42 citations · 60 across the 13 of their papers we have counts for
13 papers · 1 filter
Restoring without Forgetting: Filter-Level Continual Image Restoration via Parameter-Space Integrated Gradients
Xin Feng, Jin Zhao, Yizhen Zhang +3
Adapting image restoration models to a stream of new tasks without revisiting past data remains challenging due to catastrophic forgetting. In this work, we propose Restoring witho…
WeCromCL: Weakly Supervised Cross-Modality Contrastive Learning for Transcription-only Supervised Text Spotting
Jingjing Wu, Zhengyao Fang, Pengyuan Lyu +4
Transcription-only Supervised Text Spotting aims to learn text spotters relying only on transcriptions but no text boundaries for supervision, thus eliminating expensive boundary a…
Domain-Rectifying Adapter for Cross-Domain Few-Shot Segmentation
Jiapeng Su, Qi Fan, Guangming Lu +2
Few-shot semantic segmentation (FSS) has achieved great success on segmenting objects of novel classes, supported by only a few annotated samples. However, existing FSS methods oft…
STA-VPT: SpatioTemporally Aligned Visual Prompt Tuning
Wenjie Pei, Tongqi Xia, Qizhong Tan +3
Typical methods for visual prompt tuning follow the sequential modeling paradigm originating from NLP, learning a sequence of unordered parameterized tokens as visual prompts, whic…
Universal Object Detection with Large Vision Model
Feng Lin, Wenze Hu, Yaowei Wang +5
Over the past few years, there has been growing interest in developing a broad, universal, and general-purpose computer vision system. Such systems have the potential to address a…
Semantic-Aware Local-Global Vision Transformer
Jiatong Zhang, Zengwei Yao, Fanglin Chen +2
Vision Transformers have achieved remarkable progresses, among which Swin Transformer has demonstrated the tremendous potential of Transformer for vision tasks. It surmounts the ke…
Learning Generalizable Latent Representations for Novel Degradations in Super Resolution
Fengjun Li, Xin Feng, Fanglin Chen +2
Typical methods for blind image super-resolution (SR) focus on dealing with unknown degradations by directly estimating them or learning the degradation representations in a latent…
Few-Shot Object Detection by Knowledge Distillation Using Bag-of-Visual-Words Representations
Wenjie Pei, Shuang Wu, Dianwen Mei +3
While fine-tuning based methods for few-shot object detection have achieved remarkable progress, a crucial challenge that has not been addressed well is the potential class-specifi…
Multi-Faceted Distillation of Base-Novel Commonality for Few-shot Object Detection
Shuang Wu, Wenjie Pei, Dianwen Mei +3
Most of existing methods for few-shot object detection follow the fine-tuning paradigm, which potentially assumes that the class-agnostic generalizable knowledge can be learned and…
Global-Local Stepwise Generative Network for Ultra High-Resolution Image Restoration
Xin Feng, Haobo Ji, Wenjie Pei +2
While the research on image background restoration from regular size of degraded images has achieved remarkable progress, restoring ultra high-resolution (e.g., 4K) images remains…
Pedestrian Detection by Exemplar-Guided Contrastive Learning
Zebin Lin, Wenjie Pei, Fanglin Chen +2
Typical methods for pedestrian detection focus on either tackling mutual occlusions between crowded pedestrians, or dealing with the various scales of pedestrians. Detecting pedest…
Generative Memory-Guided Semantic Reasoning Model for Image Inpainting
Xin Feng, Wenjie Pei, Fengjun Li +3
Most existing methods for image inpainting focus on learning the intra-image priors from the known regions of the current input image to infer the content of the corrupted regions…
Deep-Masking Generative Network: A Unified Framework for Background Restoration from Superimposed Images
Xin Feng, Wenjie Pei, Zihui Jia +3
Restoring the clean background from the superimposed images containing a noisy layer is the common crux of a classical category of tasks on image restoration such as image reflecti…