Search Results for author:
Found 6 papers, 2 papers with code
SAAS: Solving Ability Amplification Strategy for Enhanced Mathematical Reasoning in Large Language Models
We focus on integrating the Chain-of-Thought (CoT) and the Program-of-Thought (PoT) learning, hypothesizing that prioritizing the learning of mathematical reasoning ability is helpful for the amplification of problem-solving ability.
Highway Driving Dataset for Semantic Video Segmentation
Together with our attempt to analyze the temporal correlation, we expect the Highway Driving dataset to encourage research on semantic video segmentation.
Collaborative Method for Incremental Learning on Classification and Generation
In this paper, we introduce a novel algorithm, Incremental Class Learning with Attribute Sharing (ICLAS), for incremental class learning with deep neural networks.
Adjusting Decision Boundary for Class Imbalanced Learning
Inspired by observations, we investigate how the class imbalance affects the decision boundary and deteriorates the performance.
Learning Not to Learn: Training Deep Neural Networks with Biased Data
We propose a novel regularization algorithm to train deep neural networks, in which data at training time is severely biased.
Mimicking Ensemble Learning with Deep Branched Networks
This paper proposes a branched residual network for image classification.
