Search Results for author: Tong Wei

Found 27 papers, 16 papers with code

Continuous Contrastive Learning for Long-Tailed Semi-Supervised Recognition

1 code implementation8 Oct 2024 Zi-Hao Zhou, Siyuan Fang, Zi-Jing Zhou, Tong Wei, Yuanyu Wan, Min-Ling Zhang

By progressively estimating the underlying label distribution and optimizing its alignment with model predictions, we tackle the diverse distribution of unlabeled data in real-world scenarios.

Contrastive Learning Density Estimation +1

Vision-Language Models are Strong Noisy Label Detectors

1 code implementation29 Sep 2024 Tong Wei, Hao-Tian Li, Chun-Shu Li, Jiang-Xin Shi, Yu-Feng Li, Min-Ling Zhang

The proposed framework establishes a noisy label detector by learning positive and negative textual prompts for each class.

Denoising Image Classification +1

Breaking the Frame: Visual Place Recognition by Overlap Prediction

1 code implementation23 Jun 2024 Tong Wei, Philipp Lindenberger, Jiri Matas, Daniel Barath

We propose a novel visual place recognition approach based on overlap prediction, called VOP, shifting from traditional reliance on global image similarities and local features to image overlap prediction.

Image Retrieval Pose Estimation +3

Boosting Consistency in Dual Training for Long-Tailed Semi-Supervised Learning

1 code implementation19 Jun 2024 Kai Gan, Tong Wei, Min-Ling Zhang

While long-tailed semi-supervised learning (LTSSL) has received tremendous attention in many real-world classification problems, existing LTSSL algorithms typically assume that the class distributions of labeled and unlabeled data are almost identical.

Efficient and Long-Tailed Generalization for Pre-trained Vision-Language Model

1 code implementation18 Jun 2024 Jiang-Xin Shi, Chi Zhang, Tong Wei, Yu-Feng Li

For efficient adaptation, we treat the CLIP model as a black box and leverage the extracted features to obtain visual and textual prototypes for prediction.

Image-text matching Language Modeling +2

Erasing the Bias: Fine-Tuning Foundation Models for Semi-Supervised Learning

1 code implementation20 May 2024 Kai Gan, Tong Wei

Semi-supervised learning (SSL) has witnessed remarkable progress, resulting in the emergence of numerous method variations.

Fire in SRRN: Next-Gen 3D Temperature Field Reconstruction Technology

1 code implementation10 May 2024 Shenxiang Feng, Xiaojian Hao, Xiaodong Huang, Pan Pei, Tong Wei, Chenyang Xu

This method utilizes the flame thermal radiation characteristics and differentiable rendering in graphics, and combines it with a multi-layer perceptron to achieve a functional representation of the flame temperature field.

Optimal and Efficient Algorithms for Decentralized Online Convex Optimization

no code implementations14 Feb 2024 Yuanyu Wan, Tong Wei, Bo Xue, Mingli Song, Lijun Zhang

Our analysis reveals that the projection-free variant can achieve ${O}(nT^{3/4})$ and ${O}(nT^{2/3}(\log T)^{1/3})$ regret bounds for convex and strongly convex functions with nearly optimal $\tilde{O}(\rho^{-1/2}\sqrt{T})$ and $\tilde{O}(\rho^{-1/2}T^{1/3}(\log T)^{2/3})$ communication rounds, respectively.

EAT: Towards Long-Tailed Out-of-Distribution Detection

1 code implementation14 Dec 2023 Tong Wei, Bo-Lin Wang, Min-Ling Zhang

The main difficulty lies in distinguishing OOD data from samples belonging to the tail classes, as the ability of a classifier to detect OOD instances is not strongly correlated with its accuracy on the in-distribution classes.

Long-tail Learning Out-of-Distribution Detection +1

Bridging the Gap: Learning Pace Synchronization for Open-World Semi-Supervised Learning

1 code implementation21 Sep 2023 Bo Ye, Kai Gan, Tong Wei, Min-Ling Zhang

In open-world semi-supervised learning, a machine learning model is tasked with uncovering novel categories from unlabeled data while maintaining performance on seen categories from labeled data.

Novel Class Discovery Open-World Semi-Supervised Learning +1

Long-Tail Learning with Foundation Model: Heavy Fine-Tuning Hurts

1 code implementation18 Sep 2023 Jiang-Xin Shi, Tong Wei, Zhi Zhou, Jie-Jing Shao, Xin-Yan Han, Yu-Feng Li

The fine-tuning paradigm in addressing long-tail learning tasks has sparked significant interest since the emergence of foundation models.

 Ranked #1 on Long-tail Learning on CIFAR-100-LT (ρ=100) (using extra training data)

Fine-Grained Image Classification Long-tail learning with class descriptors

Scene-Aware Feature Matching

no code implementations ICCV 2023 Xiaoyong Lu, Yaping Yan, Tong Wei, Songlin Du

Current feature matching methods focus on point-level matching, pursuing better representation learning of individual features, but lacking further understanding of the scene.

Homography Estimation Pose Estimation +1

RIS-Aided Wideband Holographic DFRC

no code implementations8 May 2023 Tong Wei, Linlong Wu, Kumar Vijay Mishra, M. R. Bhavani Shankar

This surface is crucial for designing compact low-cost wideband wireless systems, wherein ultra-massive antenna arrays are required to compensate for the losses incurred by severe attenuation and diffraction.

Towards Realistic Long-Tailed Semi-Supervised Learning: Consistency Is All You Need

1 code implementation CVPR 2023 Tong Wei, Kai Gan

While long-tailed semi-supervised learning (LTSSL) has received tremendous attention in many real-world classification problems, existing LTSSL algorithms typically assume that the class distributions of labeled and unlabeled data are almost identical.

Generalized Differentiable RANSAC

2 code implementations ICCV 2023 Tong Wei, Yash Patel, Alexander Shekhovtsov, Jiri Matas, Daniel Barath

We propose $\nabla$-RANSAC, a generalized differentiable RANSAC that allows learning the entire randomized robust estimation pipeline.

Point Cloud Registration

A Survey on Extreme Multi-label Learning

4 code implementations8 Oct 2022 Tong Wei, Zhen Mao, Jiang-Xin Shi, Yu-Feng Li, Min-Ling Zhang

Multi-label learning has attracted significant attention from both academic and industry field in recent decades.

Multi-Label Learning Survey

Revisiting Discrete Soft Actor-Critic

1 code implementation21 Sep 2022 Haibin Zhou, Tong Wei, Zichuan Lin, Junyou Li, Junliang Xing, Yuanchun Shi, Li Shen, Chao Yu, Deheng Ye

We study the adaption of Soft Actor-Critic (SAC), which is considered as a state-of-the-art reinforcement learning (RL) algorithm, from continuous action space to discrete action space.

Atari Games Q-Learning +1

Transfer and Share: Semi-Supervised Learning from Long-Tailed Data

no code implementations26 May 2022 Tong Wei, Qian-Yu Liu, Jiang-Xin Shi, Wei-Wei Tu, Lan-Zhe Guo

TRAS transforms the imbalanced pseudo-label distribution of a traditional SSL model via a delicate function to enhance the supervisory signals for minority classes.

Pseudo Label Representation Learning

Adaptive Reordering Sampler with Neurally Guided MAGSAC

1 code implementation ICCV 2023 Tong Wei, Jiri Matas, Daniel Barath

We propose a new sampler for robust estimators that always selects the sample with the highest probability of consisting only of inliers.

Prototypical Classifier for Robust Class-Imbalanced Learning

no code implementations22 Oct 2021 Tong Wei, Jiang-Xin Shi, Yu-Feng Li, Min-Ling Zhang

Deep neural networks have been shown to be very powerful methods for many supervised learning tasks.

Learning with noisy labels

Robust Long-Tailed Learning under Label Noise

no code implementations26 Aug 2021 Tong Wei, Jiang-Xin Shi, Wei-Wei Tu, Yu-Feng Li

To overcome this limitation, we establish a new prototypical noise detection method by designing a distance-based metric that is resistant to label noise.

Image Classification

NGC: A Unified Framework for Learning with Open-World Noisy Data

no code implementations ICCV 2021 Zhi-Fan Wu, Tong Wei, Jianwen Jiang, Chaojie Mao, Mingqian Tang, Yu-Feng Li

The existence of noisy data is prevalent in both the training and testing phases of machine learning systems, which inevitably leads to the degradation of model performance.

Image Classification

Sparse Array Beampattern Synthesis via Majorization-Based ADMM

no code implementations9 Apr 2021 Tong Wei, Linlong Wu, M. R. Bhavani Shankar

Beampattern synthesis is a key problem in many wireless applications.

Improving Tail Label Prediction for Extreme Multi-label Learning

no code implementations1 Jan 2021 Tong Wei, Wei-Wei Tu, Yu-Feng Li

Extreme multi-label learning (XML) works to annotate objects with relevant labels from an extremely large label set.

Multi-Label Learning

Fuzzy Graph Neural Network for Few-Shot Learning

1 code implementation19 Jul 2020 Tong Wei, Junlin Hou and Rui Feng

According to the output of edge prediction, we design a fuzzy membership function to achieve more exact relationship representations for node classification.

Few-Shot Learning Graph Neural Network +2

MixPUL: Consistency-based Augmentation for Positive and Unlabeled Learning

no code implementations20 Apr 2020 Tong Wei, Feng Shi, Hai Wang, Wei-Wei Tu. Yu-Feng Li

To facilitate supervised consistency, reliable negative examples are mined from unlabeled data due to the absence of negative samples.

Data Augmentation

Cannot find the paper you are looking for? You can Submit a new open access paper.