ICLR 2023 accepted papers on Detection and segmentation
53 of the 1,575 papers accepted at ICLR 2023 (3.4%) are on Detection and segmentation, compared with 3.2% at ICLR 2022. They fall into 5 topics.
See ICLR 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 · 22 papers
- Open-Vocabulary Object Detection upon Frozen Vision and Language Models (37 citations)
- Learning Object-Language Alignments for Open-Vocabulary Object Detection (36 citations)
- Bridging the Gap to Real-World Object-Centric Learning (30 citations)
- ViewCo: Discovering Text-Supervised Segmentation Masks via Multi-View Semantic Consistency (16 citations)
- Soft Neighbors are Positive Supporters in Contrastive Visual Representation Learning (14 citations)
- Equivariant Descriptor Fields: SE(3)-Equivariant Energy-Based Models for End-to-End Visual Robotic Manipulation Learning (11 citations)
- Multi-skill Mobile Manipulation for Object Rearrangement (9 citations)
- Compositional Prompt Tuning with Motion Cues for Open-vocabulary Video Relation Detection (8 citations)
- A Simple Approach for Visual Room Rearrangement: 3D Mapping and Semantic Search (5 citations)
- GOOD: Exploring geometric cues for detecting objects in an open world (5 citations)
- Improving Object-centric Learning with Query Optimization (4 citations)
- LMSeg: Language-guided Multi-dataset Segmentation (2 citations)
and 10 more in the interactive map.
CNN features · 20 papers
- DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detection (771 citations)
- Vision Transformer Adapter for Dense Predictions (199 citations)
- The KFIoU Loss for Rotated Object Detection (90 citations)
- Designing BERT for Convolutional Networks: Sparse and Hierarchical Masked Modeling (37 citations)
- Reversible Column Networks (21 citations)
- Explicit Box Detection Unifies End-to-End Multi-Person Pose Estimation (16 citations)
- Masked Image Modeling with Denoising Contrast (8 citations)
- Patch-Level Contrasting without Patch Correspondence for Accurate and Dense Contrastive Representation Learning (8 citations)
- GPViT: A High Resolution Non-Hierarchical Vision Transformer with Group Propagation (7 citations)
- Masked Distillation with Receptive Tokens (7 citations)
- PatchDCT: Patch Refinement for High Quality Instance Segmentation (5 citations)
- ODAM: Gradient-based Instance-Specific Visual Explanations for Object Detection (4 citations)
and 8 more in the interactive map.
Weakly supervised detection and segmentation · 6 papers
- H2RBox: Horizontal Box Annotation is All You Need for Oriented Object Detection (24 citations)
- Unsupervised Semantic Segmentation with Self-supervised Object-centric Representations (16 citations)
- ImaginaryNet: Learning Object Detectors without Real Images and Annotations (5 citations)
- Weakly-supervised HOI Detection via Prior-guided Bi-level Representation Learning (5 citations)
- Weakly Supervised Knowledge Transfer with Probabilistic Logical Reasoning for Object Detection
- Bayes-MIL: A New Probabilistic Perspective on Attention-based Multiple Instance Learning for Whole Slide Images
3D detection and driving · 4 papers
- BEVDistill: Cross-Modal BEV Distillation for Multi-View 3D Object Detection (28 citations)
- DBQ-SSD: Dynamic Ball Query for Efficient 3D Object Detection (12 citations)
- Unsupervised 3D Object Learning through Neuron Activity aware Plasticity
- 3D Segmenter: 3D Transformer based Semantic Segmentation via 2D Panoramic Distillation