pith:NMXAYK3N
Radar-Camera BEV Multi-Task Learning with Cross-Task Attention Bridge for Joint 3D Detection and Segmentation
A bidirectional attention bridge in shared BEV space lets detection and segmentation exchange features, raising segmentation accuracy on seven classes while detection stays neutral.
arxiv:2604.12918 v2 · 2026-04-14 · cs.CV
Add to your LaTeX paper
\usepackage{pith}
\pithnumber{NMXAYK3NTGOHEIQIE6UPZMNQHO}
Prints a linked badge after your title and injects PDF metadata. Compiles on arXiv. Learn more · Embed verified badge
Record completeness
Claims
CTAB is a bidirectional module that exchanges features between detection and segmentation branches via multi-scale deformable attention in shared BEV space.
That detection and segmentation features are sufficiently complementary and that attention-based transfer will not introduce noise or task interference that degrades either head.
CTAB exchanges features between detection and segmentation via multi-scale deformable attention in BEV space, yielding segmentation gains on 7 nuScenes classes at neutral detection cost.
Receipt and verification
| First computed | 2026-05-27T02:06:14.051020Z |
|---|---|
| Builder | pith-number-builder-2026-05-17-v1 |
| Signature | Pith Ed25519
(pith-v1-2026-05) · public key |
| Schema | pith-number/v1.0 |
Canonical hash
6b2e0c2b6d999c72220827a8fcb1b03ba3110ed4cd1b6353c43a648ddcf241ad
Aliases
· · · · ·Agent API
Verify this Pith Number yourself
curl -sH 'Accept: application/ld+json' https://pith.science/pith/NMXAYK3NTGOHEIQIE6UPZMNQHO \
| 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: 6b2e0c2b6d999c72220827a8fcb1b03ba3110ed4cd1b6353c43a648ddcf241ad
Canonical record JSON
{
"metadata": {
"abstract_canon_sha256": "3a1cfa7ea5ac46f875e8f0b3f3a4f9c2559ef902b07ee8211fdb590f8da3e268",
"cross_cats_sorted": [],
"license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
"primary_cat": "cs.CV",
"submitted_at": "2026-04-14T16:00:53Z",
"title_canon_sha256": "30ecc991678a7bbf4e1f7a2ef0bcb08c329a8c309b533be728123c1ea8ef161d"
},
"schema_version": "1.0",
"source": {
"id": "2604.12918",
"kind": "arxiv",
"version": 2
}
}