ICML 2023 accepted papers on Detection and segmentation
25 of the 1,865 papers accepted at ICML 2023 (1.3%) are on Detection and segmentation, compared with 1.1% at ICML 2022. They fall into 3 topics.
See ICML 2023 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 · 14 papers
- SegCLIP: Patch Aggregation with Learnable Centers for Open-Vocabulary Semantic Segmentation (27 citations)
- Open-Vocabulary Universal Image Segmentation with MaskCLIP (19 citations)
- Multi-Modal Classifiers for Open-Vocabulary Object Detection (13 citations)
- Tuning Computer Vision Models With Task Rewards (13 citations)
- X-Paste: Revisiting Scalable Copy-Paste for Instance Segmentation using CLIP and StableDiffusion (5 citations)
- Multiple Thinking Achieving Meta-Ability Decoupling for Object Navigation (4 citations)
- Invariant Slot Attention: Object Discovery with Slot-Centric Reference Frames (2 citations)
- A Critical View of Vision-Based Long-Term Dynamics Prediction Under Environment Misalignment (1 citation)
- Unlocking Slot Attention by Changing Optimal Transport Costs (1 citation)
- Discovering Object-Centric Generalized Value Functions From Pixels
- Provably Learning Object-Centric Representations
- Slot-VAE: Object-Centric Scene Generation with Slot Attention
and 2 more in the interactive map.
CNN features · 10 papers
- Global Context Vision Transformers (36 citations)
- CLUSTSEG: Clustering for Universal Segmentation (26 citations)
- Topologically Faithful Image Segmentation via Induced Matching of Persistence Barcodes (7 citations)
- ACAT: Adversarial Counterfactual Attention for Classification and Detection in Medical Imaging (4 citations)
- Learning Dynamic Query Combinations for Transformer-based Object Detection and Segmentation (2 citations)
- End-to-End Multi-Object Detection with a Regularized Mixture Model
- Learning Affinity with Hyperbolic Representation for Spatial Propagation
- Patch-level Contrastive Learning via Positional Query for Visual Pre-training
- SAAL: Sharpness-Aware Active Learning
- SpeedDETR: Speed-aware Transformers for End-to-end Object Detection
3D detection and driving · 1 paper
- VectorMapNet: End-to-end Vectorized HD Map Learning (35 citations)