12 citations · 22 across the 12 of their papers we have counts for
12 papers
Unbiased Alignment for Large Language Models with Noisy Preferences
Jialiang Wang, Xianming Liu, Xiong Zhou +2
The alignment of large language models with human preferences is commonly achieved through Reinforcement Learning from Human Feedback or Direct Preference Optimization. However, th…
Variation-Bounded Loss for Noise-Tolerant Learning
Jialiang Wang, Xiong Zhou, Xianming Liu +4
Mitigating the negative impact of noisy labels has been aperennial issue in supervised learning. Robust loss functions have emerged as a prevalent solution to this problem. In this…
-Softmax: Approximating One-Hot Vectors for Mitigating Label Noise
Jialiang Wang, Xiong Zhou, Deming Zhai +3
Noisy labels pose a common challenge for training accurate deep neural networks. To mitigate label noise, prior studies have proposed various robust loss functions to achieve noise…
Neural Field Classifiers via Target Encoding and Classification Loss
Xindi Yang, Zeke Xie, Xiong Zhou +6
Neural field methods have seen great progress in various long-standing tasks in computer vision and computer graphics, including novel view synthesis and geometry reconstruction. A…
On the Dynamics Under the Unhinged Loss and Beyond
Xiong Zhou, Xianming Liu, Hanzhang Wang +3
Recent works have studied implicit biases in deep learning, especially the behavior of last-layer features and classifier weights. However, they usually need to simplify the interm…
Prototype-Anchored Learning for Learning with Imperfect Annotations
Xiong Zhou, Xianming Liu, Deming Zhai +3
The success of deep neural networks greatly relies on the availability of large amounts of high-quality annotated data, which however are difficult or expensive to obtain. The resu…
Learning Towards the Largest Margins
Xiong Zhou, Xianming Liu, Deming Zhai +3
One of the main challenges for feature representation in deep learning-based classification is the design of appropriate loss functions that exhibit strong discriminative power. Th…
ReSmooth: Detecting and Utilizing OOD Samples when Training with Data Augmentation
Chenyang Wang, Junjun Jiang, Xiong Zhou +1
Data augmentation (DA) is a widely used technique for enhancing the training of deep neural networks. Recent DA techniques which achieve state-of-the-art performance always meet th…
Learning with Noisy Labels via Sparse Regularization
Xiong Zhou, Xianming Liu, Chenyang Wang +3
Learning with noisy labels is an important and challenging task for training accurate deep neural networks. Some commonly-used loss functions, such as Cross Entropy (CE), suffer fr…
Asymmetric Loss Functions for Learning with Noisy Labels
Xiong Zhou, Xianming Liu, Junjun Jiang +2
Robust loss functions are essential for training deep neural networks with better generalization power in the presence of noisy labels. Symmetric loss functions are confirmed to be…
Exploiting Invariance in Training Deep Neural Networks
Chengxi Ye, Xiong Zhou, Tristan McKinney +3
Inspired by two basic mechanisms in animal visual systems, we introduce a feature transform technique that imposes invariance properties in the training of deep neural networks. Th…
Out-of-the-box channel pruned networks
Ragav Venkatesan, Gurumurthy Swaminathan, Xiong Zhou +1
In the last decade convolutional neural networks have become gargantuan. Pre-trained models, when used as initializers are able to fine-tune ever larger networks on small datasets.…