Search Results for author:
Found 10 papers, 2 papers with code
Evaluating Hierarchical Document Categorisation
Hierarchical document categorisation is a special case of multi-label document categorisation, where there is a taxonomic hierarchy among the labels.
On Active Privacy Auditing in Supervised Fine-tuning for White-Box Language Models
To help develop more privacy-resilient fine-tuning models, we introduce a novel active privacy auditing framework, dubbed Parsing, designed to identify and quantify privacy leakage risks during the supervised fine-tuning (SFT) of language models (LMs).
Horizon-wise Learning Paradigm Promotes Gene Splicing Identification
In this paper, we propose a novel framework for the task of gene splicing identification, named Horizon-wise Gene Splicing Identification (H-GSI).
Semi-Weakly Supervised Object Kinematic Motion Prediction
First, although 3D dataset with fully annotated motion labels is limited, there are existing datasets and methods for object part semantic segmentation at large scale.
Search By Image: Deeply Exploring Beneficial Features for Beauty Product Retrieval
Searching by image is popular yet still challenging due to the extensive interference arose from i) data variations (e. g., background, pose, visual angle, brightness) of real-world captured images and ii) similar images in the query dataset.
OPE-SR: Orthogonal Position Encoding for Designing a Parameter-free Upsampling Module in Arbitrary-scale Image Super-Resolution
Motivated by position encoding, we propose orthogonal position encoding (OPE) - an extension of position encoding - and an OPE-Upscale module to replace the INR-based upsampling module for arbitrary-scale image super-resolution.
Semantic Segmentation by Improved Generative Adversarial Networks
Besides, the adversarial loss aggressively encourages the output image to be close to the distribution of the ground truth.
Superpixel Segmentation with Fully Convolutional Networks
In computer vision, superpixels have been widely used as an effective way to reduce the number of image primitives for subsequent processing.
Stochastic Coordinate Coding and Its Application for Drosophila Gene Expression Pattern Annotation
The effectiveness of gene expression pattern annotation relies on the quality of feature representation.
A Two-Stage Weighting Framework for Multi-Source Domain Adaptation
In this paper we propose a two-stage domain adaptation methodology which combines weighted data from multiple sources based on marginal probability differences (first stage) as well as conditional probability differences (second stage), with the target domain data.
