ENInst: Enhancing Weakly-supervised Low-shot Instance Segmentation
Not on the map. Why?
Abstract (arXiv)
We address a weakly-supervised low-shot instance segmentation, an annotation-efficient training method to deal with novel classes effectively. Since it is an under-explored problem, we first investigate the difficulty of the problem and identify the performance bottleneck by conducting systematic analyses of model components and individual sub-tasks with a simple baseline model. Based on the analyses, we propose ENInst with sub-task enhancement methods: instance-wise mask refinement for enhancing pixel localization quality and novel classifier composition for improving classification accuracy. Our proposed method lifts the overall performance by enhancing the performance of each sub-task. We demonstrate that our ENInst is 7.5 times more efficient in achieving comparable performance to the existing fully-supervised few-shot models and even outperforms them at times.
Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 59 of its 86 references that are in the map. First posted on arXiv 20 Feb 2023.
Builds on
59 of 86 references.
References · 59
- 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
- 2014Microsoft COCO: Common Objects in Contextcited by 17,608
- 2017Mask R-CNNcited by 7,277
- 2017mixup: Beyond Empirical Risk Minimizationcited by 5,183
- 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,897
- 2016DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFscited by 3,241
- 2017Prototypical Networks for Few-shot Learningcited by 3,015
- 2016V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentationcited by 2,292
- 2016Matching Networks for One Shot Learningcited by 2,255
- 2019FCOS: Fully Convolutional One-Stage Object Detectioncited by 1,577
- 2017Deep Image Priorcited by 1,098
- 2019A Closer Look at Few-shot Classificationcited by 684
38 more
- 2019Bridging the Gap Between Anchor-based and Anchor-free Detection via Adaptive Training Sample Selectioncited by 540
- 2019PANet: Few-Shot Image Semantic Segmentation with Prototype Alignmentcited by 449
- 2019YOLACT: Real-time Instance Segmentationcited by 443
- 2020Conditional Convolutions for Instance Segmentationcited by 314
- 2019A Baseline for Few-Shot Image Classificationcited by 298
- 2020Frustratingly Simple Few-Shot Object Detectioncited by 282
- 2016Simple Does It: Weakly Supervised Instance and Semantic Segmentationcited by 227
- 2016UnitBox: An Advanced Object Detection Networkcited by 205
- 2019CenterMask : Real-Time Anchor-Free Instance Segmentationcited by 201
- 2019PolarMask: Single Shot Instance Segmentation with Polar Representationcited by 188
- 2019Meta R-CNN : Towards General Solver for Instance-level Few-shot Learningcited by 182
- 2020BoxInst: High-Performance Instance Segmentation with Box Annotationscited by 151
- 2020BlendMask: Top-Down Meets Bottom-Up for Instance Segmentationcited by 145
- 2019Charting the Right Manifold: Manifold Mixup for Few-shot Learningcited by 136
- 2018Efficient Interactive Annotation of Segmentation Datasets with Polygon-RNN++cited by 120
- 2021Simpler is Better: Few-shot Semantic Segmentation with Classifier Weight Transformercited by 116
- 2019Large-scale interactive object segmentation with human annotatorscited by 110
- 2021BBAM: Bounding Box Attribution Map for Weakly Supervised Semantic and Instance Segmentationcited by 105
- 2019TensorMask: A Foundation for Dense Object Segmentationcited by 101
- 2018Weakly Supervised Instance Segmentation using Class Peak Responsecited by 75
- 2021Mining Latent Classes for Few-shot Segmentationcited by 69
- 2017Learning to Segment Every Thingcited by 65
- 2017MaskLab: Instance Segmentation by Refining Object Detection with Semantic and Direction Featurescited by 54
- 2018Learning Compositional Representations for Few-Shot Recognitioncited by 50
- 2022Singular Value Fine-tuning: Few-shot Segmentation requires Few-parameters Fine-tuningcited by 50
- 2021Incremental Few-Shot Instance Segmentationcited by 49
- 2020FGN: Fully Guided Network for Few-Shot Instance Segmentationcited by 46
- 2018One-Shot Instance Segmentationcited by 43
- 2019ShapeMask: Learning to Segment Novel Objects by Refining Shape Priorscited by 43
- 2015Instance-Level Segmentation for Autonomous Driving with Deep Densely Connected MRFscited by 32
- 2019Image Captioning with Very Scarce Supervised Data: Adversarial Semi-Supervised Learning Approachcited by 30
- 2018Few-Shot Segmentation Propagation with Guided Networkscited by 29
- 2019Variational Prototyping-Encoder: One-Shot Learning with Prototypical Imagescited by 22
- 2018MetaAnchor: Learning to Detect Objects with Customized Anchorscited by 21
- 2021Weakly-supervised Instance Segmentation via Class-agnostic Learning with Salient Imagescited by 20
- 2022iFS-RCNN: An Incremental Few-shot Instance Segmentercited by 19
- 2019Where are the Masks: Instance Segmentation with Image-level Supervisioncited by 18
- 2022Prediction Calibration for Generalized Few-shot Semantic Segmentationcited by 16
50 most cited of 59 All 59 (JSON)
Built on by
Citing papers per year: 2023: 1; 2024: 0; 2025: 1.
2 papers.