ICLR 2022 accepted papers on Detection and segmentation
35 of the 1,095 papers accepted at ICLR 2022 (3.2%) are on Detection and segmentation, compared with 2.6% at ICLR 2021. They fall into 4 topics.
See ICLR 2022 in the interactive map
Submitting to ICLR? Checklist →
Working on something in this area? Describe your idea in scime atlas to see the closest papers by meaning and how crowded the spot has become.
Topics and papers
CNN features · 17 papers
- DAB-DETR: Dynamic Anchor Boxes are Better Queries for DETR (398 citations)
- CrossFormer: A Versatile Vision Transformer Hinging on Cross-scale Attention (315 citations)
- Image BERT Pre-training with Online Tokenizer (205 citations)
- Unsupervised Semantic Segmentation by Distilling Feature Correspondences (113 citations)
- CycleMLP: A MLP-like Architecture for Dense Prediction (98 citations)
- Sparse DETR: Efficient End-to-End Object Detection with Learnable Sparsity (91 citations)
- AS-MLP: An Axial Shifted MLP Architecture for Vision (85 citations)
- PolyLoss: A Polynomial Expansion Perspective of Classification Loss Functions (85 citations)
- GiraffeDet: A Heavy-Neck Paradigm for Object Detection (78 citations)
- Sample and Computation Redistribution for Efficient Face Detection (71 citations)
- Quadtree Attention for Vision Transformers (70 citations)
- ViDT: An Efficient and Effective Fully Transformer-based Object Detector (46 citations)
and 5 more in the interactive map.
Open-set and few-shot detection · 13 papers
- Open-vocabulary Object Detection via Vision and Language Knowledge Distillation (276 citations)
- Language-driven Semantic Segmentation (161 citations)
- Pix2seq: A Language Modeling Framework for Object Detection (128 citations)
- VOS: Learning What You Don't Know by Virtual Outlier Synthesis (75 citations)
- Decoupled Adaptation for Cross-Domain Object Detection (28 citations)
- Salient ImageNet: How to discover spurious features in Deep Learning? (20 citations)
- Objects in Semantic Topology (15 citations)
- R4D: Utilizing Reference Objects for Long-Range Distance Estimation (2 citations)
- Autonomous Learning of Object-Centric Abstractions for High-Level Planning (1 citation)
- Evaluating Disentanglement of Structured Representations (1 citation)
- Conditional Object-Centric Learning from Video
- Object Pursuit: Building a Space of Objects via Discriminative Weight Generation
and 1 more in the interactive map.
