paper-with-me

홈 › Papers

Label Refinery: Improving ImageNet Classification through Label Progression

2018-05-07 · Hessam Bagherinezhad, Maxwell Horton, Mohammad Rastegari, Ali Farhadi

Among the three main components (data, labels, and models) of any supervised learning system, data and models have been the main subjects of active research. However, studying labels and their properties has received very little attention. Current principles and paradigms of labeling impose several challenges to machine learning algorithms. Labels are often incomplete, ambiguous, and redundant. In this paper we study the effects of various properties of labels and introduce the Label Refinery: an iterative procedure that updates the ground truth labels after examining the entire dataset. We show significant gain using refined labels across a wide range of models. Using a Label Refinery improves the state-of-the-art top-1 accuracy of (1) AlexNet from 59.3 to 67.2, (2) MobileNet from 70.6 to 73.39, (3) MobileNet-0.25 from 50.6 to 55.59, (4) VGG19 from 72.7 to 75.46, and (5) Darknet19 from 72.9 to 74.47.

📄 PDF Abstract BibTeX arXiv:1805.02641

Code (4)

hessamb/label-refinery 공식 구현 pytorch
HoganZhang/label-refinery pytorch
Yang-YiFan/DiracDeltaNet pytorch
chrisqqq123/FA-Dist-EfficientNet pytorch

Tasks

ClassificationGeneral Classification

Similar Papers 제목 키워드 기반

Distribution Aligning Refinery of Pseudo-label for Imbalanced Semi-supervised Learning

2020-07-17 · NeurIPS 2020 12 · Jaehyung Kim, Youngbum Hur, Sejun Park, Eunho Yang 외

While semi-supervised learning (SSL) has proven to be a promising way for leveraging unlabeled data when labeled data is scarce, the existing SSL algorithms typically assume that training class distributions are balanced…

Pseudo Label

A Theory-Driven Self-Labeling Refinement Method for Contrastive Representation Learning

2021-06-28 · NeurIPS 2021 12 · Pan Zhou, Caiming Xiong, Xiao-Tong Yuan, Steven Hoi

For an image query, unsupervised contrastive learning labels crops of the same image as positives, and other image crops as negatives. Although intuitive, such a native label assignment strategy cannot reveal the underly…

Contrastive LearningRepresentation LearningSemantic SimilaritySemantic Textual Similarity

Uncertainty-Aware Pseudo Label Refinery for Domain Adaptive Semantic Segmentation

2021-01-01 · ICCV 2021 10 · Yuxi Wang, Junran Peng, Zhaoxiang Zhang

Unsupervised domain adaptation for semantic segmentation aims to assign the pixel-level labels for unlabeled target domain by transferring knowledge from the labeled source domain. A typical self-supervised learning …

Domain AdaptationPseudo LabelSelf-Supervised LearningSemantic Segmentation+1

PiTL: Cross-modal Retrieval with Weakly-supervised Vision-language Pre-training via Prompting

2023-07-14 · Zixin Guo, Tzu-Jui Julius Wang, Selen Pehlivan, Abduljalil Radman 외

Vision-language (VL) Pre-training (VLP) has shown to well generalize VL models over a wide range of VL downstream tasks, especially for cross-modal retrieval. However, it hinges on a huge amount of image-text pairs, whic…

Cross-Modal RetrievalImage to textObjectRetrieval

MrTF: Model Refinery for Transductive Federated Learning

2023-05-07 · Xin-Chun Li, Yang Yang, De-Chuan Zhan

We consider a real-world scenario in which a newly-established pilot project needs to make inferences for newly-collected data with the help of other parties under privacy protection policies. Current federated learning …

Federated Learningmodel