ICML 2025 accepted papers on Detection and segmentation
34 of the 3,342 papers accepted at ICML 2025 (1.0%) are on Detection and segmentation, compared with 0.9% at ICML 2024. They fall into 4 topics.
See ICML 2025 in the interactive map
Working on something in this area? Describe your idea in scime atlas to see the closest accepted papers by meaning and how crowded the spot has become.
Topics and papers
Open-set and few-shot detection · 14 papers
- Subobject-level Image Tokenization (2 citations)
- Contour Integration Underlies Human-Like Vision (1 citation)
- "Why Is There a Tumor?": Tell Me the Reason, Show Me the Evidence
- Adaptive Sensitivity Analysis for Robust Augmentation against Natural Corruptions in Image Segmentation
- Alberta Wells Dataset: Pinpointing Oil and Gas Wells from Satellite Imagery
- iDPA: Instance Decoupled Prompt Attention for Incremental Medical Object Detection
- Open-Det: An Efficient Learning Framework for Open-Ended Detection
- Separating Knowledge and Perception with Procedural Data
- Sounding that Object: Interactive Object-Aware Image to Audio Generation
- Unlocking the Power of SAM 2 for Few-Shot Segmentation
- unMORE: Unsupervised Multi-Object Segmentation via Center-Boundary Reasoning
- Better to Teach than to Give: Domain Generalized Semantic Segmentation via Agent Queries with Diffusion Model Guidance
and 2 more in the interactive map.
CNN features · 13 papers
- RUN: Reversible Unfolding Network for Concealed Object Segmentation (3 citations)
- SToFM: a Multi-scale Foundation Model for Spatial Transcriptomics (2 citations)
- Poly2Vec: Polymorphic Fourier-Based Encoding of Geospatial Objects for GeoAI Applications (1 citation)
- A Two-Stage Learning-to-Defer Approach for Multi-Task Learning
- Complex Wavelet Mutual Information Loss: A Multi-Scale Loss Function for Semantic Segmentation
- FuseUNet: A Multi-Scale Feature Fusion Method for U-like Networks
- Hybrid Spiking Vision Transformer for Object Detection with Event Cameras
- Self-Bootstrapping for Versatile Test-Time Adaptation
- The Four Color Theorem for Cell Instance Segmentation
- EFDTR: Learnable Elliptical Fourier Descriptor Transformer for Instance Segmentation
- Not All Tokens Matter All The Time: Dynamic Token Aggregation Towards Efficient Detection Transformers
- Self-Supervised Learning of Intertwined Content and Positional Features for Object Detection
and 1 more in the interactive map.
3D detection and driving · 4 papers
- How Do Images Align and Complement LiDAR? Towards a Harmonized Multi-modal 3D Panoptic Segmentation
- Towards Learning to Complete Anything in Lidar
- CSV-Occ: Fusing Multi-frame Alignment for Occupancy Prediction with Temporal Cross State Space Model and Central Voting Mechanism
- Generalizable Multi-Camera 3D Object Detection from a Single Source via Fourier Cross-View Learning