Papers › Long-Tailed 3D Detection via Multi-Modal Fusion

Long-Tailed 3D Detection via Multi-Modal Fusion

18 Dec 2023arXiv:2312.10986archive 2025-07-28

Yechi Ma, Neehar Peri, Shuoquan Wei, Achal Dave, Wei Hua, Yanan Li, Deva Ramanan, Shu Kong

Contemporary autonomous vehicle (AV) benchmarks have advanced techniques for training 3D detectors, particularly on large-scale multi-modal (LiDAR + RGB) data. Surprisingly, although semantic class labels naturally follow a long-tailed distribution, existing benchmarks only focus on a few common classes (e.g., pedestrian and car) and neglect many rare but crucial classes (e.g., emergency vehicle and stroller). However, AVs must reliably detect both common and rare classes for safe operation in the open world. We address this challenge by formally studying the problem of Long-Tailed 3D Detection (LT3D), which evaluates all annotated classes, including those in-the-tail. We address LT3D with hierarchical losses that promote feature sharing across classes, and introduce diagnostic metrics that award partial credit to ``reasonable'' mistakes with respect to the semantic hierarchy (e.g., mistaking a child for an adult). Further, we point out that rare-class accuracy is particularly improved via multi-modal late fusion (MMLF) of independently trained uni-modal LiDAR and RGB detectors. Importantly, such an MMLF framework allows us to leverage large-scale uni-modal datasets (with more examples for rare classes) to train better uni-modal detectors, unlike prevailing end-to-end trained multi-modal detectors that require paired multi-modal data. Finally, we examine three critical components of our simple MMLF approach from first principles and investigate whether to train 2D or 3D RGB detectors for fusion, whether to match RGB and LiDAR detections in 3D or the projected 2D image plane, and how to fuse matched detections. Our proposed MMLF approach significantly improves LT3D performance over prior work, particularly improving rare class performance from 12.8 to 20.0 mAP!

PaperPDFCodeCode Syntology ran

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 15 code samples harvested from 1 repository linked to this paper: 14 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 3 honoured, 0 violated, 3 with no contract checked; 8 where Syntology's instrument failed) · 1 unverified. Where Syntology's instrument failed: 6 where our contract draft was wrong; 2 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 15 samples from 1 repository, 14 ran (6 with no instrument failure; 8 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Levels written on 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

mayechi/lt3d-lf officialSyntology: 15 samples, 14 ran (8 instrument-failed) · 1 unverified report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

15 samples harvested: 14 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 3 honoured, 0 violated, 3 with no contract checked; 8 where Syntology's instrument failed) · 1 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

3ran · honoured contract
6ran · our draft was wrong
2ran; the contract check could not run
3ran
1unverified

Licence: 15 of the 15 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from mayechi/lt3d-lf. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of six reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity.

mayechi/lt3d-lf official repository 15 samples, 14 ran (8 instrument-failed) · 1 unverified
cache_lookup analysis/stratified_lca0_ap.py ran · our draft was wrong no licence file found · pointer only · 480505311f7aaa80 · report fixture: signature cache_records:list/1/dict · returned defaultdict · level recorded 2026-09-24
calibration_from_json lt3d_lf/calibration.py ran · our draft was wrong no licence file found · pointer only · 329acd6c9aaf5155 · report fixture: signature path:str/0/str · returned dict · level recorded 2026-09-24
check_point_in_img lt3d_lf/fusion.py ran no licence file found · pointer only · 00236c9e7be34d8a · report fixture: signature points:ndarray/2/float, height:int/0/int, width:int/0/int · returned ndarray · level recorded 2026-09-24
ego_distance analysis/stratified_lca0_ap.py ran · honoured contract no licence file found · pointer only · 727b61f5c14e92dc · report fixture: signature box:Box/0/? · returned float · level recorded 2026-09-24
lca0 lt3d_lf/metrics.py ran · honoured contract no licence file found · pointer only · 1e8adc563b758332 · report fixture: signature eval_cls:str/0/str · returned float · level recorded 2026-09-24
lidar2img lt3d_lf/fusion.py ran; the contract check could not run (RAISES) no licence file found · pointer only · 357751b9f8e9f8a1 · report fixture: signature points_lidar:ndarray/2/float, camrera_info:dict/0/? · returned tuple · level recorded 2026-09-24
lidar_count_for_gt analysis/stratified_lca0_ap.py ran no licence file found · pointer only · 15a57e02b1ee3c6c · report fixture: signature box:Box/0/?, cache_by_key:dict/0/? · returned int · level recorded 2026-09-24
load in 392 papers lt3d_lf/utils.py ran · our draft was wrong fingerprinted no licence file found · pointer only · fe833b27ab49ae23 · report fixture: signature path:str/0/str · returned dict · level recorded 2026-09-24
manifest_path lt3d_lf/directional_tune.py ran · our draft was wrong no licence file found · pointer only · 8938b79a9f23a7bb · report fixture: signature grid_dir:PosixPath/0/?, factor:float/0/float · returned PosixPath · level recorded 2026-09-24
progressbar lt3d_lf/utils.py ran; the contract check could not run (RAISES) no licence file found · pointer only · 817a354ced0f660f · report fixture: signature itr:list/1/int, desc:str/0/str, total:int/0/int, unit:str/0/str, leave:bool/0/bool · returned tqdm · level recorded 2026-09-24
rounded lt3d_lf/directional_tune.py ran · honoured contract fingerprinted no licence file found · pointer only · 773288d87dbf2ec3 · report fixture: signature value:float/0/float · returned float · level recorded 2026-09-24
runtime_args lt3d_lf/tune.py ran no licence file found · pointer only · 904dbf0f59c378c4 · report fixture: signature args:SimpleNamespace/0/?, output_dir:str/0/str · returned SimpleNamespace · level recorded 2026-09-24
tag lt3d_lf/directional_tune.py ran · our draft was wrong fingerprinted no licence file found · pointer only · 42c80eb17c846d36 · report fixture: signature factor:float/0/float · returned str · level recorded 2026-09-24
uniform_calibration lt3d_lf/tune.py ran · our draft was wrong no licence file found · pointer only · 41b153582ebe8c90 · report fixture: signature factor:float/0/float · returned dict · level recorded 2026-09-24
unpack_predictions lt3d_lf/utils.py unverified no licence file found · pointer only · 52c5507d10c79e35 · report

Tasks

3D Object DetectionAutonomous VehiclesDepth EstimationDiagnosticObject Detectionobject-detection

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Focus

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections