Search Results for author:
Found 5 papers, 2 papers with code
Improve Cross-domain Mixed Sampling with Guidance Training for Adaptive Segmentation
Typically, various prevailing methods baseline rely on constructing intermediate domains via cross-domain mixed sampling techniques to mitigate the performance decline caused by domain gaps.
Ranked #8 on
Domain Adaptation
on SYNTHIA-to-Cityscapes
LBL: Logarithmic Barrier Loss Function for One-class Classification
To address this issue, then, a unilateral relaxation Sigmoid function is introduced into LBL and a novel OCC loss named LBLSig is proposed.
Self-Annotated Training for Controllable Image Captioning
In this paper, we propose a novel reinforcement training method for structure-related control signals: Self-Annotated Training (SAT), to improve both the accuracy and controllability of CIC models.
Macroscopic Control of Text Generation for Image Captioning
With such a control signal, the controllability and diversity of existing captioning models are enhanced.
Multi-Model Least Squares-Based Recomputation Framework for Large Data Analysis
Most multilayer least squares (LS)-based neural networks are structured with two separate stages: unsupervised feature encoding and supervised pattern classification.
