paper-with-me

홈 › Papers

Deep Active Learning over the Long Tail

2017-11-02 · Yonatan Geifman, Ran El-Yaniv

This paper is concerned with pool-based active learning for deep neural networks. Motivated by coreset dataset compression ideas, we present a novel active learning algorithm that queries consecutive points from the pool using farthest-first traversals in the space of neural activation over a representation layer. We show consistent and overwhelming improvement in sample complexity over passive learning (random sampling) for three datasets: MNIST, CIFAR-10, and CIFAR-100. In addition, our algorithm outperforms the traditional uncertainty sampling technique (obtained using softmax activations), and we identify cases where uncertainty sampling is only slightly better than random sampling.

📄 PDF Abstract BibTeX arXiv:1711.00941

Code (0)

등록된 구현이 없습니다.

Tasks

Active Learning

Methods 이 논문이 사용한 방법론

Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…

Similar Papers 제목 키워드 기반

Proactive Guiding Strategy for Item-side Fairness in Interactive Recommendation

2026-03-03 · Chongjun Xia, Xiaoyu Shi, Hong Xie, Xianzhi Wang 외 arxiv

Item-side fairness is crucial for ensuring the fair exposure of long-tail items in interactive recommender systems. Existing approaches promote the exposure of long-tail items by directly incorporating them into recommen…

Hierarchical Reinforcement Learning

Agent-driven Long-tail Simulation for Autonomous Driving

2026-07-05 · Junru Gu, Lijin Yang, Jianing Huang, Shu Liu 외 arxiv

Evaluating autonomous driving systems in closed-loop settings requires realistic and interactive simulation, yet existing simulators largely rely on log replay or rule-based agents, limiting behavioral diversity and long…

Autonomous Driving

Generative Data Mining with Longtail-Guided Diffusion

2025-02-04 · David S. Hayden, Mao Ye, Timur Garipov, Gregory P. Meyer 외

It is difficult to anticipate the myriad challenges that a predictive model will encounter once deployed. Common practice entails a reactive, cyclical approach: model deployment, data mining, and retraining. We instead d…

image-classificationImage Classification

Generative Active Learning for Long-tail Trajectory Prediction via Controllable Diffusion Model

2025-07-30 · Daehee Park, Monu Surana, Pranav Desai, Ashish Mehta 외 arxiv

While data-driven trajectory prediction has enhanced the reliability of autonomous driving systems, it still struggles with rarely observed long-tail scenarios. Prior works addressed this by modifying model architectures…

Trajectory PredictionLong-tail LearningAutonomous DrivingActive Learning

Can I see an Example? Active Learning the Long Tail of Attributes and Relations

2022-03-11 · Tyler L. Hayes, Maximilian Nickel, Christopher Kanan, Ludovic Denoyer 외

There has been significant progress in creating machine learning models that identify objects in scenes along with their associated attributes and relationships; however, there is a large gap between the best models and …

Active Learning