mlsanityData to 14 Oct 2026

Size-invariance Matters: Rethinking Metrics and Losses for Imbalanced Multi-object Salient Object Detection

arXiv 2405.09782 ↗First posted 16 May 2024cs.CVcited by 14

Not on the map. Why?

Abstract (arXiv)

This paper explores the size-invariance of evaluation metrics in Salient Object Detection (SOD), especially when multiple targets of diverse sizes co-exist in the same image. We observe that current metrics are size-sensitive, where larger objects are focused, and smaller ones tend to be ignored. We argue that the evaluation should be size-invariant because bias based on size is unjustified without additional semantic information. In pursuit of this, we propose a generic approach that evaluates each salient object separately and then combines the results, effectively alleviating the imbalance. We further develop an optimization framework tailored to this goal, achieving considerable improvements in detecting objects of different sizes. Theoretically, we provide evidence supporting the validity of our new metrics and present the generalization analysis of SOD. Extensive experiments demonstrate the effectiveness of our method. The code is available at https://github.com/Ferry-Li/SI-SOD.

Key facts. Cited by 14 papers in the map (data through 14 Oct 2026). Builds on 32 of its 73 references that are in the map. First posted on arXiv 16 May 2024.

Builds on

32 of 73 references.

References · 32

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  3. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,639
  4. 2015You Only Look Once: Unified, Real-Time Object Detectioncited by 4,852
  5. 2016V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentationcited by 2,292
  6. 2013Rich feature hierarchies for accurate object detection and semantic segmentationcited by 2,162
  7. 2018Enhanced-alignment Measure for Binary Foreground Map Evaluationcited by 370
  8. 2020Causal Intervention for Weakly-Supervised Semantic Segmentationcited by 229
  9. 2019A Simple Pooling-Based Design for Real-Time Salient Object Detectioncited by 212
  10. 2016UnitBox: An Advanced Object Detection Networkcited by 205
  11. 2021Object Detection in Aerial Images: A Large-Scale Benchmark and Challengescited by 204
  12. 2015Visual Saliency Based on Multiscale Deep Featurescited by 185
20 more
  1. 2016What do different evaluation metrics tell us about saliency models?cited by 185
  2. 2019Salient Object Detection in the Deep Learning Era: An In-Depth Surveycited by 164
  3. 2016A vector-contraction inequality for Rademacher complexitiescited by 142
  4. 2020Few-Shot Object Detection and Viewpoint Estimation for Objects in the Wildcited by 142
  5. 2021Salient Object Detection via Integrity Learningcited by 133
  6. 2020Label Decoupling Framework for Salient Object Detectioncited by 111
  7. 2014Salient Object Detection: A Surveycited by 98
  8. 2017Amulet: Aggregating Multi-level Convolutional Features for Salient Object Detectioncited by 93
  9. 2020EDN: Salient Object Detection via Extremely-Downsampled Networkcited by 64
  10. 2021Learning Generative Vision Transformer with Energy-Based Latent Space for Saliency Predictioncited by 57
  11. 2016Deep Contrast Learning for Salient Object Detectioncited by 52
  12. 2020Accurate RGB-D Salient Object Detection via Collaborative Learningcited by 52
  13. 2017Learning Uncertain Convolutional Features for Accurate Saliency Detectioncited by 44
  14. 2020A General Framework for Consistent Structured Prediction with Implicit Loss Embeddingscited by 35
  15. 2018PiCANet: Pixel-wise Contextual Attention Learning for Accurate Saliency Detectioncited by 28
  16. 2020Regularized Densely-connected Pyramid Network for Salient Instance Segmentationcited by 18
  17. 2022Optimizing Two-way Partial AUC with an End-to-end Frameworkcited by 15
  18. 2019CNN-based RGB-D Salient Object Detection: Learn, Select and Fusecited by 9
  19. 2019Richer and Deeper Supervision Network for Salient Object Detectioncited by 4
  20. 2021Addressing Multiple Salient Object Detection via Dual-Space Long-Range Dependenciescited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 2; 2025: 7; 2026: 5.

14 papers.

Sort:

By area:

  1. 2024AUCSeg: AUC-oriented Pixel-level Long-tail Semantic Segmentationcited by 18
  2. 2025One Image is Worth a Thousand Words: A Usability Preservable Text-Image Collaborative Erasing Frameworkcited by 16
  3. 2025Balancing the Scales: A Theoretical and Algorithmic Framework for Learning from Imbalanced Datacited by 15
  4. 2025Improved Balanced Classification with Theoretically Grounded Loss Functionscited by 9
  5. 2025Adaptive Event Stream Slicing for Open-Vocabulary Event-Based Object Detection via Vision-Language Knowledge Distillationcited by 8
  6. 2024Rethinking Detecting Salient and Camouflaged Objects in Unconstrained Scenescited by 7
  7. 2025Dual-Stage Reweighted MoE for Long-Tailed Egocentric Mistake Detectioncited by 3
  8. 2026From Static to Dynamic: Exploring Self-supervised Image-to-Video Representation Transfer Learningcited by 2
  9. 2026Optimized Deferral for Imbalanced Settingscited by 2
  10. 2025Divide, Weight, and Route: Difficulty-Aware Optimization with Dynamic Expert Fusion for Long-tailed Recognitioncited by 1
  11. 2026Deconstructing the Failure of Ideal Noise Correction: A Three-Pillar Diagnosiscited by 1
  12. 2026Beyond Pixel Overlap: A Framework for Decomposing Segmentation Evaluation Metricscited by 1
2 more
  1. 2025Towards Size-invariant Salient Object Detection: A Generic Evaluation and Optimization Approachcited by 0
  2. 2026Rethinking Conditional Generation for Underwater Salient Object Detectioncited by 0