paper-with-me

Papers

A Three-Player GAN: Generating Hard Samples To Improve Classification Networks

2019-03-08 · Simon Vandenhende, Bert de Brabandere, Davy Neven, Luc van Gool

We propose a Three-Player Generative Adversarial Network to improve classification networks. In addition to the game played between the discriminator and generator, a competition is introduced between the generator and the classifier. The generator's objective is to synthesize samples that are both realistic and hard to label for the classifier. Even though we make no assumptions on the type of augmentations to learn, we find that the model is able to synthesize realistically looking examples that are hard for the classification model. Furthermore, the classifier becomes more robust when trained on these difficult samples. The method is evaluated on a public dataset for traffic sign recognition.

📄 PDF Abstract BibTeX arXiv:1903.03496

Code (0)

등록된 구현이 없습니다.

Tasks

ClassificationGeneral ClassificationGenerative Adversarial NetworkTraffic Sign Recognition

Similar Papers 제목 키워드 기반

$m$-mix: Generating hard negatives via multiple samples mixing for contrastive learning

2021-09-29 · Shaofeng Zhang, Meng Liu, Junchi Yan, Hengrui Zhang 외

Negative pairs are essential in contrastive learning, which plays the role of avoiding degenerate solutions. Hard negatives can improve the representation ability on the basis of common negatives. Inspired by recent hard…

ClassificationContrastive LearningGraph Classificationimage-classification+2

Automatic Generation of Alternative Starting Positions for Simple Traditional Board Games

2014-11-14 · Umair Z. Ahmed, Krishnendu Chatterjee, Sumit Gulwani

Simple board games, like Tic-Tac-Toe and CONNECT-4, play an important role not only in the development of mathematical and logical skills, but also in the emotional and social development. In this paper, we address the p…

Board Games

Public Information Representation for Adversarial Team Games

2022-01-25 · Luca Carminati, Federico Cacciamani, Marco Ciccone, Nicola Gatti

The peculiarity of adversarial team games resides in the asymmetric information available to the team members during the play, which makes the equilibrium computation problem hard even with zero-sum payoffs. The algorith…

STORY2GAME: Generating (Almost) Everything in an Interactive Fiction Game

2025-05-06 · Eric Zhou, Shreyas Basavatia, Moontashir Siam, Zexin Chen 외

We introduce STORY2GAME, a novel approach to using Large Language Models to generate text-based interactive fiction games that starts by generating a story, populates the world, and builds the code for actions in a game …

Action GenerationCode GenerationStory Generation

Are the Players in an Interactive Belief Model Meta-certain of the Model Itself?

2021-06-22 · Satoshi Fukuda

In an interactive belief model, are the players "commonly meta-certain" of the model itself? This paper formalizes such implicit "common meta-certainty" assumption. To that end, the paper expands the objects of players' …

model