</> Code with Papers by Syntology

Methods › Computer Vision › Feature Extractors › TUM

Thinned U-shape Module

TUM

57 papers tagged archive 2025-07-28

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.

Source: M2Det: A Single-Shot Object Detector based on...See Code · qijiezhao/M2Det

Papers archive 2025-07-28

30 shown of 57, newest first. Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code; it is per sample and not a correctness claim.

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.

TaskPapers
Simultaneous Localization and Mapping12
Pose Estimation10
3D Reconstruction7
Object Detection7
object-detection7
Semantic Segmentation6
Camera Localization5
Object5
Depth Estimation4
NeRF4
Optical Flow Estimation4
Visual Odometry4
3D Object Detection3
Autonomous Driving3
GPU3
Semantic SLAM3
Surface Reconstruction3
Camera Pose Estimation2
Decoder2
Novel View Synthesis2

Usage over time archive 2025-07-28

Papers per year tagged with TUM: 2018 to 2025, peak 20 20 0 2018: 1 paper 2018 2019: 0 papers 2019 2020: 6 papers 2020 2021: 6 papers 2021 2022: 12 papers 2022 2023: 5 papers 2023 2024: 20 papers 2024 2025: 7 papers 2025
Papers per year the archive tags with this method, by the paper's archive date (57 dated). Bars are counts, not a trend claim.

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

Feature Extractors

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