Pith Number

pith:D7DWUI5J

pith:2026:D7DWUI5JPMRCTJEMIVPUHTLNJO

not attested not anchored not stored refs resolved

Deep Image Segmentation via Discriminant Feature Learning

Adam Dawid Sztamborski, Antonio Agudo, Ra\"ul P\'erez-Gonzalo

A new loss based on classical discriminant analysis sharpens segmentation boundaries by making features more separable.

arxiv:2605.14609 v1 · 2026-05-14 · cs.CV · cs.LG

Open paper page JSON Open Graph Bundle Merged state Verified badge What is a Pith Number?

Add to your LaTeX paper

\usepackage{pith}
\pithnumber{D7DWUI5JPMRCTJEMIVPUHTLNJO}

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

DDA explicitly maximizes between-class variance while minimizing within-class one, promoting compact and separable feature distributions without increasing inference cost.

C2weakest assumption

That the observed improvements on the DIS5K benchmark are caused by the discriminant properties of the loss rather than by differences in training schedule, hyper-parameters, or implementation details not described in the abstract.

C3one line summary

Deep Discriminant Analysis (DDA) is a new loss that maximizes between-class variance and minimizes within-class variance to produce more compact and separable features for image segmentation.

References

38 extracted · 38 resolved · 2 Pith anchors

[1] Deep Image Segmentation via Discriminant Feature Learning 2026 · doi:10.13039/501100011033

[2] It can lead to over- lapping foreground and background activations and uncertain or blurred boundaries

[3] A largerS B indicates better class separability

[4] Smaller values indicate more compact, discriminable classes

[5] This desirable general separability criterion should take larger values when the within-class scatter is smaller and when the between-class scatter is larger

Formal links

2 machine-checked theorem links

Cited by

1 paper in Pith

Deep Image Segmentation via Discriminant Feature Learning

Receipt and verification

First computed	2026-05-17T23:39:04.180103Z
Builder	pith-number-builder-2026-05-17-v1
Signature	Pith Ed25519 (`pith-v1-2026-05`) · public key
Schema	pith-number/v1.0

Canonical hash

1fc76a23a97b2229a48c455f43cd6d4b92595ab491a0cf829a7890fa054d45f9

Aliases

arxiv: 2605.14609 · arxiv_version: 2605.14609v1 · doi: 10.48550/arxiv.2605.14609 · pith_short_12: D7DWUI5JPMRC · pith_short_16: D7DWUI5JPMRCTJEM · pith_short_8: D7DWUI5J

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/D7DWUI5JPMRCTJEMIVPUHTLNJO \
  | 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: 1fc76a23a97b2229a48c455f43cd6d4b92595ab491a0cf829a7890fa054d45f9

Canonical record JSON

{
  "metadata": {
    "abstract_canon_sha256": "fca97bee5d8b4c4cc85c25f8b881ccf926981f032b3e70933097ac5b901b7193",
    "cross_cats_sorted": [
      "cs.LG"
    ],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "primary_cat": "cs.CV",
    "submitted_at": "2026-05-14T09:25:36Z",
    "title_canon_sha256": "8b12fce1a60d43dc963b15cbf7c64ef90026d74fb1ce16892e72c914f4deb8e7"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2605.14609",
    "kind": "arxiv",
    "version": 1
  }
}