrated Image Signal Processor (ISP). Numerous low-level…
Learning Dual Memory Dictionaries for Blind Face Restoration
Xiaoming Li, Shiguang Zhang, Shangchen Zhou +2
To improve the performance of blind face restoration, recent works mainly treat the two aspects, i.e., generic and specific restoration, separately. In particular, generic restorat…
From Face to Natural Image: Learning Real Degradation for Blind Image Super-Resolution
Xiaoming Li, Chaofeng Chen, Xianhui Lin +2
How to design proper training pairs is critical for super-resolving real-world low-quality (LQ) images, which suffers from the difficulties in either acquiring paired ground-truth…
ImaginaryNet: Learning Object Detectors without Real Images and Annotations
Minheng Ni, Zitong Huang, Kailai Feng +1
Without the demand of training in reality, humans can easily detect a known concept simply based on its language description. Empowering deep learning with this ability undoubtedly…
Multi-stage image denoising with the wavelet transform
Chunwei Tian, Menghua Zheng, Wangmeng Zuo +3
Deep convolutional neural networks (CNNs) are used for image denoising via automatically mining accurate structure information. However, most of existing CNNs depend on enlarging d…
CLIP2Point: Transfer CLIP to Point Cloud Classification with Image-Depth Pre-training
Tianyu Huang, Bowen Dong, Yunhan Yang +4
Pre-training across 3D vision and language remains under development because of limited training data. Recent works attempt to transfer vision-language pre-training models to 3D vi…
LPT: Long-tailed Prompt Tuning for Image Classification
Bowen Dong, Pan Zhou, Shuicheng Yan +1
For long-tailed classification, most works often pretrain a big model on a large-scale dataset, and then fine-tune the whole model for adapting to long-tailed data. Though promisin…
A heterogeneous group CNN for image super-resolution
Chunwei Tian, Yanning Zhang, Wangmeng Zuo +3
Convolutional neural networks (CNNs) have obtained remarkable performance via deep architectures. However, these CNNs often achieve poor robustness for image super-resolution (SR)…
Two-Stream Networks for Object Segmentation in Videos
Hannan Lu, Zhi Tian, Lirong Yang +2
Existing matching-based approaches perform video object segmentation (VOS) via retrieving support features from a pixel-level memory, while some pixels may suffer from lack of corr…
W2N:Switching From Weak Supervision to Noisy Supervision for Object Detection
Zitong Huang, Yiping Bao, Bowen Dong +2
Weakly-supervised object detection (WSOD) aims to train an object detector only requiring the image-level annotations. Recently, some works have managed to select the accurate boxe…
Adversarial Contrastive Learning via Asymmetric InfoNCE
Qiying Yu, Jieming Lou, Xianyuan Zhan +4
Contrastive learning (CL) has recently been applied to adversarial learning tasks. Such practice considers adversarial samples as additional positive views of an instance, and by m…
Towards Diverse and Faithful One-shot Adaption of Generative Adversarial Networks
Yabo Zhang, Mingshuai Yao, Yuxiang Wei +3
One-shot generative domain adaption aims to transfer a pre-trained generator on one domain to a new domain using one reference image only. However, it remains very challenging for…
Symmetry-Aware Transformer-based Mirror Detection
Tianyu Huang, Bowen Dong, Jiaying Lin +3
Mirror detection aims to identify the mirror regions in the given input image. Existing works mainly focus on integrating the semantic features and structural features to mine spec…
Learning Diverse Tone Styles for Image Retouching
Haolin Wang, Jiawei Zhang, Ming Liu +2
Image retouching, aiming to regenerate the visually pleasing renditions of given images, is a subjective task where the users are with different aesthetic sensations. Most existing…
An Improved Normed-Deformable Convolution for Crowd Counting
Xin Zhong, Zhaoyi Yan, Jing Qin +2
In recent years, crowd counting has become an important issue in computer vision. In most methods, the density maps are generated by convolving with a Gaussian kernel from the grou…
Robust Deep Ensemble Method for Real-world Image Denoising
Pengju Liu, Hongzhi Zhang, Jinghui Wang +3
Recently, deep learning-based image denoising methods have achieved promising performance on test data with the same distribution as training set, where various denoising models ba…
Image Super-resolution with An Enhanced Group Convolutional Neural Network
Chunwei Tian, Yixuan Yuan, Shichao Zhang +3
CNNs with strong learning abilities are widely chosen to resolve super-resolution problem. However, CNNs depend on deeper network architectures to improve performance of image supe…
Squeeze Training for Adversarial Robustness
Qizhang Li, Yiwen Guo, Wangmeng Zuo +1
The vulnerability of deep neural networks (DNNs) to adversarial examples has attracted great attention in the machine learning community. The problem is related to non-flatness and…