30 citations · 68 across the 9 of their papers we have counts for
10 papers
Neuro-Symbolic Predicate Learning for Semantic Safe Robot Control
Zihan Ye, Jiayi Liu, Puze Liu +4
As robots are increasingly deployed in everyday environments, ensuring their safety has become a central challenge. Existing methods often encode safety requirements as opaque math…
Segment Anything with Robust Uncertainty-Accuracy Correlation
Hongyou Zhou, Marc Toussaint, Ling Shao +1
Despite strong zero-shot performance, SAM is unreliable under domain shift due to Mask-level Confidence Confusion (MCC), where a single IoU-based mask score fails to reflect pixel-…
Neural Meta-Symbolic Reasoning and Learning
Zihan Ye, Hikaru Shindo, Devendra Singh Dhami +1
Deep neural learning uses an increasing amount of computation and data to solve very specific problems. By stark contrast, human minds solve a wide range of problems using a fixed…
SSD: Towards Better Text-Image Consistency Metric in Text-to-Image Generation
Zhaorui Tan, Xi Yang, Zihan Ye +4
Generating consistent and high-quality images from given texts is essential for visual-language understanding. Although impressive results have been achieved in generating high-qua…
Rebalanced Zero-shot Learning
Zihan Ye, Guanyu Yang, Xiaobo Jin +2
Zero-shot learning (ZSL) aims to identify unseen classes with zero samples during training. Broadly speaking, present ZSL methods usually adopt class-level semantic labels and comp…
A Unified Perspective on Natural Gradient Variational Inference with Gaussian Mixture Models
Oleg Arenz, Philipp Dahlinger, Zihan Ye +2
Variational inference with Gaussian mixture models (GMMs) enables learning of highly tractable yet multi-modal approximations of intractable target distributions with up to a few h…
Disentangling Semantic-to-visual Confusion for Zero-shot Learning
Zihan Ye, Fuyuan Hu, Fan Lyu +2
Using generative models to synthesize visual features from semantic distribution is one of the most popular solutions to ZSL image classification in recent years. The triplet loss…
Multi-Domain Multi-Task Rehearsal for Lifelong Learning
Fan Lyu, Shuai Wang, Wei Feng +3
Rehearsal, seeking to remind the model by storing old knowledge in lifelong learning, is one of the most effective ways to mitigate catastrophic forgetting, i.e., biased forgetting…
Associating Multi-Scale Receptive Fields for Fine-grained Recognition
Zihan Ye, Fuyuan Hu, Yin Liu +3
Extracting and fusing part features have become the key of fined-grained image recognition. Recently, Non-local (NL) module has shown excellent improvement in image recognition. Ho…
SR-GAN: Semantic Rectifying Generative Adversarial Network for Zero-shot Learning
Zihan Ye, Fan Lyu, Linyan Li +3
The existing Zero-Shot learning (ZSL) methods may suffer from the vague class attributes that are highly overlapped for different classes. Unlike these methods that ignore the disc…