- List up computer vision SOTA paper
- Fast and Accurate Model Scaling : https://arxiv.org/pdf/2103.06877.pdf
- EfficientNetV2: Smaller Models and Faster Training : https://arxiv.org/pdf/2104.00298.pdf
- TransUNet: Transformers Make Strong Encoders for Medical Image Segmentation : https://arxiv.org/abs/2102.04306
- RefineMask: Towards High-Quality Instance Segmentation with Fine-Grained Features : https://arxiv.org/pdf/2104.08569.pdf
- Rethinking BiSeNet For Real-time Semantic Segmentation : https://arxiv.org/pdf/2104.13188.pdf
- Lite-HRNet: A Lightweight High-Resolution Network : https://arxiv.org/pdf/2104.06403.pdf
- You Only Look One-level Feature : https://arxiv.org/pdf/2103.09460.pdf
- Track to Detect and Segment: An Online Multi-Object Tracker : https://arxiv.org/pdf/2103.08808v1.pdf
- FairMOT: On the Fairness of Detection and Re-Identification in Multiple Object Tracking : https://arxiv.org/pdf/2004.01888v5.pdf
- RetinaTrack: Online Single Stage Joint Detection and Tracking : https://arxiv.org/pdf/2003.13870.pdf
- TransTrack: Multiple Object Tracking with Transformer : https://arxiv.org/pdf/2012.15460.pdf : https://github.com/PeizeSun/TransTrack
- TrackFormer: Multi-Object Tracking with Transformers : https://arxiv.org/pdf/2101.02702.pdf : https://github.com/timmeinhardt/trackformer
- LoFTR: Detector-Free Local Feature Matching with Transformers : https://arxiv.org/pdf/2104.00680.pdf
- Rethinking Architecture Selection in Differentiable NAS : https://openreview.net/forum?id=PKubaeJkw3