Pith. sign in
Pith Number

pith:BKNIXIKE

pith:2013:BKNIXIKEOEQPS7TV2DA25S635M
not attested not anchored not stored refs resolved

Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps

Andrea Vedaldi, Andrew Zisserman, Karen Simonyan

A convolutional network trained only for image classification can produce saliency maps from class-score gradients that support weakly supervised object segmentation.

arxiv:1312.6034 v2 · 2013-12-20 · cs.CV

Open paper page JSON Open Graph Bundle Merged state Verified badge What is a Pith Number?
Add to your LaTeX paper 
\usepackage{pith}
\pithnumber{BKNIXIKEOEQPS7TV2DA25S635M}

Prints a linked badge after your title and injects PDF metadata. Compiles on arXiv. Learn more · Embed verified badge

Record completeness

1 Bitcoin timestamp
2 Internet Archive
3 Author claim open · sign in to claim
4 Citations open
5 Replications open
✓ Portable graph bundle live · download bundle · merged state
The bundle contains the canonical record plus signed events. A mirror can host it anywhere and recompute the same current state with the deterministic merge algorithm.

Claims

C1strongest claim

We show that such maps can be employed for weakly supervised object segmentation using classification ConvNets.

C2weakest assumption

That the gradient of the class score with respect to the input image pixels provides a faithful measure of pixel importance or saliency for the model's decision.

C3one line summary

Gradient ascent on class scores and input-image gradients produce visualizations of ConvNet class notions and saliency maps usable for weakly supervised segmentation.

References

13 extracted · 13 resolved · 0 Pith anchors

[1] D. Baehrens, T. Schroeter, S. Harmeling, M. Kawanabe, K. Hansen, and K.-R. M ¨uller. How to explain individual classification decisions. JMLR, 11:1803–1831, 2010 2010
[2] A. Berg, J. Deng, and L. Fei-Fei. Large scale visual recognition challenge (ILSVRC), 2010. URL http://www.image-net.org/challenges/LSVRC/2010/ 2010
[3] Y . Boykov and M. P. Jolly. Interactive graph cuts for optimal boundary and region segmentation of objects in N-D images. In Proc. ICCV, volume 2, pages 105–112, 2001 2001
[4] D. C. Ciresan, U. Meier, and J. Schmidhuber. Multi-column deep neural networks for image classification. In Proc. CVPR, pages 3642–3649, 2012 2012
[5] D. Erhan, Y . Bengio, A. Courville, and P. Vincent. Visualizing higher-layer features of a deep network. Technical Report 1341, University of Montreal, Jun 2009 2009

Formal links

1 machine-checked theorem link

Cited by

118 papers in Pith

Gradient-Based Speech-to-Text Alignment for Any ASR Model: From CTC to Speech LLMs
Mechanistic Interpretability of LLM Jailbreaks via Internal Attribution Graphs
Learned Committors as Reaction Coordinates for Nucleation Rates
X-FEMR: A Token-level Explainable Approach for Electronic Health Records Foundation Models using Transformer-based Models
Explainable AI for Next-Generation Wireless Physical Layer: Basics, State-of-the-Art, and Open Challenges
Receipt and verification
First computed 2026-07-04T18:53:55.286564Z
Builder pith-number-builder-2026-05-17-v1
Signature Pith Ed25519 (pith-v1-2026-05) · public key
Schema pith-number/v1.0

Canonical hash

0a9a8ba1447120f97e75d0c1aecbdbeb1a7520ac2617791a07191dd35ec8643e

Aliases

arxiv: 1312.6034 · arxiv_version: 1312.6034v2 · doi: 10.48550/arxiv.1312.6034 · pith_short_12: BKNIXIKEOEQP · pith_short_16: BKNIXIKEOEQPS7TV · pith_short_8: BKNIXIKE
Agent API
Resolver JSON Graph JSON Events JSON Schema Signing key
Verify this Pith Number yourself 
curl -sH 'Accept: application/ld+json' https://pith.science/pith/BKNIXIKEOEQPS7TV2DA25S635M \
  | jq -c '.canonical_record' \
  | python3 -c "import sys,json,hashlib; b=json.dumps(json.loads(sys.stdin.read()), sort_keys=True, separators=(',',':'), ensure_ascii=False).encode(); print(hashlib.sha256(b).hexdigest())"
# expect: 0a9a8ba1447120f97e75d0c1aecbdbeb1a7520ac2617791a07191dd35ec8643e
Canonical record JSON 
{
  "metadata": {
    "abstract_canon_sha256": "c6f6267cd2b70914f6018a2479afb24dc3fe836c857e5f9012fd021ce93ab937",
    "cross_cats_sorted": [],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.CV",
    "submitted_at": "2013-12-20T16:45:54Z",
    "title_canon_sha256": "6e02324c737aee549d89bbebe4922ce8aa15033116a178446188de2a46d320e7"
  },
  "schema_version": "1.0",
  "source": {
    "id": "1312.6034",
    "kind": "arxiv",
    "version": 2
  }
}