ICML 2026 accepted papers on Detection and segmentation
56 of the 6,341 papers accepted at ICML 2026 (0.9%) are on Detection and segmentation, compared with 1.0% at ICML 2025. They fall into 4 topics.
See ICML 2026 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 · 29 papers
- Causal-JEPA: Learning World Models through Object-Level Latent Masking (5 citations)
- Alterbute: Editing Intrinsic Attributes of Objects in Images
- DecomPose: Disentangling Cross-Category Optimization Contention for Category-Level 6D Object Pose Estimation
- Dywave: Event-Aligned Dynamic Tokenization for Heterogeneous IoT Sensing Signals
- Evaluating Object-Centric Models beyond Object Discovery
- FlatLab: A Unified Methodology Framework and Simulation-Based Benchmark for Robotic Manipulation of Flat Objects
- FOCUS: Forcing In-Context Object Localization through Visual Support Constraints and Policy Optimization
- HOI-PAGE: Zero-Shot Human-Object Interaction Generation with Part Affordance Guidance
- InfoGeo: Information-Theoretic Object-Centric Learning for Cross-View Generalizable UAV Geo-Localization
- Knowing the Unknown: Interpretable Open-World Object Detection via Concept Decomposition Model
- Med-SegLens: Latent-Level Model Diffing for Interpretable Medical Image Segmentation
- OOVDet: Low-Density Prior Learning for Zero-Shot Out-of-Vocabulary Object Detection
and 17 more in the interactive map.
CNN features · 18 papers
- AdaEraser: Training-Free Object Removal via Adaptive Attention Suppression
- Deformba: Vision State Space Model with Adaptive State Fusion
- Formalizing the Binding Problem
- Just Noticeable Difference Modeling for Deep Visual Features
- Learning Global Representation from Queries for Vectorized HD Map Construction
- Looking Locally: Object-Centric Vision Transformers as Foundation Models for Efficient Segmentation
- SCRWKV: Ultra-Compact Structure-Calibrated Vision-RWKV for Topological Crack Segmentation
- SF-Mamba: Rethinking State Space Model for Vision
- Towards Effective Waste Segmentation for Automated Waste Recycling in Cluttered Background
- WorldComp2D: Spatio-semantic Representations of Object Identity and Location from Local Views
- Bio-Vision-Inspired Spiking Neural Networks for Object Detection with Event Cameras
- CODiff: One-Step Diffusion Model for Camouflaged Object Detection
and 6 more in the interactive map.
3D detection and driving · 5 papers
- FoundObj: Self-supervised Foundation Models as Rewards for Label-free 3D Object Segmentation
- Embodied-DETR: End-to-End Temporal 3D Object Detection in Egocentric Views
- MapUQ: Map with Uncertainty Quantification for Robust BEV Vectorized Construction
- OBJVanish: Prompt-Driven Generation of Physically Realizable 3D LiDAR-Invisible Objects
- Radial Scaling Voxelization for Accurate Small Object 3D Detection