# SCNet: Training Inference Sample Consistency for Instance Segmentation

arXiv: https://arxiv.org/abs/2012.10150 · HTML: https://mlsanity.com/paper/2012.10150/

## Key facts

- Cited by 38 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 18 Dec 2020.

## Built on by (most cited first, 30 of 38)

- [RSPrompter: Learning to Prompt for Remote Sensing Instance Segmentation based on Visual Foundation Model](https://mlsanity.com/paper/2306.16269/) (2023)
- [Instances as Queries](https://mlsanity.com/paper/2105.01928/) (2021)
- [M6Doc: A Large-Scale Multi-Format, Multi-Type, Multi-Layout, Multi-Language, Multi-Annotation Category Dataset for Modern Document Layout Analysis](https://mlsanity.com/paper/2305.08719/) (2023)
- [TransNorm: Transformer Provides a Strong Spatial Normalization Mechanism for a Deep Segmentation Model](https://mlsanity.com/paper/2207.13415/) (2022)
- [From Forks to Forceps: A New Framework for Instance Segmentation of Surgical Instruments](https://mlsanity.com/paper/2211.16200/) (2022)
- [Object Segmentation-Assisted Inter Prediction for Versatile Video Coding](https://mlsanity.com/paper/2403.11694/) (2024)
- [Learning Equivariant Segmentation with Instance-Unique Querying](https://mlsanity.com/paper/2210.00911/) (2022)
- [MAE-DET: Revisiting Maximum Entropy Principle in Zero-Shot NAS for Efficient Object Detection](https://mlsanity.com/paper/2111.13336/) (2021)
- [SOIT: Segmenting Objects with Instance-Aware Transformers](https://mlsanity.com/paper/2112.11037/) (2021)
- [Learning to Aggregate Multi-Scale Context for Instance Segmentation in Remote Sensing Images](https://mlsanity.com/paper/2111.11057/) (2021)
- [Image Quality Assessment: From Human to Machine Preference](https://mlsanity.com/paper/2503.10078/) (2025)
- [Multi-scale Regional Attention Deeplab3+: Multiple Myeloma Plasma Cells Segmentation in Microscopic Images](https://mlsanity.com/paper/2105.06238/) (2021)
- [USIS16K: High-Quality Dataset for Underwater Salient Instance Segmentation](https://mlsanity.com/paper/2506.19472/) (2025)
- [Visual Instruction Pretraining for Domain-Specific Foundation Models](https://mlsanity.com/paper/2509.17562/) (2025)
- [VIPriors 2: Visual Inductive Priors for Data-Efficient Deep Learning Challenges](https://mlsanity.com/paper/2201.08625/) (2022)
- [BoundarySqueeze: Image Segmentation as Boundary Squeezing](https://mlsanity.com/paper/2105.11668/) (2021)
- [DocSAM: Unified Document Image Segmentation via Query Decomposition and Heterogeneous Mixed Learning](https://mlsanity.com/paper/2504.04085/) (2025)
- [QSAM-Net: Rain streak removal by quaternion neural network with self-attention module](https://mlsanity.com/paper/2208.04346/) (2022)
- [Multi-Task Learning-Enabled Automatic Vessel Draft Reading for Intelligent Maritime Surveillance](https://mlsanity.com/paper/2310.07212/) (2023)
- [A Simulation Framework for Electromagnetic Signal Injection Attacks on Image Sensors](https://mlsanity.com/paper/2408.05124/) (2024)
- [Tuning a SAM-Based Model with Multi-Cognitive Visual Adapter to Remote Sensing Instance Segmentation](https://mlsanity.com/paper/2408.08576/) (2024)
- [Insight Any Instance: Promptable Instance Segmentation for Remote Sensing Images](https://mlsanity.com/paper/2409.07022/) (2024)
- [DynamicVis: Dynamic Visual Perception for Efficient Remote Sensing Foundation Models](https://mlsanity.com/paper/2503.16426/) (2025)
- [EffSeg: Efficient Fine-Grained Instance Segmentation using Structure-Preserving Sparsity](https://mlsanity.com/paper/2307.01545/) (2023)
- [USIS-PGM: Photometric Gaussian Mixtures for Underwater Salient Instance Segmentation](https://mlsanity.com/paper/2603.13961/) (2026)
- [Segmentation of Multiple Myeloma Plasma Cells in Microscopy Images with Noisy Labels](https://mlsanity.com/paper/2111.05125/) (2021)
- [Lightweight HDR Camera ISP for Robust Perception in Dynamic Illumination Conditions via Fourier Adversarial Networks](https://mlsanity.com/paper/2204.01795/) (2022)
- [Few-Shot Object Detection with Proposal Balance Refinement](https://mlsanity.com/paper/2204.10527/) (2022)
- [Look in Different Views: Multi-Scheme Regression Guided Cell Instance Segmentation](https://mlsanity.com/paper/2208.08078/) (2022)
- [OBSeg: Accurate and Fast Instance Segmentation Framework Using Segmentation Foundation Models with Oriented Bounding Box Prompts](https://mlsanity.com/paper/2401.08174/) (2024)

## Abstract (arXiv)

Cascaded architectures have brought significant performance improvement in object detection and instance segmentation. However, there are lingering issues regarding the disparity in the Intersection-over-Union (IoU) distribution of the samples between training and inference. This disparity can potentially exacerbate detection accuracy. This paper proposes an architecture referred to as Sample Consistency Network (SCNet) to ensure that the IoU distribution of the samples at training time is close to that at inference time. Furthermore, SCNet incorporates feature relay and utilizes global contextual information to further reinforce the reciprocal relationships among classifying, detecting, and segmenting sub-tasks. Extensive experiments on the standard COCO dataset reveal the effectiveness of the proposed method over multiple evaluation metrics, including box AP, mask AP, and inference speed. In particular, while running 38% faster, the proposed SCNet improves the AP of the box and mask predictions by respectively 1.3 and 2.3 points compared to the strong Cascade Mask R-CNN baseline. Code is available at urlhttps://github.com/thangvubk/SCNet.