12 Result(s)
within
Zhicheng Li
Computer Science
-
Article
IAFPN: interlayer enhancement and multilayer fusion network for object detection
Feature pyramid network (FPN) improves object detection performance by means of top-down multilevel feature fusion. However, the current FPN-based methods have not effectively utilized the interlayer features ...
-
Article
Towards domain adaptation underwater image enhancement and restoration
Currently, deep convolutional neural networks have made significant research progress in the field of underwater image enhancement and restoration. However, most of the existing methods use fixed-scale convolu...
-
Chapter and Conference Paper
Punctuation Matters! Stealthy Backdoor Attack for Language Models
Recent studies have pointed out that natural language processing (NLP) models are vulnerable to backdoor attacks. A backdoored model produces normal outputs on the clean samples while performing improperly on ...
-
Chapter and Conference Paper
IMTM: Invisible Multi-trigger Multimodal Backdoor Attack
Computer Vision and Natural Language Processing have made significant advancements, leading to the emergence of multimodal models that seamlessly integrate diverse input modalities. While these models hold gre...
-
Chapter and Conference Paper
Vulnerability Analysis of Continuous Prompts for Pre-trained Language Models
Prompt-based learning has recently emerged as a promising approach for handling the increasing complexity of downstream natural language processing (NLP) tasks, achieving state-of-the-art performance without u...
-
Chapter and Conference Paper
Pancreatic Image Augmentation Based on Local Region Texture Synthesis for Tumor Segmentation
High-accuracy segmentation of lesions in pancreatic images is essential for computer-aided precision diagnosis and treatment. The segmentation accuracy of deep learning-based segmentation models depends on the...
-
Chapter and Conference Paper
Enhanced Spatial Awareness for Deep Interactive Image Segmentation
Existing deep interactive segmentation approaches can extract the desired object for the user based on simple click interaction. However, the first click provided by the user on the full image space domain is ...
-
Chapter and Conference Paper
Pancreatic Neoplasm Image Translation Based on Feature Correlation Analysis of Cross-Phase Image
CT arterial phase images can provide a powerful auxiliary to formulate pancreatic neoplasm diagnosis and treatment plans. In the absence of such images, we can use the image translation model convert CT images...
-
Chapter and Conference Paper
3D Deep Residual Encoder-Decoder CNNS with Squeeze-and-Excitation for Brain Tumor Segmentation
Segmenting brain tumors from multimodal MR scans is thought to be highly beneficial for brain abnormality diagnosis, prognosis monitoring, and treatment evaluation. Due to the highly heterogeneous appearance a...
-
Chapter and Conference Paper
Nighttime Haze Removal with Fusion Atmospheric Light and Improved Entropy
Haze removal is important for the normal work of computer vision system. However, most of the existing image dehazing methods are aimed at daytime haze images. These methods cannot always work well for night h...
-
Chapter and Conference Paper
Edge-aware Local Laplacian Filters for Medical X-Ray Image Enhancement
This paper proposed a method of edge-aware image processing using standard Laplacian pyramid for medical X-ray image enhancement. It combines edge-aware image processing with multi-scale medical image enhancem...
-
Chapter and Conference Paper
Group Visible Nearest Neighbor Queries in Spatial Databases
Traditional nearest neighbor queries and its variants, such as Group Nearest Neighbor Query (GNN), have been widely studied by many researchers. Recently obstacles are involved in spatial queries. The existence o...
