Search Results for author:
Found 9 papers, 6 papers with code
Enlighten-Your-Voice: When Multimodal Meets Zero-shot Low-light Image Enhancement
Low-light image enhancement is a crucial visual task, and many unsupervised methods tend to overlook the degradation of visible information in low-light scenes, which adversely affects the fusion of complementary information and hinders the generation of satisfactory results.
A Dual Attentive Generative Adversarial Network for Remote Sensing Image Change Detection
Remote sensing change detection between bi-temporal images receives growing concentration from researchers.
Enlighten Anything: When Segment Anything Model Meets Low-Light Image Enhancement
Image restoration is a low-level visual task, and most CNN methods are designed as black boxes, lacking transparency and intrinsic aesthetics.
SAM-helps-Shadow:When Segment Anything Model meet shadow removal
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-shot learning in this field.
Distribution Learning Based on Evolutionary Algorithm Assisted Deep Neural Networks for Imbalanced Image Classification
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 instead of the data level and focus on searching the latent feature space for optimal distributions.
Self-supervised Implicit Glyph Attention for Text Recognition
Supervised attention can alleviate the above issue, but it is character category-specific, which requires extra laborious character-level bounding box annotations and would be memory-intensive when handling languages with larger character categories.
Ranked #2 on
Scene Text Recognition
on ICDAR 2003
Industrial Scene Text Detection with Refined Feature-attentive Network
Then, an attentive refinement network is developed by the attention map to rectify the location deviation of candidate boxes.
Complementary Patch for Weakly Supervised Semantic Segmentation
Therefore, a CAM with more information related to object seeds can be obtained by narrowing down the gap between the sum of CAMs generated by the CP Pair and the original CAM.
An Improved Algorithm of Robot Path Planning in Complex Environment Based on Double DQN
Deep Q Network (DQN) has several limitations when applied in planning a path in environment with a number of dilemmas according to our experiment.
