Methods › Computer Vision › Feature Extractors › TUM
Thinned U-shape Module
TUM
archive 2025-07-28 Description, source and code snippet are the archive's method entry.
Thinned U-shape Module, or TUM, is a feature extraction block used for object detection models. It was introduced as part of the M2Det architecture. Different from FPN and RetinaNet, TUM adopts a thinner U-shape structure as illustrated in the Figure to the right. The encoder is a series of 3x3 convolution layers with stride 2. And the decoder takes the outputs of these layers as its reference set of feature maps, while the original FPN chooses the output of the last layer of each stage in ResNet backbone.
In addition, with TUM, we add 1x1 convolution layers after the upsample and element-wise sum operation at the decoder branch to enhance learning ability and keep smoothness for the features. In the context of M2Det, all of the outputs in the decoder of each TUM form the multi-scale features of the current level. As a whole, the outputs of stacked TUMs form the multi-level multi-scale features, while the front TUM mainly provides shallow-level features, the middle TUM provides medium-level features, and the back TUM provides deep-level features.
In Syntology name not resolved (unknown_name). The lookup matched no method, paper or venue by this name; that asserts nothing about whether code exists.
Syntology's have check for this name (free, it answers coverage only), read 2026-10-05; ask it again live. A level is the served verification level of that one answer; nothing here is summed across methods.
Papers archive 2025-07-28
archive papers tagged: 57 · with a code link: 24 · where Syntology ran a sample: 3 (3 with a run with no instrument failure, 0 where every run was a failure of Syntology's instrument) Syntology
Show: all tagged papersonly where code ran (3 of 57 tagged: 3 with a run with no instrument failure, 0 where every run was a failure of Syntology's instrument)
Page 1 of 1: papers 1 to 57 of 57, newest first by the archive's date (ties by slug), in archive order.
Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code, as “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the instrument figure counts failures of Syntology's instrument, not of the code. It is per sample and not a correctness claim. When the archive marks a repository official for the paper, the line starts with that repository's state (the archive's flag, not a verdict on who wrote the code; “community repositories only” when every sample that ran came from a community repository, “official: no sample here; runs from other or unrecorded repositories” when some came from a repository the paper names or has in its text, or from none recorded); hover it for the repositories the samples that ran came from.
-
GS4: Generalizable Sparse Splatting Semantic SLAM 6 Jun 2025 · 0 repositories · arXiv:2506.06517
-
Black-box Adversarial Attacks on CNN-based SLAM Algorithms 30 May 2025 · 0 repositories · arXiv:2505.24654
-
FGS-SLAM: Fourier-based Gaussian Splatting for Real-time SLAM with Sparse and Dense Map Fusion 3 Mar 2025 · 0 repositories · arXiv:2503.01109
-
Surface-SOS: Self-Supervised Object Segmentation via Neural Surface Representation 17 Jan 2025 · 1 repository · arXiv:2501.09947
-
AutoLoop: Fast Visual SLAM Fine-tuning through Agentic Curriculum Learning 15 Jan 2025 · 0 repositories · arXiv:2501.09160
-
SP-SLAM: Neural Real-Time Dense SLAM With Scene Priors 11 Jan 2025 · 0 repositories · arXiv:2501.06469
-
Scaffold-SLAM: Structured 3D Gaussians for Simultaneous Localization and Photorealistic Mapping 9 Jan 2025 · 0 repositories · arXiv:2501.05242
-
GSplatLoc: Ultra-Precise Camera Localization via 3D Gaussian Splatting 28 Dec 2024 · 1 repository · arXiv:2412.20056
-
LoRA3D: Low-Rank Self-Calibration of 3D Geometric Foundation Models 10 Dec 2024 · 0 repositories · arXiv:2412.07746
-
A Semantic Communication System for Real-time 3D Reconstruction Tasks 2 Dec 2024 · 0 repositories · arXiv:2412.01191
-
DATAP-SfM: Dynamic-Aware Tracking Any Point for Robust Structure from Motion in the Wild 20 Nov 2024 · 0 repositories · arXiv:2411.13291
-
V3D-SLAM: Robust RGB-D SLAM in Dynamic Environments with 3D Semantic Geometry Voting 15 Oct 2024 · 1 repository · arXiv:2410.12068
-
CLIP-Clique: Graph-based Correspondence Matching Augmented by Vision Language Models for Object-based Global Localization 4 Oct 2024 · 0 repositories · arXiv:2410.03054
-
Inline Photometrically Calibrated Hybrid Visual SLAM 25 Sep 2024 · 1 repository · arXiv:2409.16810
-
Towards Global Localization using Multi-Modal Object-Instance Re-Identification 18 Sep 2024 · 1 repository · arXiv:2409.12002
-
UDGS-SLAM : UniDepth Assisted Gaussian Splatting for Monocular SLAM 31 Aug 2024 · 0 repositories · arXiv:2409.00362
-
Geometry-guided Feature Learning and Fusion for Indoor Scene Reconstruction 28 Aug 2024 · 0 repositories · arXiv:2408.15608
-
Transfer Learning from Simulated to Real Scenes for Monocular 3D Object Detection 28 Aug 2024 · 0 repositories · arXiv:2408.15637
-
FAWN: Floor-And-Walls Normal Regularization for Direct Neural TSDF Reconstruction 17 Jun 2024 · 0 repositories · arXiv:2406.12054
-
MEDeA: Multi-view Efficient Depth Adjustment 17 Jun 2024 · 0 repositories · arXiv:2406.12048
-
Predictive Energy Management for Battery Electric Vehicles with Hybrid Models 15 May 2024 · 0 repositories · arXiv:2405.10984
-
SLAIM: Robust Dense Neural SLAM for Online Tracking and Mapping 17 Apr 2024 · 0 repositories · arXiv:2404.11419
-
High-Fidelity SLAM Using Gaussian Splatting with Rendering-Guided Densification and Regularized Optimization 19 Mar 2024 · 1 repository · arXiv:2403.12535
-
An Error-Matching Exclusion Method for Accelerating Visual SLAM 22 Feb 2024 · 0 repositories · arXiv:2402.14345
-
A Robust Error-Resistant View Selection Method for 3D Reconstruction 18 Feb 2024 · 0 repositories · arXiv:2402.11431
-
ActiveAnno3D -- An Active Learning Framework for Multi-Modal 3D Object Detection 5 Feb 2024 · 1 repository · arXiv:2402.03235
-
Geometry Depth Consistency in RGBD Relative Pose Estimation 1 Jan 2024 · 0 repositories · arXiv:2401.00639
-
3DS-SLAM: A 3D Object Detection based Semantic SLAM towards Dynamic Indoor Environments 10 Oct 2023 · 0 repositories · arXiv:2310.06385
-
DynaMoN: Motion-Aware Fast and Robust Camera Localization for Dynamic Neural Radiance Fields 16 Sep 2023 · 1 repository · arXiv:2309.08927
-
H-SLAM: Hybrid Direct-Indirect Visual SLAM 12 Jun 2023 · 2 repositories · arXiv:2306.07363
-
Scan2LoD3: Reconstructing semantic 3D building models at LoD3 using ray casting and Bayesian networks 10 May 2023 · 1 repository · arXiv:2305.06314
-
Co-SLAM: Joint Coordinate and Sparse Parametric Encodings for Neural Real-Time SLAM 27 Apr 2023 · 2 repositories · arXiv:2304.14377Syntology official (archive's flag): 6 ran · 6 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified (of 8 harvested samples) · 4 pointer-only (licence)
-
Autonomous Driving Simulator based on Neurorobotics Platform 31 Dec 2022 · 0 repositories · arXiv:2301.00089
-
CASSPR: Cross Attention Single Scan Place Recognition 22 Nov 2022 · 1 repository · arXiv:2211.12542
-
ESLAM: Efficient Dense SLAM System Based on Hybrid Representation of Signed Distance Fields 21 Nov 2022 · 1 repository · arXiv:2211.11704Syntology 4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified (of 4 harvested samples) · 4 pointer-only (licence)
-
VP-SLAM: A Monocular Real-time Visual SLAM with Points, Lines and Vanishing Points 23 Oct 2022 · 0 repositories · arXiv:2210.12756
-
Visual SLAM: What are the Current Trends and What to Expect? 19 Oct 2022 · 0 repositories · arXiv:2210.10491
-
Self-Improving SLAM in Dynamic Environments: Learning When to Mask 15 Oct 2022 · 1 repository · arXiv:2210.08350
-
Using Detection, Tracking and Prediction in Visual SLAM to Achieve Real-time Semantic Mapping of Dynamic Scenarios 10 Oct 2022 · 0 repositories · arXiv:2210.04562
-
Det-SLAM: A semantic visual SLAM for highly dynamic scenes using Detectron2 1 Oct 2022 · 1 repository · arXiv:2210.00278
-
PROB-SLAM: Real-time Visual SLAM Based on Probabilistic Graph Optimization 15 Sep 2022 · 0 repositories · arXiv:2209.07061
-
RWT-SLAM: Robust Visual SLAM for Highly Weak-textured Environments 7 Jul 2022 · 0 repositories · arXiv:2207.03539
-
MITI: SLAM Benchmark for Laparoscopic Surgery 23 Feb 2022 · 0 repositories · arXiv:2202.11496
-
Indy Autonomous Challenge -- Autonomous Race Cars at the Handling Limits 8 Feb 2022 · 0 repositories · arXiv:2202.03807
-
Robust Edge-Direct Visual Odometry based on CNN edge detection and Shi-Tomasi corner optimization 21 Oct 2021 · 0 repositories · arXiv:2110.11064
-
Efficient Surfel Fusion Using Normalised Information Distance 11 Aug 2021 · 1 repository · arXiv:2108.05163
-
VOLDOR: Visual Odometry from Log-logistic Dense Optical flow Residuals 14 Apr 2021 · 1 repository · arXiv:2104.06789
-
Generalizing to the Open World: Deep Visual Odometry with Online Adaptation 29 Mar 2021 · 0 repositories · arXiv:2103.15279
-
3D Point Cloud Registration with Multi-Scale Architecture and Unsupervised Transfer Learning 26 Mar 2021 · 1 repository · arXiv:2103.14533
-
Towards Robust Visual Information Extraction in Real World: New Dataset and Novel Solution 24 Jan 2021 · 1 repository · arXiv:2102.06732
-
Learning to Segment Dynamic Objects using SLAM Outliers 12 Nov 2020 · 0 repositories · arXiv:2011.06259
-
IMU-Assisted Learning of Single-View Rolling Shutter Correction 5 Nov 2020 · 1 repository · arXiv:2011.03106
-
Deep Probabilistic Feature-metric Tracking 31 Aug 2020 · 1 repository · arXiv:2008.13504
-
A Multi-Task Learning Approach for Human Activity Segmentation and Ergonomics Risk Assessment 7 Aug 2020 · 1 repository · arXiv:2008.03014
-
Dynamic Object Tracking and Masking for Visual SLAM 31 Jul 2020 · 1 repository · arXiv:2008.00072
-
Learning Monocular Visual Odometry via Self-Supervised Long-Term Modeling 21 Jul 2020 · 0 repositories · arXiv:2007.10983
-
M2Det: A Single-Shot Object Detector based on Multi-Level Feature Pyramid Network 12 Nov 2018 · 11 repositories · arXiv:1811.04533Syntology 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified (of 1 harvested sample)
Tasks archive 2025-07-28
20 shown of 61 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.
Usage over time archive 2025-07-28
Components: the archive holds no method-to-method composition, so PwC's Components table cannot be rebuilt; the Papers list carries no Results column for the same reason (the archive does not join its leaderboard rows to method tags).
Categories archive 2025-07-28
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