TPAMI 2025 papers on Detection and segmentation
86 of the 932 papers published in TPAMI 2025 (9.2%) are on Detection and segmentation, compared with 11.0% at TPAMI 2024. They fall into 5 topics.
See TPAMI 2025 in the interactive map
Working on something in this area? Describe your idea in scime atlas to see the closest papers by meaning and how crowded the spot has become.
Topics and papers
CNN features · 32 papers
- YOLO-MS: Rethinking Multi-Scale Representation Learning for Real-Time Object Detection (333 citations)
- Spatial Residual for Underwater Object Detection (102 citations)
- Spatial Frequency Modulation for Semantic Segmentation (45 citations)
- Low-Resolution Self-Attention for Semantic Segmentation (39 citations)
- Explicit Visual Prompting for Universal Foreground Segmentations (25 citations)
- Rapid Salient Object Detection With Difference Convolutional Neural Networks (23 citations)
- REST: Holistic Learning for End-to-End Semantic Segmentation of Whole-Scene Remote Sensing Imagery (20 citations)
- Enhancing Object Detection With Fourier Series (19 citations)
- CLRNetV2: A Faster and Stronger Lane Detector (13 citations)
- Oriented Tiny Object Detection: A Dataset, Benchmark, and Dynamic Unbiased Learning (12 citations)
- Structural and Statistical Texture Knowledge Distillation and Learning for Segmentation (11 citations)
- NICE: Improving Panoptic Narrative Detection and Segmentation With Cascading Collaborative Learning (10 citations)
and 20 more in the interactive map.
Open-set and few-shot detection · 28 papers
- Visible-Thermal Tiny Object Detection: A Benchmark Dataset and Baselines (107 citations)
- Conditional Diffusion Models for Camouflaged and Salient Object Detection (71 citations)
- Referring Camouflaged Object Detection (65 citations)
- Unsupervised Pre-Training With Language-Vision Prompts for Low-Data Instance Segmentation (44 citations)
- ACDC: The Adverse Conditions Dataset With Correspondences for Robust Semantic Driving Scene Perception (35 citations)
- Rethinking Evaluation Metrics of Open-Vocabulary Segmentation (20 citations)
- Rate-Distortion Theory in Coding for Machines and Its Applications (19 citations)
- Generalized Semantic Contrastive Learning via Embedding Side Information for Few-Shot Object Detection (18 citations)
- SKDF: A Simple Knowledge Distillation Framework for Distilling Open-Vocabulary Knowledge to Open-World Object Detector (18 citations)
- Fixing Background Misclassification in Few-Shot Object Detection via Product of Experts (14 citations)
- Laser: Efficient Language-Guided Segmentation in Neural Radiance Fields (14 citations)
- Towards Real Zero-Shot Camouflaged Object Segmentation Without Camouflaged Annotations (11 citations)
and 16 more in the interactive map.
3D detection and driving · 14 papers
- BEVHeight++: Toward Robust Visual Centric 3D Object Detection (85 citations)
- DeepInteraction++: Multi-Modality Interaction for Autonomous Driving (28 citations)
- Collaborative Novel Object Discovery and Box-Guided Cross-Modal Alignment for Open-Vocabulary 3D Object Detection (19 citations)
- MTMamba++: Enhancing Multi-Task Dense Scene Understanding via Mamba-Based Decoders (13 citations)
- Exploiting Ground Depth Estimation for Mobile Monocular 3D Object Detection (11 citations)
- Toward Unified 3D Object Detection via Algorithm and Data Unification (8 citations)
- Toward Optimal Mixture of Experts System for 3D Object Detection: A Game of Accuracy, Efficiency and Adaptivity (7 citations)
- Unsupervised 3D Object Detection by Commonsense Clue (5 citations)
- MGAF: LiDAR-Camera 3D Object Detection With Multiple Guidance and Adaptive Fusion (4 citations)
- Uncertain Object Representation for Image-Based 3D Object Perception (3 citations)
- Advancing 3D Object Detection With Depth-Aware Spatial Knowledge Distillation (2 citations)
- A Visual Benchmark for Autonomous Driving in Open-Pit Mines (1 citation)
and 2 more in the interactive map.
Weakly supervised detection and segmentation · 9 papers
- Segment Concealed Objects With Incomplete Supervision (36 citations)
- Frozen CLIP-DINO: A Strong Backbone for Weakly Supervised Semantic Segmentation (34 citations)
- Modeling the Label Distributions for Weakly-Supervised Semantic Segmentation (34 citations)
- Wholly-WOOD: Wholly Leveraging Diversified-Quality Labels for Weakly-Supervised Oriented Object Detection (18 citations)
- SOOD++: Leveraging Unlabeled Data to Boost Oriented Object Detection (14 citations)
- CLIP-Driven Transformer for Weakly Supervised Object Localization (11 citations)
- Data-Driven Bidirectional Spatial-Adaptive Network for Weakly Supervised Object Detection in Remote Sensing Images (3 citations)
- SA3Det++: Side-Aware Quality Estimation for Semi-Supervised 3D Object Detection (2 citations)
- Toward Efficient Semi-Supervised Object Detection With Detection Transformer (2 citations)
