mlsanityData to 7 Oct 2026

Instance-sensitive Fully Convolutional Networks

arXiv 1603.08678 ↗First posted 29 Mar 2016cs.CVcited by 36

Not on the map. Why?

Abstract (arXiv)

Fully convolutional networks (FCNs) have been proven very successful for semantic segmentation, but the FCN outputs are unaware of object instances. In this paper, we develop FCNs that are capable of proposing instance-level segment candidates. In contrast to the previous FCN that generates one score map, our FCN is designed to compute a small set of instance-sensitive score maps, each of which is the outcome of a pixel-wise classifier of a relative position to instances. On top of these instance-sensitive score maps, a simple assembling module is able to output instance candidate at each position. In contrast to the recent DeepMask method for segmenting instances, our method does not have any high-dimensional layer related to the mask resolution, but instead exploits image local coherence for estimating instances. We present competitive results of instance segment proposal on both PASCAL VOC and MS COCO.

Key facts. Cited by 36 papers in the map (data through 7 Oct 2026). First posted on arXiv 29 Mar 2016.

Builds on

No reference list yet.

Built on by

Cited by year

Citing papers per year: 2021: 12; 2022: 13; 2023: 6; 2024: 3; 2025: 2.

36 papers.

Sort:

By area:

  1. 2021Hierarchical Aggregation for 3D Instance Segmentationcited by 126
  2. 2021SG-Net: Spatial Granularity Network for One-Stage Video Instance Segmentationcited by 87
  3. 2021MOST: A Multi-Oriented Scene Text Detector with Localization Refinementcited by 33
  4. 2021Instance-wise Occlusion and Depth Orders in Natural Scenescited by 31
  5. 2023Semantic Image Segmentation: Two Decades of Researchcited by 26
  6. 2021BoxeR: Box-Attention for 2D and 3D Transformerscited by 22
  7. 2021Target-Aware Object Discovery and Association for Unsupervised Video Multi-Object Segmentationcited by 21
  8. 2021Instance and Panoptic Segmentation Using Conditional Convolutionscited by 19
  9. 2022Learning Equivariant Segmentation with Instance-Unique Queryingcited by 17
  10. 2022Fashionformer: A simple, Effective and Unified Baseline for Human Fashion Segmentation and Recognitioncited by 16
  11. 2022Panoramic Panoptic Segmentation: Insights Into Surrounding Parsing for Mobile Agents via Unsupervised Contrastive Learningcited by 14
  12. 2021Improving Video Instance Segmentation via Temporal Pyramid Routingcited by 13
24 more
  1. 2022Deep Learning Serves Traffic Safety Analysis: A Forward-looking Reviewcited by 13
  2. 2022Solve the Puzzle of Instance Segmentation in Videos: A Weakly Supervised Framework with Spatio-Temporal Collaborationcited by 11
  3. 2023Boosting Low-Data Instance Segmentation by Unsupervised Pre-training with Saliency Promptcited by 11
  4. 2021INSTA-YOLO: Real-Time Instance Segmentationcited by 7
  5. 2022A Survey of Computer Vision Technologies In Urban and Controlled-environment Agriculturecited by 6
  6. 2022Test-time Adaptation vs. Training-time Generalization: A Case Study in Human Instance Segmentation using Keypoints Estimationcited by 5
  7. 2023[CLS] Token is All You Need for Zero-Shot Semantic Segmentationcited by 5
  8. 2021BoundarySqueeze: Image Segmentation as Boundary Squeezingcited by 4
  9. 2024Unsupervised Pre-training with Language-Vision Prompts for Low-Data Instance Segmentationcited by 4
  10. 2022Learn Fast, Segment Well: Fast Object Segmentation Learning on the iCub Robotcited by 3
  11. 20222D Human Pose Estimation with Explicit Anatomical Keypoints Structure Constraintscited by 3
  12. 2021Understanding Pixel-level 2D Image Semantics with 3D Keypoint Knowledge Enginecited by 2
  13. 2022Semantic Segmentation-Assisted Instance Feature Fusion for Multi-Level 3D Part Instance Segmentationcited by 2
  14. 2023Towards Robust Video Instance Segmentation with Temporal-Aware Transformercited by 2
  15. 2023Single-stage Multi-human Parsing via Point Sets and Center-based Offsetscited by 2
  16. 2024A foundation model enpowered by a multi-modal prompt engine for universal seismic geobody interpretation across surveyscited by 2
  17. 2021Contour Loss for Instance Segmentation via k-step Distance Transformation Imagecited by 1
  18. 2022SODAR: Segmenting Objects by DynamicallyAggregating Neighboring Mask Representationscited by 1
  19. 2022Instance Segmentation with Cross-Modal Consistencycited by 1
  20. 2023Deep Convolutional Neural Network for Plume Rise Measurements in Industrial Environmentscited by 1
  21. 2025VISUALCENT: Visual Human Analysis using Dynamic Centroid Representationcited by 1
  22. 2022Fully Convolutional Fractional Scalingcited by 0
  23. 2024P2Seg: Pointly-supervised Segmentation via Mutual Distillationcited by 0
  24. 2025Keypoints as Dynamic Centroids for Unified Human Pose and Segmentationcited by 0