Claim · 2016-10-07 · publication · Stated in source · Supported

The paper proposes a technique, Grad-CAM, for making CNN-based models more transparent by visualizing the input regions that matter for their predictions.

One recorded claim. The claim panel gives its qualification, the source passages with their place in each source, and how it was checked.

What it connects

Grad-CAM: Visual Explanations from Deep Networks via Gradient-Based Localization → states its contribution → The paper proposes a technique, Grad-CAM, for making CNN-based models more transparent by visualizing the input regions that matter for their predictions.

Where it appears

No collection page holds this claim. It is listed with its records in the explorer.

Claim and evidence

Grad-CAM: Visual Explanations from Deep Networks via Gradient-Based Localizationstates its contribution ↓The paper proposes a technique, Grad-CAM, for making CNN-based models more transparent by visualizing the input regions that matter for their predictions.

Machine-checked, not reviewed by an editorStated in sourceSupported

Supporting evidence: primary · 1 source

Date: 2016-10-07 · publication Records dated 2016 →

Scope and limitsThe paper's own description of its contribution; not an assessment of it.

The evidence 01

primary sourceSupports the claim

Grad-CAM: Visual Explanations from Deep Networks via Gradient-Based Localization

arXiv · 2016-10-07

Cite the original source

Cite the original document, not Selekoa. Check these details against it.

Source excerpt

“We propose a technique for making Convolutional Neural Network (CNN)-based models more transparent by visualizing the regions of input that are ‘important’ for predictions from these models – or visual explanations.”

Location in source arXiv v1, PDF p. 1, abstract

Machine-checked · 2026-10-31

Source details and check notes

Authors: Ramprasaath R. Selvaraju; Michael Cogswell; Abhishek Das; Ramakrishna Vedantam; Devi Parikh; Dhruv Batra
Version: arXiv:1610.02391v1, submitted 7 October 2016 (UTC). Retrieved for the candidate pack on 2026-10-28 (SHA-256 dcbedb7a15ee9f572aee9b0d5600e0a6c24c47f8f9e1336a8a2b879702bed224). The author list is the byline as printed on the first page.
Version date: 2016-10-07
Canonical address: Open the canonical source ↗
Accessed: 2026-10-28
Language: English (en)
Attribution: Ramprasaath R. Selvaraju, Michael Cogswell, Abhishek Das, Ramakrishna Vedantam, Devi Parikh, Dhruv Batra, “Grad-CAM: Visual Explanations from Deep Networks via Gradient-Based Localization”, 2016-10-07.
Reuse: No open redistribution licence asserted. Bibliographic metadata, editorial paraphrases and short attributed quotations (at most 50 words each). Recheck terms before wider redistribution.
Check notes: Candidate pack passage, key papers (research/key-papers). The quotation (30 words) matched the text retrieved for the candidate pack on 2026-10-28 (research/key-papers/verification.json). Matching ignored differences of whitespace, case, quotation marks, dashes and line-break hyphens, so the source’s typography can differ. A cross-family machine check (2026-10-30, item B049) found the quotation at its locator. No human editorial review.

Status and meaning

Editorial status. Not reviewed by an editor. An exploratory record that no editor has accepted. This status does not say whether a person has read any linked passage. Each evidence record above shows how it was checked.

Relation. A paper or other publication describes its own contribution, quoted from the expression the record names, usually its abstract or introduction. The record is the document’s own description, not an assessment: a claim of priority or novelty it contains is the document’s claim, flagged as such, and says nothing about earlier or later work.

Date. Date of the arXiv version quoted, submitted 7 October 2016 (UTC); later versions may word it differently.

Record ID kp-states-grad-cam-visual-explanations-from-2016-1