Deep Active Learning over the Long Tail
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.
Code (0)
등록된 구현이 없습니다.
Tasks
Active LearningMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Proactive Guiding Strategy for Item-side Fairness in Interactive Recommendation
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 LearningAgent-driven Long-tail Simulation for Autonomous Driving
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 DrivingGenerative Data Mining with Longtail-Guided Diffusion
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 ClassificationGenerative Active Learning for Long-tail Trajectory Prediction via Controllable Diffusion Model
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 LearningCan I see an Example? Active Learning the Long Tail of Attributes and Relations
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