Search Results for author:
Found 24 papers, 15 papers with code
Cross-modal Contrastive Attention Model for Medical Report Generation
Medical report automatic generation has gained increasing interest recently as a way to help radiologists write reports more efficiently.
NTIRE 2024 Challenge on Image Super-Resolution ($\times$4): Methods and Results
This paper reviews the NTIRE 2024 challenge on image super-resolution ($\times$4), highlighting the solutions proposed and the outcomes obtained.
IDF-CR: Iterative Diffusion Process for Divide-and-Conquer Cloud Removal in Remote-sensing Images
IDF-CR consists of a pixel space cloud removal module (Pixel-CR) and a latent space iterative noise diffusion network (IND).
Image Restoration Through Generalized Ornstein-Uhlenbeck Bridge
Diffusion models possess powerful generative capabilities enabling the mapping of noise to data using reverse stochastic differential equations.
Towards Real-World Burst Image Super-Resolution: Benchmark and Method
Despite substantial advances, single-image super-resolution (SISR) is always in a dilemma to reconstruct high-quality images with limited information from one input image, especially in realistic scenarios.
Identity-Preserving Talking Face Generation with Landmark and Appearance Priors
Prior landmark characteristics of the speaker's face are employed to make the generated landmarks coincide with the facial outline of the speaker.
Masked Images Are Counterfactual Samples for Robust Fine-tuning
In this paper, based on causal analysis of the aforementioned problems, we propose a novel fine-tuning method, which uses masked images as counterfactual samples that help improve the robustness of the fine-tuning model.
TopoSeg: Topology-Aware Nuclear Instance Segmentation
Experiments on three nuclear instance segmentation datasets justify the superiority of TopoSeg, which achieves state-of-the-art performance.
DQnet: Cross-Model Detail Querying for Camouflaged Object Detection
Optimizing a convolutional neural network (CNN) for camouflaged object detection (COD) tends to activate local discriminative regions while ignoring complete object extent, causing the partial activation issue which inevitably leads to missing or redundant regions of objects.
Out-of-Candidate Rectification for Weakly Supervised Semantic Segmentation
Weakly supervised semantic segmentation is typically inspired by class activation maps, which serve as pseudo masks with class-discriminative regions highlighted.
Optical Character Recognition (OCR)
Weakly supervised Semantic Segmentation
+1
DreamArtist: Towards Controllable One-Shot Text-to-Image Generation via Positive-Negative Prompt-Tuning
Although recent attempts have employed fine-tuning or prompt-tuning strategies to teach the pre-trained diffusion model novel concepts from a reference image set, they have the drawback of overfitting to the given reference images, particularly in one-shot applications, which is harmful to generate diverse and high-quality images while maintaining generation controllability.
Robust Real-World Image Super-Resolution against Adversarial Attacks
Since the frequency masking may not only destroys the adversarial perturbations but also affects the sharp details in a clean image, we further develop an adversarial sample classifier based on the frequency domain of images to determine if applying the proposed mask module.
Adversarially-Aware Robust Object Detector
In this work, we empirically explore the model training for adversarial robustness in object detection, which greatly attributes to the conflict between learning clean images and adversarial images.
Real-World Image Super-Resolution by Exclusionary Dual-Learning
Real-world image super-resolution is a practical image restoration problem that aims to obtain high-quality images from in-the-wild input, has recently received considerable attention with regard to its tremendous application potentials.
Dual Adversarial Adaptation for Cross-Device Real-World Image Super-Resolution
To address this issue, we propose an unsupervised domain adaptation mechanism for real-world SR, named Dual ADversarial Adaptation (DADA), which only requires LR images in the target domain with available real paired data from a source camera.
NTIRE 2022 Challenge on Super-Resolution and Quality Enhancement of Compressed Video: Dataset, Methods and Results
This challenge includes three tracks.
Open Set Domain Adaptation By Novel Class Discovery
In Open Set Domain Adaptation (OSDA), large amounts of target samples are drawn from the implicit categories that never appear in the source domain.
Trash to Treasure: Harvesting OOD Data with Cross-Modal Matching for Open-Set Semi-Supervised Learning
Open-set semi-supervised learning (open-set SSL) investigates a challenging but practical scenario where out-of-distribution (OOD) samples are contained in the unlabeled data.
CDNet: Centripetal Direction Network for Nuclear Instance Segmentation
Specifically, we define the centripetal direction feature as a class of adjacent directions pointing to the nuclear center to represent the spatial relationship between pixels within the nucleus.
AIM 2020 Challenge on Real Image Super-Resolution: Methods and Results
This paper introduces the real image Super-Resolution (SR) challenge that was part of the Advances in Image Manipulation (AIM) workshop, held in conjunction with ECCV 2020.
Component Divide-and-Conquer for Real-World Image Super-Resolution
Learning an SR model with conventional pixel-wise loss usually is easily dominated by flat regions and edges, and fails to infer realistic details of complex textures.
A Near-Optimal Gradient Flow for Learning Neural Energy-Based Models
To solve this problem, we derive a second-order Wasserstein gradient flow of the global relative entropy from Fokker-Planck equation.
Min-Entropy Latent Model for Weakly Supervised Object Detection
Weakly supervised object detection is a challenging task when provided with image category supervision but required to learn, at the same time, object locations and object detectors.
3D Human Pose Machines with Self-supervised Learning
Driven by recent computer vision and robotic applications, recovering 3D human poses has become increasingly important and attracted growing interests.
Ranked #263 on
3D Human Pose Estimation
on Human3.6M
