NeurIPS 2018 accepted papers on Detection and segmentation
27 of the 1,008 papers accepted at NeurIPS 2018 (2.7%) are on Detection and segmentation, compared with 1.2% at NeurIPS 2017. They fall into 4 topics.
See NeurIPS 2018 in the interactive map
Submitting to NeurIPS? 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 · 12 papers
- Sanity Checks for Saliency Maps (580 citations)
- Searching for Efficient Multi-Scale Architectures for Dense Image Prediction (348 citations)
- Beyond Grids: Learning Graph Representations for Visual Recognition (165 citations)
- Neighbourhood Consensus Networks (151 citations)
- Pelee: A Real-Time Object Detection System on Mobile Devices (101 citations)
- FishNet: A Versatile Backbone for Image, Region, and Pixel Level Prediction (93 citations)
- MetaAnchor: Learning to Detect Objects with Customized Anchors (88 citations)
- SNIPER: Efficient Multi-Scale Training (55 citations)
- Revisiting Multi-Task Learning with ROCK: a Deep Residual Auxiliary Block for Visual Detection (40 citations)
- DifNet: Semantic Segmentation by Diffusion Networks (22 citations)
- Sequential Context Encoding for Duplicate Removal (20 citations)
- Submodular Field Grammars: Representation, Inference, and Application to Image Parsing (4 citations)
Open-set and few-shot detection · 11 papers
- Deep Anomaly Detection Using Geometric Transformations (398 citations)
- A Probabilistic U-Net for Segmentation of Ambiguous Images (151 citations)
- Hybrid Knowledge Routed Modules for Large-scale Object Detection (76 citations)
- Learning Hierarchical Semantic Image Manipulation through Structured Representations (68 citations)
- Context-aware Synthesis and Placement of Object Instances (65 citations)
- Unsupervised Video Object Segmentation for Deep Reinforcement Learning (55 citations)
- Adversarial Scene Editing: Automatic Object Removal from Weak Supervision (51 citations)
- Partially-Supervised Image Captioning (26 citations)
- Object-Oriented Dynamics Predictor (20 citations)
- Modelling and unsupervised learning of symmetric deformable object categories (11 citations)
- A loss framework for calibrated anomaly detection
Weakly supervised detection and segmentation · 3 papers
Tracking · 1 paper
- Deep Attentive Tracking via Reciprocative Learning (8 citations)
