Search Results for author:
Found 22 papers, 8 papers with code
Filter or Compensate: Towards Invariant Representation from Distribution Shift for Anomaly Detection
Recent Anomaly Detection (AD) methods have achieved great success with In-Distribution (ID) data.
Fleximo: Towards Flexible Text-to-Human Motion Video Generation
Current methods for generating human motion videos rely on extracting pose sequences from reference videos, which restricts flexibility and control.
Poisson Ordinal Network for Gleason Group Estimation Using Bi-Parametric MRI
The Gleason groups serve as the primary histological grading system for prostate cancer, providing crucial insights into the cancer's potential for growth and metastasis.
Camera-Invariant Meta-Learning Network for Single-Camera-Training Person Re-identification
Previous methods address it by assuming that the most similar person should be found in another camera.
PracticalDG: Perturbation Distillation on Vision-Language Models for Hybrid Domain Generalization
Domain Generalization (DG) aims to resolve distribution shifts between source and target domains, and current DG methods are default to the setting that data from source and target domains share identical categories.
Selection, Ensemble, and Adaptation: Advancing Multi-Source-Free Domain Adaptation via Architecture Zoo
This paper introduces Zoo-MSFDA, a more general setting that allows each source domain to offer a zoo of multiple source models with different architectures.
Instance Paradigm Contrastive Learning for Domain Generalization
In this paper, we propose an instance paradigm contrastive learning framework, introducing contrast between original features and novel paradigms to alleviate domain-specific distractions.
EviPrompt: A Training-Free Evidential Prompt Generation Method for Segment Anything Model in Medical Images
Then, we incorporate the human prior into the prompts, which is vital for alleviating the domain gap between natural and medical images and enhancing the applicability and usefulness of SAM in medical scenarios.
Incorporating Pre-training Data Matters in Unsupervised Domain Adaptation
To answer the first question, we empirically observed an interesting Spontaneous Pulling (SP) Effect in fine-tuning where the discrepancies between any two of the three domains (ImageNet, Source, Target) decrease but at the cost of the impaired semantic structure of the pre-train domain.
Causality-based Dual-Contrastive Learning Framework for Domain Generalization
In this paper, we propose a Dual-Contrastive Learning (DCL) module on feature and prototype contrast.
Uncertainty-Induced Transferability Representation for Source-Free Unsupervised Domain Adaptation
Secondly, based on the UTR, we propose a novel Calibrated Adaption Framework (CAF) for SFUDA, including i)the source knowledge calibration module that guides the target model to learn the transferable source knowledge and discard the non-transferable one, and ii)the target semantics calibration module that calibrates the unreliable semantics.
Delving into the Continuous Domain Adaptation
Existing domain adaptation methods assume that domain discrepancies are caused by a few discrete attributes and variations, e. g., art, real, painting, quickdraw, etc.
Bag of Tricks for Out-of-Distribution Generalization
Recently, out-of-distribution (OOD) generalization has attracted attention to the robustness and generalization ability of deep learning based models, and accordingly, many strategies have been made to address different aspects related to this issue.
Seeing your sleep stage: cross-modal distillation from EEG to infrared video
$S^3VE$ is a large-scale dataset including synchronized infrared video and EEG signal for sleep stage classification, including 105 subjects and 154, 573 video clips that is more than 1100 hours long.
Rethinking the constraints of multimodal fusion: case study in Weakly-Supervised Audio-Visual Video Parsing
For multimodal tasks, a good feature extraction network should extract information as much as possible and ensure that the extracted feature embedding and other modal feature embedding have an excellent mutual understanding.
Taylor saves for later: disentanglement for video prediction using Taylor representation
We propose a two-branch seq-to-seq deep model to disentangle the Taylor feature and the residual feature in video frames by a novel recurrent prediction module (TaylorCell) and residual module.
Bridge the Vision Gap from Field to Command: A Deep Learning Network Enhancing Illumination and Details
With the goal of tuning up the brightness, low-light image enhancement enjoys numerous applications, such as surveillance, remote sensing and computational photography.
Shed Various Lights on a Low-Light Image: Multi-Level Enhancement Guided by Arbitrary References
This paper proposes a neural network for multi-level low-light image enhancement, which is user-friendly to meet various requirements by selecting different images as brightness reference.
A Switched View of Retinex: Deep Self-Regularized Low-Light Image Enhancement
The generated reflectance, which is assumed to be irrelevant of illumination by Retinex, is treated as enhanced brightness.
Split to Be Slim: An Overlooked Redundancy in Vanilla Convolution
Therefore, instead of directly removing uncertain redundant features, we propose a \textbf{sp}lit based \textbf{conv}olutional operation, namely SPConv, to tolerate features with similar patterns but require less computation.
Pyramid Real Image Denoising Network
Second, at the multi-scale denoising stage, pyramid pooling is utilized to extract multi-scale features.
Ranked #2 on
Color Image Denoising
on Darmstadt Noise Dataset
Microwave breast cancer detection using Empirical Mode Decomposition features
One of the most widely used feature extraction method is principle component analysis (PCA).
