paper-with-me

홈 › Papers

Generative-Discriminative Complementary Learning

2019-04-02 · Yanwu Xu, Mingming Gong, Junxiang Chen, Tongliang Liu, Kun Zhang, Kayhan Batmanghelich

Majority of state-of-the-art deep learning methods are discriminative approaches, which model the conditional distribution of labels given inputs features. The success of such approaches heavily depends on high-quality labeled instances, which are not easy to obtain, especially as the number of candidate classes increases. In this paper, we study the complementary learning problem. Unlike ordinary labels, complementary labels are easy to obtain because an annotator only needs to provide a yes/no answer to a randomly chosen candidate class for each instance. We propose a generative-discriminative complementary learning method that estimates the ordinary labels by modeling both the conditional (discriminative) and instance (generative) distributions. Our method, we call Complementary Conditional GAN (CCGAN), improves the accuracy of predicting ordinary labels and can generate high-quality instances in spite of weak supervision. In addition to the extensive empirical studies, we also theoretically show that our model can retrieve the true conditional distribution from the complementarily-labeled data.

📄 PDF Abstract BibTeX arXiv:1904.01612

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…
Dogecoin Customer Service Number +1-833-534-1729 설명 없음

Similar Papers 제목 키워드 기반

TrueMoE: Dual-Routing Mixture of Discriminative Experts for Synthetic Image Detection

2025-09-19 · Laixin Zhang, Shuaibo Li, Wei Ma, Hongbin Zha arxiv

The rapid progress of generative models has made synthetic image detection an increasingly critical task. Most existing approaches attempt to construct a single, universal discriminative space to separate real from fake …

Extract and Diffuse: Latent Integration for Improved Diffusion-based Speech and Vocal Enhancement

2024-09-15 · Yudong Yang, Zhan Liu, Wenyi Yu, Guangzhi Sun 외

Diffusion-based generative models have recently achieved remarkable results in speech and vocal enhancement due to their ability to model complex speech data distributions. While these models generalize well to unseen ac…

UME-R1: Exploring Reasoning-Driven Generative Multimodal Embeddings

2025-11-01 · Zhibin Lan, Liqiang Niu, Fandong Meng, Jie Zhou 외 arxiv

The remarkable success of multimodal large language models (MLLMs) has driven advances in multimodal embeddings, yet existing models remain inherently discriminative, limiting their ability to benefit from reasoning-driv…

Reinforcement Learning

Unsupervised, Efficient and Semantic Expertise Retrieval

2016-08-23 · Christophe Van Gysel, Maarten de Rijke, Marcel Worring

We introduce an unsupervised discriminative model for the task of retrieving experts in online document collections. We exclusively employ textual evidence and avoid explicit feature engineering by learning distributed w…

Feature EngineeringRetrieval

G2D: Generative-to-Discriminative Collaborative Inference for Zero-Shot Image Classification

2026-08-27 · Zehua Hao, Fang Liu, Qinliang Wang, Yaoyang Du 외 arxiv

Zero-shot classification needs efficient label retrieval and fine-grained visual reasoning, yet discriminative and generative vision-language models fail in complementary ways.When CLIP's top-1 prediction is wrong, the c…

Zero-Shot Image ClassificationVisual Reasoning