Big Self-Supervised Models are Strong Semi-Supervised Learners
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.
Forward citations
Cited by 8 Pith papers
-
TabPFN: A Transformer That Solves Small Tabular Classification Problems in a Second
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...
-
From Phase to Phenomenon: Self-Supervised Learning of Subsurface Scattering with Minimal Phase-shift Inputs
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.
-
Learning Posterior Predictive Distributions for Node Classification from Synthetic Graph Priors
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.
-
Central Description Length (CDL) Clustering Validation Index
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...
-
Revisiting Feature Prediction for Learning Visual Representations from Video
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.
-
Template-assisted Contrastive Learning of Task-oriented Dialogue Sentence Embeddings
TaDSE learns dialogue sentence embeddings via template-guided self-supervised contrastive learning plus synthetic slot-filling augmentation and reports gains on five downstream benchmarks.
-
Is Conditional Generative Modeling all you need for Decision-Making?
Return-conditional diffusion models for policies outperform offline RL on benchmarks by circumventing dynamic programming and enable constraint or skill composition.
-
Vector-quantized Image Modeling with Improved VQGAN
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.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.