Search Results for author:
Found 7 papers, 2 papers with code
FairRAG: Fair Human Generation via Fair Retrieval Augmentation
In this work, we introduce Fair Retrieval Augmented Generation (FairRAG), a novel framework that conditions pre-trained generative models on reference images retrieved from an external image database to improve fairness in human generation.
Semi-Supervised Learning for Anomaly Traffic Detection via Bidirectional Normalizing Flows
We consider the problem of anomaly network traffic detection and propose a three-stage anomaly detection framework using only normal traffic.
Cluster-level Feature Alignment for Person Re-identification
Instance-level alignment is widely exploited for person re-identification, e. g. spatial alignment, latent semantic alignment and triplet alignment.
Ranked #30 on
Person Re-Identification
on DukeMTMC-reID
Adaptive Fractional Dilated Convolution Network for Image Aesthetics Assessment
Specifically, the fractional dilated kernel is adaptively constructed according to the image aspect ratios, where the interpolation of nearest two integers dilated kernels is used to cope with the misalignment of fractional sampling.
Embedding Complementary Deep Networks for Image Classification
In this paper, a deep embedding algorithm is developed to achieve higher accuracy rates on large-scale image classification.
Deep Boosting of Diverse Experts
In this paper, a deep boosting algorithm is developed to learn more discriminative ensemble classifier by seamlessly combining a set of base deep CNNs (base experts) with diverse capabilities, e. g., these base deep CNNs are sequentially trained to recognize a set of object classes in an easy-to-hard way according to their learning complexities.
Virtual Blood Vessels in Complex Background using Stereo X-ray Images
We propose a fully automatic system to reconstruct and visualize 3D blood vessels in Augmented Reality (AR) system from stereo X-ray images with bones and body fat.
