ICML 2024 accepted papers on Detection and segmentation
23 of the 2,610 papers accepted at ICML 2024 (0.9%) are on Detection and segmentation, compared with 1.3% at ICML 2023. They fall into 3 topics.
See ICML 2024 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 · 12 papers
- Diving into Underwater: Segment Anything Model Guided Underwater Salient Instance Segmentation and A Large-scale Dataset (6 citations)
- Latent Noise Segmentation: How Neural Noise Leads to the Emergence of Segmentation and Grouping (2 citations)
- Completing Visual Objects via Bridging Generation and Segmentation (1 citation)
- DSD-DA: Distillation-based Source Debiasing for Domain Adaptive Object Detection (1 citation)
- Generative Active Learning for Long-tailed Instance Segmentation (1 citation)
- NExT-Chat: An LMM for Chat, Detection and Segmentation (1 citation)
- Spider: A Unified Framework for Context-dependent Concept Segmentation (1 citation)
- Discrete Latent Perspective Learning for Segmentation and Detection
- Bidirectional Reciprocative Information Communication for Few-Shot Semantic Segmentation
- BLO-SAM: Bi-level Optimization Based Finetuning of the Segment Anything Model for Overfitting-Preventing Semantic Segmentation
- Easing Concept Bleeding in Diffusion via Entity Localization and Anchoring
- Implicit Representations for Constrained Image Segmentation
CNN features · 9 papers
- Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Model (417 citations)
- Proactive Detection of Voice Cloning with Localized Watermarking (7 citations)
- Size-invariance Matters: Rethinking Metrics and Losses for Imbalanced Multi-object Salient Object Detection (1 citation)
- Towards Unified Multi-granularity Text Detection with Interactive Attention (1 citation)
- UPOCR: Towards Unified Pixel-Level OCR Interface (1 citation)
- Scale-Free Image Keypoints Using Differentiable Persistent Homology
- DetKDS: Knowledge Distillation Search for Object Detectors
- ESNet: Evolution and Succession Network for High-Resolution Salient Object Detection
- Learning 1-Bit Tiny Object Detector with Discriminative Feature Refinement