55 citations · 81 across the 7 of their papers we have counts for
7 papers
Enlighten Anything: When Segment Anything Model Meets Low-Light Image Enhancement
Qihan Zhao, Xiaofeng Zhang, Hao Tang +2
Image restoration is a low-level visual task, and most CNN methods are designed as black boxes, lacking transparency and intrinsic aesthetics. Many unsupervised approaches ignore t…
SAM-helps-Shadow:When Segment Anything Model meet shadow removal
Xiaofeng Zhang, Chaochen Gu, Shanying Zhu
The challenges surrounding the application of image shadow removal to real-world images and not just constrained datasets like ISTD/SRD have highlighted an urgent need for zero-sho…
Distribution Learning Based on Evolutionary Algorithm Assisted Deep Neural Networks for Imbalanced Image Classification
Yudi Zhao, Kuangrong Hao, Chaochen Gu +1
To address the trade-off problem of quality-diversity for the generated images in imbalanced classification tasks, we research on over-sampling based methods at the feature level i…
Self-supervised Implicit Glyph Attention for Text Recognition
Tongkun Guan, Chaochen Gu, Jingzheng Tu +5
The attention mechanism has become the \emph{de facto} module in scene text recognition (STR) methods, due to its capability of extracting character-level representations. These me…
Industrial Scene Text Detection with Refined Feature-attentive Network
Tongkun Guan, Chaochen Gu, Changsheng Lu +4
Detecting the marking characters of industrial metal parts remains challenging due to low visual contrast, uneven illumination, corroded character structures, and cluttered backgro…
Complementary Patch for Weakly Supervised Semantic Segmentation
Fei Zhang, Chaochen Gu, Chenyue Zhang +1
Weakly Supervised Semantic Segmentation (WSSS) based on image-level labels has been greatly advanced by exploiting the outputs of Class Activation Map (CAM) to generate the pseudo…
An Improved Algorithm of Robot Path Planning in Complex Environment Based on Double DQN
Fei Zhang, Chaochen Gu, Feng Yang
Deep Q Network (DQN) has several limitations when applied in planning a path in environment with a number of dilemmas according to our experiment. The reward function may be hard t…