ICLR 2025 accepted papers on Detection and segmentation
58 of the 3,703 papers accepted at ICLR 2025 (1.6%) are on Detection and segmentation, compared with 1.9% at ICLR 2024. They fall into 5 topics.
See ICLR 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 · 24 papers
- MMAD: A Comprehensive Benchmark for Multimodal Large Language Models in Industrial Anomaly Detection (4 citations)
- Open-YOLO 3D: Towards Fast and Accurate Open-Vocabulary 3D Instance Segmentation (4 citations)
- SONICS: Synthetic Or Not - Identifying Counterfeit Songs (3 citations)
- Pursuing Better Decision Boundaries for Long-Tailed Object Detection via Category Information Amount (2 citations)
- Segment Any 3D Object with Language (2 citations)
- Stable Segment Anything Model (1 citation)
- Vision CNNs trained to estimate spatial latents learned similar ventral-stream-aligned representations (1 citation)
- 3D-AffordanceLLM: Harnessing Large Language Models for Open-Vocabulary Affordance Detection in 3D Worlds
- Cyclic Contrastive Knowledge Transfer for Open-Vocabulary Object Detection
- HiBug2: Efficient and Interpretable Error Slice Discovery for Comprehensive Model Debugging
- IMDPrompter: Adapting SAM to Image Manipulation Detection by Cross-View Automated Prompt Learning
- Interaction Asymmetry: A General Principle for Learning Composable Abstractions
and 12 more in the interactive map.
CNN features · 17 papers
- IFORMER: INTEGRATING CONVNET AND TRANSFORMER FOR MOBILE APPLICATION (4 citations)
- RMP-SAM: Towards Real-Time Multi-Purpose Segment Anything (4 citations)
- DECO: Unleashing the Potential of ConvNets for Query-based Detection and Segmentation (1 citation)
- SAMRefiner: Taming Segment Anything Model for Universal Mask Refinement (1 citation)
- Topograph: An Efficient Graph-Based Framework for Strictly Topology Preserving Image Segmentation (1 citation)
- UNIP: Rethinking Pre-trained Attention Patterns for Infrared Semantic Segmentation (1 citation)
- MGMapNet: Multi-Granularity Representation Learning for End-to-End Vectorized HD Map Construction
- Progressive Token Length Scaling in Transformer Encoders for Efficient Universal Segmentation
- R2Det: Exploring Relaxed Rotation Equivariance in 2D Object Detection
- Training-Free Dataset Pruning for Instance Segmentation
- Union-over-Intersections: Object Detection beyond Winner-Takes-All
- YOLO-RD: Introducing Relevant and Compact Explicit Knowledge to YOLO by Retriever-Dictionary
and 5 more in the interactive map.
3D detection and driving · 9 papers
- Gaussian-Det: Learning Closed-Surface Gaussians for 3D Object Detection (1 citation)
- Intent3D: 3D Object Detection in RGB-D Scans Based on Human Intention (1 citation)
- Cocoon: Robust Multi-Modal Perception with Uncertainty-Aware Sensor Fusion
- GrabS: Generative Embodied Agent for 3D Object Segmentation without Scene Supervision
- Learning 3D Perception from Others' Predictions
- MOS: Model Synergy for Test-Time Adaptation on LiDAR-Based 3D Object Detection
- RobuRCDet: Enhancing Robustness of Radar-Camera Fusion in Bird's Eye View for 3D Object Detection
- Uni$^2$Det: Unified and Universal Framework for Prompt-Guided Multi-dataset 3D Detection
- MamBEV: Enabling State Space Models to Learn Birds-Eye-View Representations
Tracking · 5 papers
- Samba: Synchronized Set-of-Sequences Modeling for Multiple Object Tracking (1 citation)
- Track-On: Transformer-based Online Point Tracking with Memory (1 citation)
- Tracking objects that change in appearance with phase synchrony
- CO-MOT: Boosting End-to-end Transformer-based Multi-Object Tracking via Coopetition Label Assignment and Shadow Sets
- OVTR: End-to-End Open-Vocabulary Multiple Object Tracking with Transformer