Jian Zhang

Unsupervised visual domain adaptation via dictionary evolution

2016

In real-word visual applications, distribution mismatch between samples from different domains may significantly degrade classification performance. To improve the generalization capability of classifier across domains, domain adaptation has attracted a lot of interest in computer …

Page File-Oriented Web Application Design

2016

This paper provides a Web application design method, page file-oriented Web application design with relevant concept and the corresponding definitions for the variety of Web application development, technology and software engineering. We provide the page …

Relational Mimic for Visual Adversarial Imitation Learning

2019 · arXiv (Cornell University)

In this work, we introduce a new method for imitation learning from video demonstrations. Our method, Relational Mimic (RM), improves on previous visual imitation learning methods by combining generative adversarial networks and relational learning. RM …

RRL-GAT: Graph Attention Network-Driven Multilabel Image Robust Representation Learning

2021 · IEEE Internet of Things Journal

Exploring the characterization laws of image data and improving the efficiency of image data characterization knowledge is essential to promote the development of the Internet of Things technology. Considering that images in the real world …

PTN: A Poisson Transfer Network for Semi-supervised Few-shot Learning

2020 · arXiv (Cornell University)

The predicament in semi-supervised few-shot learning (SSFSL) is to maximize the value of the extra unlabeled data to boost the few-shot learner. In this paper, we propose a Poisson Transfer Network (PTN) to mine the …

Analysis and research on breakdown cause of lightning arrester at low voltage side of 220kV transformer

2022 · Journal of Physics Conference Series

Abstract This paper describes an event of zinc oxide arrester breakdown at low voltage side due to single-phase grounding at medium voltage side of 220kV transformer. Combined with the system wiring mode, equipment damage, system …

Constructing Sample-to-Class Graph for Few-Shot Class-Incremental Learning

2023 · arXiv (Cornell University)

Few-shot class-incremental learning (FSCIL) aims to build machine learning model that can continually learn new concepts from a few data samples, without forgetting knowledge of old classes. The challenges of FSCIL lies in the limited …

Detecting Memory Errors in Python Native Code by Tracking Object Lifecycle with Reference Count

2023

Third-party Python modules are usually implemented as binary extensions by using native code (C/C++) to provide additional features and runtime acceleration. In native code, the heap-allocated PyObjects are managed by the reference counting mechanism provided …

Label-Efficient Few-Shot Semantic Segmentation with Unsupervised Meta-Training

2024 · Proceedings of the AAAI Conference on Artificial Intelligence

The goal of this paper is to alleviate the training cost for few-shot semantic segmentation (FSS) models. Despite that FSS in nature improves model generalization to new concepts using only a handful of test exemplars, …

Retrieval Augmented Instruction Tuning for Open NER with Large Language Models

2024 · arXiv (Cornell University)

The strong capability of large language models (LLMs) has been applied to information extraction (IE) through either retrieval augmented prompting or instruction tuning (IT). However, the best way to incorporate information with LLMs for IE …

Causal Graphs Meet Thoughts: Enhancing Complex Reasoning in Graph-Augmented LLMs

2025 · arXiv (Cornell University)

In knowledge-intensive tasks, especially in high-stakes domains like medicine and law, it is critical not only to retrieve relevant information but also to provide causal reasoning and explainability. Large language models (LLMs) have achieved remarkable …

FedFLD: Heterogeneous Federated Learning via Forget-Less Distillation

2025

Federated learning, as a distributed machine learning paradigm, enhances privacy protection but faces the challenge of heterogeneity. Data-free knowledge distillation (DFKD) methods attempt to overcome this challenge by using a generator to synthesize samples for …

أوراق هذا المؤلف