DETR 34
- Enhancing Your Trained DETRs with Box Refinement
- Enhanced Training of Query-Based Object Detection via Selective Query Recollection
- Dense Distinct Query for End-to-End Object Detection
- FP-DETR: Detection Transformer Advanced by Fully Pre-training
- Fast Convergence of DETR with Spatially Modulated Co-Attention
- Accelerating DETR Convergence via Semantic-Aligned Matching
- DETReg: Unsupervised Pretraining With Region Priors for Object Detection
- UP-DETR: Unsupervised Pre-Training for Object Detection With Transformers
- Siamese DETR
- Lite DETR : An Interleaved Multi-Scale Encoder for Efficient DETR
- Anchor DETR: Query Design for Transformer-Based Object Detection
- Efficient DETR: Improving End-to-End Object Detector with Dense Prior
- DETR Does Not Need Multi-Scale or Locality Design
- Cascade-DETR: Delving into High-Quality Universal Object Detection
- Decoupled DETR: Spatially Disentangling Localization and Classification for Improved End-to-End Object Detection
- Sparse DETR: Efficient end-to-end object detection with learnable sparsity
- DETRs with Collaborative Hybrid Assignments Training
- MS-DETR: Efficient DETR Training with Mixed Supervision
- Incremental-DETR: Incremental Few-Shot Object Detection via Self-Supervised Learning
- DAC-DETR: Divide the Attention Layers and Conquer
- SimPLR: A Simple and Plain Transformer for Object Detection and Segmentation
- BoxeR: Box-Attention for 2D and 3D Transformers
- Gen2Det: Generate to Detect
- Cal-DETR: Calibrated Detection Transformer
- Rank-DETR for High Quality Object Detection
- Align-DETR: Improving DETR with Simple IoU-aware BCE loss
- Less is More: Focus Attention for Efficient DETR
- AlignDet: Aligning Pre-training and Fine-tuning in Object Detection
- StageInteractor: Query-based Object Detector with Cross-stage Interaction
- Towards Efficient Use of Multi-Scale Features in Transformer-Based Object Detectors
- Towards Data-Efficient Detection Transformers
- DESTR: Object Detection with Split Transformer
- DETRDistill: A Universal Knowledge Distillation Framework for DETR-families
- AdaMixer: A Fast-Converging Query-Based Object Detector