paper-with-me

Active Learning

1개 벤치마크 · 논문 3,567편 · 이 태스크의 논문 보기 →

Benchmarks

CIFAR10 (10,000)

결과 14개

Most implemented

Learning Loss for Active Learning

2019-05-09 · 구현 7개

Variational Adversarial Active Learning

2019-03-31 · 구현 6개

Papers

One Loop, Two Gains: Can Active Learning win the Lottery for Free?

2026-09-09 · Benedikt Tscheschner, Eduardo Veas, Marc Masana arxiv

The lottery ticket hypothesis posits the existence of winning tickets: sparse subnetworks that, when trained in isolation from their original initialization, match the accuracy of the full dense network. The predominant …

Image ClassificationActive Learning

Train Smarter, Not Harder: Switching Signal-Guided Training in Active Learning

2026-09-06 · Nagham Omar, Maya Rozenshtein, Evgeny Mishlyakov, Avigdor Gal hf

Training strategy, namely whether to retrain from scratch or fine-tune from the previous checkpoint, is an overlooked decision variable in active learning. We show that this choice has exploitable structure: retraining i…

Active Learning

Cost-efficient Active Learning for Referring Image Segmentation and Grounding

2026-08-31 · Junbeom Hong, Seonghoon Yu, Hyung Rok Jung, Sundong Kim 외 arxiv

Collecting natural-language referring expressions along with region annotations, such as masks or boxes, is a major bottleneck in visual grounding (VG), as annotators must write descriptions that distinguish target regio…

Image SegmentationVisual GroundingActive Learning

Loss-Based Active Learning for Neural Abstractive Summarization

2026-08-26 · Michail Ioannou, Tatiana Passali, George Michalopoulos, Grigorios Tsoumakas arxiv

Fine-tuning abstractive summarization models requires high-quality annotated data. However, obtaining such corpora is expensive and time-consuming, as it requires human annotators to read and comprehend long documents to…

Active Learning

ConfAL-WM: Confidence-Guided Active Learning for Action-Conditioned World Models

2026-08-26 · Xiang Liu, Sen Cui, Changshui Zhang arxiv

Action-conditioned world models have become an important foundation for embodied prediction, planning, and synthetic data generation, but their errors under new task and scene distributions are often concentrated in loca…

Synthetic Data GenerationActive Learning

Diversity-Based Active Learning: An Evaluation of Metric Spaces for Active Learning Selection

2026-08-24 · Siddharth Chilamkur, Dorit S. Hochbaum arxiv

With rapid advancement over the last few years, many different methods are now widely used for classification. However, training these models requires substantial labeled data. Active Learning is a potential solution to …

Active Learning

전체 3,567편 보기 →