Pith. sign in

REVIEW 2 cited by

A Comprehensive Review on Deep Supervision: Theories and Applications

Not yet reviewed by Pith; the record is open.

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 2207.02376 v1 pith:HQJSZZ7R submitted 2022-07-06 cs.CV cs.AI

classification cs.CVcs.AI
keywords supervisiondeepapplicationsdifferentnetworkcomputerneuralvision
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Deep supervision, or known as 'intermediate supervision' or 'auxiliary supervision', is to add supervision at hidden layers of a neural network. This technique has been increasingly applied in deep neural network learning systems for various computer vision applications recently. There is a consensus that deep supervision helps improve neural network performance by alleviating the gradient vanishing problem, as one of the many strengths of deep supervision. Besides, in different computer vision applications, deep supervision can be applied in different ways. How to make the most use of deep supervision to improve network performance in different applications has not been thoroughly investigated. In this paper, we provide a comprehensive in-depth review of deep supervision in both theories and applications. We propose a new classification of different deep supervision networks, and discuss advantages and limitations of current deep supervision networks in computer vision applications.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 2 Pith papers

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

  1. Supervised Extraction of the Thermal Sunyaev$-$Zel'dovich Effect with a Three-Dimensional Convolutional Neural Network

    astro-ph.IM 2025-07 conditional novelty 6.0 of 10

    A 3D Attention Nested U-Net trained on synthetic SZ signals injected into Planck maps extracts the thermal SZ effect with accuracy comparable to the NILC method.

  2. Multi-Head Explainer: A General Framework to Improve Explainability in CNNs and Transformers

    cs.CV 2025-01 reject novelty 3.0 of 10

    MHEX inserts attention-gated deep-supervision heads into ResNet and BERT and derives saliency maps from the product of the head weights, claiming better accuracy and more detailed explanations.

Pith tools