- Semantic Segmentation
- Medical Segmentation
- Other Segmentation
- Re-Identification
- text detection and OCR
- Classification
- Super-Resolution
- Detection
- AAAI
- Weakly Supervised
- Supervised
- Gated Path Selection Network for Semantic Segmentation
- MHSAN: Multi-Head Self-Attention Network for Visual Semantic Embedding
- HMANet: Hybrid Multiple Attention Network for Semantic Segmentation in Aerial Images
- Unsupervised Bidirectional Cross-Modality Adaptation via Deeply Synergistic Image and Feature Alignment for Medical Image Segmentation[TMI]
- Universal Semantic Segmentation for Fisheye Urban Driving Images[augmentation ]
- Deep Convolutional Neural Networks with Spatial Regularization, Volume and Star-shape Priori for Image Segmentation
- High-Order Paired-ASPP Networks for Semantic Segmenation
- Other
- Survey and Dataset
- Attention
- Distillation + Knowledge Distillation for Brain Tumor Segmentation
-
Neural Architecture Search
-
Adversarial and unsupervised and Weakly Supervised
- Abdominal multi-organ segmentation with cascaded convolutional and adversarial deep networks
- Brain Metastasis Segmentation Network Trained with Robustness to Annotations with Multiple False Negatives
- e-UDA: Efficient Unsupervised Domain Adaptation for Cross-Site Medical Image Segmentation
- Weakly Supervised Lesion Co-segmentation on CT Scans
- Weakly-Supervised Lesion Segmentation on CT Scans using Co-Segmentation
- A Two-Stream Meticulous Processing Network for Retinal Vessel Segmentation
- An Unsupervised Learning Model for Medical Image Segmentation
-
Attention
- RatLesNetv2: A Fully Convolutional Network for Rodent Brain Lesion Segmentation
- SAUNet: Shape Attentive U-Net for Interpretable Medical Image Segmentation
- Breast mass segmentation based on ultrasonic entropy maps and attention gated U-Net
- Edge-Gated CNNs for Volumetric Semantic Segmentation of Medical Images[[underview MIDL]]
- Liver Segmentation in Abdominal CT Images via Auto-Context Neural Network and Self-Supervised Contour Attention
-
Survey and Benchmark
- Zero-Shot Video Segmentation
- Video
- Instance
-2020 + Cross-Modality Paired-Images Generation for RGB-Infrared Person Re-Identification
- 2020
- VMRFANet:View-Specific Multi-Receptive Field Attention Network for Person Re-identification
- Learning Diverse Features with Part-Level Resolution for Person Re-Identification
- An Implicit Attention Mechanism for Deep Learning Pedestrian Re-identification Frameworks[Code]
- Looking GLAMORous: Vehicle Re-Id in Heterogeneous Cameras Networks with Global and Local Attention
- Person Re-identification by Contour Sketch under Moderate Clothing Change[TPAMI]
- An Empirical Study of Person Re-Identification with Attributes
- Diversity-Achieving Slow-DropBlock Network for Person Re-Identification
- Intra-Camera Supervised Person Re-Identification
- 2020
- 2020
ICCV: 23%-30%
CVPR: 24%-30%
ECCV: 26%-28%
ICME:30%
ACCV: 26%-29%
BMVC: 29%-35%
ICLR: ~30%
MICCAI: ~30%
ICPR: 48%-56%
COLT: 26%-52%
ICML: 25%-32%
IJCAI: 24%-34%
ICIP:50%