Label Refinery: Improving ImageNet Classification through Label Progression
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.
Code (4)
Tasks
ClassificationGeneral ClassificationSimilar Papers 제목 키워드 기반
Distribution Aligning Refinery of Pseudo-label for Imbalanced Semi-supervised Learning
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 LabelA Theory-Driven Self-Labeling Refinement Method for Contrastive Representation Learning
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 SimilarityUncertainty-Aware Pseudo Label Refinery for Domain Adaptive Semantic Segmentation
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+1PiTL: Cross-modal Retrieval with Weakly-supervised Vision-language Pre-training via Prompting
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 textObjectRetrievalMrTF: Model Refinery for Transductive Federated Learning
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