Search Results for author:
Found 13 papers, 3 papers with code
Higher Layers Need More LoRA Experts
In this paper, we introduce a novel parameter-efficient MoE method, \textit{\textbf{M}oE-L\textbf{o}RA with \textbf{L}ayer-wise Expert \textbf{A}llocation (MoLA)} for Transformer-based models, where each model layer has the flexibility to employ a varying number of LoRA experts.
Evaluation and Enhancement of Semantic Grounding in Large Vision-Language Models
Large Vision-Language Models (LVLMs) offer remarkable benefits for a variety of vision-language tasks.
Tackling Vision Language Tasks Through Learning Inner Monologues
Visual language tasks require AI models to comprehend and reason with both visual and textual content.
Augmenting Vision Language Pretraining by Learning Codebook with Visual Semantics
Language modality within the vision language pretraining framework is innately discretized, endowing each word in the language vocabulary a semantic meaning.
OSCARS: An Outlier-Sensitive Content-Based Radiography Retrieval System
While existing methods can be applied for class-wise retrieval (aka.
MedShift: identifying shift data for medical dataset curation
Given an internal dataset A as the base source, we first train anomaly detectors for each class of dataset A to learn internal distributions in an unsupervised way.
CVAD: A generic medical anomaly detector based on Cascade VAE
The key issue is the granularity of OOD data in the medical domain, where intra-class OOD samples are predominant.
Margin-Aware Intra-Class Novelty Identification for Medical Images
Traditional anomaly detection methods focus on detecting inter-class variations while medical image novelty identification is inherently an intra-class detection problem.
Liver Steatosis Segmentation with Deep Learning Methods
Liver steatosis is known as the abnormal accumulation of lipids within cells.
Clumped Nuclei Segmentation with Adjacent Point Match and Local Shape based Intensity Analysis for Overlapped Nuclei in Fluorescence In-Situ Hybridization Images
Highly clumped nuclei clusters captured in fluorescence in situ hybridization microscopy images are common histology entities under investigations in a wide spectrum of tissue-related biomedical investigations.
PortraitGAN for Flexible Portrait Manipulation
Previous methods have dealt with discrete manipulation of facial attributes such as smile, sad, angry, surprise etc, out of canonical expressions and they are not scalable, operating in single modality.
Multi-Modality Fusion based on Consensus-Voting and 3D Convolution for Isolated Gesture Recognition
Recently, the popularity of depth-sensors such as Kinect has made depth videos easily available while its advantages have not been fully exploited.
