# SGNet: A Super-class Guided Network for Image Classification and Object Detection

arXiv: https://arxiv.org/abs/2104.12898 · HTML: https://mlsanity.com/paper/2104.12898/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 37 references that are in the map.
- First posted on arXiv 26 Apr 2021.

## Builds on (most cited first, 25 of 25)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications](https://mlsanity.com/paper/1704.04861/) (2017)
- [Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification](https://mlsanity.com/paper/1502.01852/) (2015)
- [SSD: Single Shot MultiBox Detector](https://mlsanity.com/paper/1512.02325/) (2015)
- [Fast R-CNN](https://mlsanity.com/paper/1504.08083/) (2015)
- [Accurate, Large Minibatch SGD: Training ImageNet in 1 Hour](https://mlsanity.com/paper/1706.02677/) (2017)
- [Bottom-Up and Top-Down Attention for Image Captioning and Visual Question Answering](https://mlsanity.com/paper/1707.07998/) (2017)
- [SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size](https://mlsanity.com/paper/1602.07360/) (2016)
- [Image Captioning with Semantic Attention](https://mlsanity.com/paper/1603.03925/) (2016)
- [Salient Object Detection in the Deep Learning Era: An In-Depth Survey](https://mlsanity.com/paper/1904.09146/) (2019)
- [Single-Shot Refinement Neural Network for Object Detection](https://mlsanity.com/paper/1711.06897/) (2017)
- [Boosting Image Captioning with Attributes](https://mlsanity.com/paper/1611.01646/) (2016)
- [Tree-CNN: A Hierarchical Deep Convolutional Neural Network for Incremental Learning](https://mlsanity.com/paper/1802.05800/) (2018)
- [Learning Depth from Single Images with Deep Neural Network Embedding Focal Length](https://mlsanity.com/paper/1803.10039/) (2018)
- [Deep Feature Augmentation for Occluded Image Classification](https://mlsanity.com/paper/2011.00768/) (2020)
- [Recovering the Missing Link: Predicting Class-Attribute Associations for Unsupervised Zero-Shot Learning](https://mlsanity.com/paper/1610.04787/) (2016)
- [MDFN: Multi-Scale Deep Feature Learning Network for Object Detection](https://mlsanity.com/paper/1912.04514/) (2019)
- [ZoomCount: A Zooming Mechanism for Crowd Counting in Static Images](https://mlsanity.com/paper/2002.12256/) (2020)
- [Toward Learning a Unified Many-to-Many Mapping for Diverse Image Translation](https://mlsanity.com/paper/1905.08766/) (2019)
- [Location-Aware Box Reasoning for Anchor-Based Single-Shot Object Detection](https://mlsanity.com/paper/2007.06233/) (2020)
- [Object Detection with Convolutional Neural Networks](https://mlsanity.com/paper/1912.01844/) (2019)
- [Boosting Occluded Image Classification via Subspace Decomposition Based Estimation of Deep Features](https://mlsanity.com/paper/2001.04066/) (2020)

## Built on by (most cited first, 13 of 13)

- [Miti-DETR: Object Detection based on Transformers with Mitigatory Self-Attention Convergence](https://mlsanity.com/paper/2112.13310/) (2021)
- [An Unsupervised Domain Adaptation Model based on Dual-module Adversarial Training](https://mlsanity.com/paper/2112.15555/) (2021)
- [SuperDisco: Super-Class Discovery Improves Visual Recognition for the Long-Tail](https://mlsanity.com/paper/2304.00101/) (2023)
- [A Fine-Grained Visual Attention Approach for Fingerspelling Recognition in the Wild](https://mlsanity.com/paper/2105.07625/) (2021)
- [Semantic Clustering based Deduction Learning for Image Recognition and Classification](https://mlsanity.com/paper/2112.13165/) (2021)
- [T2FPV: Dataset and Method for Correcting First-Person View Errors in Pedestrian Trajectory Prediction](https://mlsanity.com/paper/2209.11294/) (2022)
- [MOFA: A Model Simplification Roadmap for Image Restoration on Mobile Devices](https://mlsanity.com/paper/2308.12494/) (2023)
- [A Discriminative Channel Diversification Network for Image Classification](https://mlsanity.com/paper/2112.05861/) (2021)
- [Multiple Classifiers Based Maximum Classifier Discrepancy for Unsupervised Domain Adaptation](https://mlsanity.com/paper/2108.00610/) (2021)
- [Towards More Effective PRM-based Crowd Counting via A Multi-resolution Fusion and Attention Network](https://mlsanity.com/paper/2112.09664/) (2021)
- [Robust 3D Point Clouds Classification based on Declarative Defenders](https://mlsanity.com/paper/2410.09691/) (2024)
- [O1O: Grouping of Known Classes to Identify Unknown Objects as Odd-One-Out](https://mlsanity.com/paper/2410.07514/) (2024)
- [Assessing Patient Eligibility for Inspire Therapy through Machine Learning and Deep Learning Models](https://mlsanity.com/paper/2402.01067/) (2024)

## Abstract (arXiv)

Most classification models treat different object classes in parallel and the misclassifications between any two classes are treated equally. In contrast, human beings can exploit high-level information in making a prediction of an unknown object. Inspired by this observation, the paper proposes a super-class guided network (SGNet) to integrate the high-level semantic information into the network so as to increase its performance in inference. SGNet takes two-level class annotations that contain both super-class and finer class labels. The super-classes are higher-level semantic categories that consist of a certain amount of finer classes. A super-class branch (SCB), trained on super-class labels, is introduced to guide finer class prediction. At the inference time, we adopt two different strategies: Two-step inference (TSI) and direct inference (DI). TSI first predicts the super-class and then makes predictions of the corresponding finer class. On the other hand, DI directly generates predictions from the finer class branch (FCB). Extensive experiments have been performed on CIFAR-100 and MS COCO datasets. The experimental results validate the proposed approach and demonstrate its superior performance on image classification and object detection.