Pith. sign in

REVIEW 7 cited by

Label Refinery: Improving ImageNet Classification through Label Progression

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 1805.02641 v1 pith:X2ZIAATS submitted 2018-05-07 cs.CV

Hessam Bagherinezhad , Maxwell Horton , Mohammad Rastegari , Ali Farhadi This is my paper · ORCID
classification cs.CV
keywords labelslabelmodelsrefinerydatalearningmainproperties
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

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.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 7 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Combined Image Data Augmentations diminish the benefits of Adaptive Label Smoothing

    cs.CV 2025-07 conditional novelty 6.0 of 10

    Soft augmentation improves training for single homogeneous augmentations like random erasing, but gives no net benefit and can reduce corruption robustness when combined with diverse augmentations like TrivialAugment.

  2. Sketch Down the FLOPs: Towards Efficient Networks for Human Sketch

    cs.CV 2025-05 conditional novelty 6.0 of 10

    By distilling a large teacher into a MobileNetV2 student and adding a reinforcement-learned canvas selector, the authors reduce FG-SBIR compute from 40.18G to 0.254G FLOPs with accuracy 32.77% vs 33.03%.

  3. Confidence Regularized Self-Training

    cs.CV 2019-08 conditional novelty 6.0 of 10

    A regularized self-training framework that softens pseudo-labels or network outputs improves unsupervised domain adaptation over the class-balanced self-training baseline.

  4. NT-ML: Backdoor Defense via Non-target Label Training and Mutual Learning

    cs.LG 2025-08 unverdicted novelty 5.0 of 10

    NT-ML combines non-target label training and mutual learning to purify a backdoored model using a small set of clean samples.

  5. Adaptive Regularization of Labels

    cs.LG 2019-08 conditional novelty 5.0 of 10

    Training a classifier with an auxiliary loss that matches its own non-ground-truth class probabilities to a learned per-class residual label improves accuracy on several benchmarks, though gains are small and top-5 Im...

  6. Multi-Modality Distillation via Learning the teacher's modality-level Gram Matrix

    cs.AI 2021-12 unverdicted novelty 4.0 of 10

    Proposes a modality relation distillation method that transfers teacher modality relationships via the modality-level Gram Matrix.

  7. Efficient Deep Neural Networks

    cs.CV 2019-08 conditional novelty 4.0 of 10

    A dissertation showing that deep learning can be made practical on edge devices through four complementary routes: model, data, hardware, and design efficiency.

Pith tools