pith. sign in

arxiv: 2006.10029 · v2 · pith:OG2UAXBFnew · submitted 2020-06-17 · 💻 cs.LG · cs.CV· stat.ML

Big Self-Supervised Models are Strong Semi-Supervised Learners

classification 💻 cs.LG cs.CVstat.ML
keywords unlabeledexamplesfine-tuninglabelslearningsemi-supervisedaccuracydata
0
0 comments X
read the original abstract

One paradigm for learning from few labeled examples while making best use of a large amount of unlabeled data is unsupervised pretraining followed by supervised fine-tuning. Although this paradigm uses unlabeled data in a task-agnostic way, in contrast to common approaches to semi-supervised learning for computer vision, we show that it is surprisingly effective for semi-supervised learning on ImageNet. A key ingredient of our approach is the use of big (deep and wide) networks during pretraining and fine-tuning. We find that, the fewer the labels, the more this approach (task-agnostic use of unlabeled data) benefits from a bigger network. After fine-tuning, the big network can be further improved and distilled into a much smaller one with little loss in classification accuracy by using the unlabeled examples for a second time, but in a task-specific way. The proposed semi-supervised learning algorithm can be summarized in three steps: unsupervised pretraining of a big ResNet model using SimCLRv2, supervised fine-tuning on a few labeled examples, and distillation with unlabeled examples for refining and transferring the task-specific knowledge. This procedure achieves 73.9% ImageNet top-1 accuracy with just 1% of the labels ($\le$13 labeled images per class) using ResNet-50, a $10\times$ improvement in label efficiency over the previous state-of-the-art. With 10% of labels, ResNet-50 trained with our method achieves 77.5% top-1 accuracy, outperforming standard supervised training with all of the labels.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 8 Pith papers

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

  1. TabPFN: A Transformer That Solves Small Tabular Classification Problems in a Second

    cs.LG 2022-07 conditional novelty 8.0

    TabPFN is a Prior-Data Fitted Network that approximates Bayesian inference for small tabular classification by training a Transformer once on synthetic data drawn from a causal prior, then solves new tasks in a single...

  2. From Phase to Phenomenon: Self-Supervised Learning of Subsurface Scattering with Minimal Phase-shift Inputs

    cs.CV 2026-06 unverdicted novelty 7.0

    A self-supervised method pretrains an encoder on eight PSP images per view to learn generalizable subsurface scattering representations that transfer to relighting and dense footprint reconstruction on unseen complex objects.

  3. Learning Posterior Predictive Distributions for Node Classification from Synthetic Graph Priors

    cs.LG 2026-04 unverdicted novelty 7.0

    NodePFN pre-trains on synthetic graphs with controllable homophily and causal feature-label models to achieve 71.27 average accuracy on 23 node classification benchmarks without graph-specific training.

  4. Central Description Length (CDL) Clustering Validation Index

    stat.ML 2026-06 unverdicted novelty 6.0

    CDL-CVI is a new internal validation index using a description length bound on cluster centers that selected correct cluster counts more often than standard CVIs on non-convex synthetic data and image embeddings in th...

  5. Revisiting Feature Prediction for Learning Visual Representations from Video

    cs.CV 2024-02 conditional novelty 6.0

    V-JEPA models trained only on feature prediction from 2 million public videos achieve 81.9% on Kinetics-400, 72.2% on Something-Something-v2, and 77.9% on ImageNet-1K using frozen ViT-H/16 backbones.

  6. Template-assisted Contrastive Learning of Task-oriented Dialogue Sentence Embeddings

    cs.CL 2023-05 unverdicted novelty 6.0

    TaDSE learns dialogue sentence embeddings via template-guided self-supervised contrastive learning plus synthetic slot-filling augmentation and reports gains on five downstream benchmarks.

  7. Is Conditional Generative Modeling all you need for Decision-Making?

    cs.LG 2022-11 unverdicted novelty 6.0

    Return-conditional diffusion models for policies outperform offline RL on benchmarks by circumventing dynamic programming and enable constraint or skill composition.

  8. Vector-quantized Image Modeling with Improved VQGAN

    cs.CV 2021-10 accept novelty 6.0

    Improved ViT-VQGAN enables autoregressive Transformer pretraining on ImageNet tokens to reach IS 175.1 and FID 4.17 for generation plus 73.2% linear-probe accuracy, beating prior iGPT models.