NeurIPS 2026 accepted papers on Detection and segmentation
87 of the 6,080 papers accepted at NeurIPS 2026 (1.4%) are on Detection and segmentation, compared with 1.9% at NeurIPS 2025. They fall into 5 topics.
See NeurIPS 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 · 46 papers
- Detect Anything in Graphic Design: Element-Level Rewards for Autoregressive Detection
- Early Semantic Grounding in Image Editing Models for Zero-Shot Referring Image Segmentation
- From Pixels to Concepts: Do Segmentation Models Understand What They Segment?
- Multi-Part Object Representations via Graph Structures and Co-Part Discovery
- OBJECT-UNI: A Unified Model for Object-Centric Spatial Understanding and Controllable Generation
- On the Relaxation of Conditional Independence Assumption for Image Segmentation
- Prompting Diffusion Models for Zero-Shot Instance Segmentation
- Rethinking Infrared Small Target Detection: A Foundation Driven Efficient Paradigm
- SANEval: Open-Vocabulary Compositional Benchmarks with Failure-mode Diagnosis
- SetCon: Towards Open-Ended Referring Segmentation via Set-Level Concept Prediction
- Unlocking Compositional Generalization in Continual Few-Shot Learning
- BAPM: Boundary-Aware Prompt Mining for Training-Free Few-Shot Medical Image Segmentation
and 34 more in the interactive map.
CNN features · 29 papers
- GLACIER: Rethinking Mass Spectrum Prediction as an Object Detection Problem (1 citation)
- AdapToPASS: Ambiguity-aware Adaptive Spherical Transformer for Panoramic Semantic Segmentation
- Beyond Chamfer Distance: Granular Order-aware Evaluation Metric For Online Mapping
- Beyond ViT Tokens: Masked-Diffusion Pretrained Convolutional Pathology Foundation Model for Cell-Level Dense Prediction
- ContextShift: A Controlled Benchmark for Context Dependence in Object Detection
- M$^2$E-UAV: A Benchmark and Analysis for Onboard Motion-on-Motion Event-Based Tiny UAV Detection
- Order Matters: Competition-Guided Query Ordering for RNN-Based Object Detection
- RATS! Patches Talk Through Registers: Emergent Parts in Register Attention Transformers
- $\textbf{EchMo}$: End-to-End Radar Echo Segmentation
- 3DABSeg: Adaptive 3D Ankle Bone Segmentation with Multiscale Feature Fusion Mixture-of-Experts
- Beyond Pixel-wise Supervision: Local Structure Regularization for Semantic Segmentation
- BiHashFormer: Hash-Driven Dual-Branch Transformer for Efficient Object Detection in HRW Shots
and 17 more in the interactive map.
3D detection and driving · 6 papers
- RefineAny3D: Depth Refinement as Semantic Alignment for Monocular 3D Detection
- FIND: Frequency Invariance Disentanglement for Test-Time Adaptation in LiDAR 3D Detection
- Rethinking Geometric Depth in Monocular 3D Object Detection: A Projection-Consistent Reformulation
- Towards Effective and Transferable Physical Camouflage against Multi-View BEV-based 3D Perception in Autonomous Driving
- Virtual Task Prompting for Multi-Task Scene Understanding
- WayPOP: A Panoramic Open-Set Panoptic Tracking Benchmark
Weakly supervised detection and segmentation · 5 papers
- Less Supervision, Better Generalization: Weakly Supervised Fake Region Localization in Diffusion-Edited Images
- Object Detection Benchmarks are Incomplete: The Role of Label Errors and Annotation Uncertainty
- Improved Weakly Supervised Semantic Segmentation with A Relationally Optimized Prototype Memory Bank Framework
- Trainable Topology Supervision under Structurally Unreliable Pseudo Supervision
- WsiSSM: A Weakly Supervised Subset-Matching Framework for Unified Classification and Segmentation of Histopathology Whole Slide Images