ICLR 2026 accepted papers on Detection and segmentation
63 of the 5,358 papers accepted at ICLR 2026 (1.2%) are on Detection and segmentation, compared with 1.6% at ICLR 2025. They fall into 5 topics.
See ICLR 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 · 36 papers
- SAM 3: Segment Anything with Concepts (13 citations)
- AMLRIS: Alignment-aware Masked Learning for Referring Image Segmentation
- Beyond In-Domain Detection: SpikeScore for Cross-Domain Hallucination Detection
- DeCo-DETR: Decoupled Cognition DETR for efficient Open-Vocabulary Object Detection
- DETR-ViP: Detection Transformer with Robust Discriminative Visual Prompts
- ForestPersons: A Large-Scale Dataset for Under-Canopy Missing Person Detection
- From Vicious to Virtuous Cycles: Synergistic Representation Learning for Unsupervised Video Object-Centric Learning
- FSOD-VFM: Few-Shot Object Detection with Vision Foundation Models and Graph Diffusion
- gen2seg: Generative Models Enable Generalizable Instance Segmentation
- K-Prism: A Knowledge-Guided and Prompt Integrated Universal Medical Image Segmentation Model
- Object-Centric World Models from Few-Shot Annotations for Sample-Efficient Reinforcement Learning
- Person-Centric Annotations of LAION-400M: Auditing Bias and Its Transfer to Models
and 24 more in the interactive map.
CNN features · 16 papers
- RF-DETR: Neural Architecture Search for Real-Time Detection Transformers (4 citations)
- Disco: Densely-overlapping Cell Instance Segmentation via Adjacency-aware Collaborative Coloring
- Exploring Specular Reflection Inconsistency for Generalizable Face Forgery Detection
- Inlier-Centric Post-Training Quantization for Object Detection Models
- Maximizing Asynchronicity in Event-based Neural Networks
- OmniCT: Towards a Unified Slice-Volume LVLM for Comprehensive CT Analysis
- Online Navigation Refinement: Achieving Lane-Level Guidance by Associating Standard-Definition and Online Perception Maps
- Towards Reliable Detection of Empty Space: Conditional Marked Point Processes for Object Detection
- Certifying the Full YOLO Pipeline: A Probabilistic Verification Approach
- CORDS - Continuous Representations of Discrete Structures
- DiffuDETR: Rethinking Detection Transformers with Diffusion Process
- Enabling True Global Perception in State Space Models for Visual Tasks
and 4 more in the interactive map.
3D detection and driving · 4 papers
- AsyncBEV: Cross-modal flow alignment in Asynchronous 3D Object Detection
- Fore-Mamba3D: Mamba-based Foreground-Enhanced Encoding for 3D Object Detection
- GaussianFusion: Unified 3D Gaussian Representation for Multi-Modal Fusion Perception
- Detecting Temporal Misalignment Attacks in Multimodal Fusion for Autonomous Driving
Weakly supervised detection and segmentation · 4 papers
- Bootstrapping MLLM for Weakly‑Supervised Class‑Agnostic Object Counting
- SPWOOD: Sparse Partial Weakly-Supervised Oriented Object Detection
- TRACE: Your Diffusion Model is Secretly an Instance Edge Detector
- Point2RBox-v3: Self-Bootstrapping from Point Annotations via Integrated Pseudo-Label Refinement and Utilization