pith. sign in

arxiv: 2201.05131 · v1 · pith:Z6RAARRDnew · submitted 2022-01-13 · 💻 cs.CV

SimReg: Regression as a Simple Yet Effective Tool for Self-supervised Knowledge Distillation

classification 💻 cs.CV
keywords distillationregressionself-supervisedsimpleteacherarchitecturechangesdistill
0
0 comments X
read the original abstract

Feature regression is a simple way to distill large neural network models to smaller ones. We show that with simple changes to the network architecture, regression can outperform more complex state-of-the-art approaches for knowledge distillation from self-supervised models. Surprisingly, the addition of a multi-layer perceptron head to the CNN backbone is beneficial even if used only during distillation and discarded in the downstream task. Deeper non-linear projections can thus be used to accurately mimic the teacher without changing inference architecture and time. Moreover, we utilize independent projection heads to simultaneously distill multiple teacher networks. We also find that using the same weakly augmented image as input for both teacher and student networks aids distillation. Experiments on ImageNet dataset demonstrate the efficacy of the proposed changes in various self-supervised distillation settings.

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 1 Pith paper

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

  1. HQ-JEPA: Hybrid Quantum Joint-Embedding Predictive Architecture for Cross-Modal Remote Sensing Representation Learning

    cs.CV 2026-05 unverdicted novelty 5.0

    HQ-JEPA combines JEPA-style predictive self-supervision with cross-modal alignment and a SWAP-test-based quantum fidelity loss for learning representations from paired remote sensing imagery, reporting competitive res...