mlsanityData to 7 Oct 2026

Logical Bias Learning for Object Relation Prediction

arXiv 2310.00712 ↗First posted 1 Oct 2023cs.CV cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Scene graph generation (SGG) aims to automatically map an image into a semantic structural graph for better scene understanding. It has attracted significant attention for its ability to provide object and relation information, enabling graph reasoning for downstream tasks. However, it faces severe limitations in practice due to the biased data and training method. In this paper, we present a more rational and effective strategy based on causal inference for object relation prediction. To further evaluate the superiority of our strategy, we propose an object enhancement module to conduct ablation studies. Experimental results on the Visual Gnome 150 (VG-150) dataset demonstrate the effectiveness of our proposed method. These contributions can provide great potential for foundation models for decision-making.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 23 of its 32 references that are in the map. First posted on arXiv 1 Oct 2023.

Builds on

23 of 32 references.

References · 23

  1. 2017Attention Is All You Needcited by 59,932
  2. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
  3. 2016Layer Normalizationcited by 5,579
  4. 2016Aggregated Residual Transformations for Deep Neural Networkscited by 2,540
  5. 2017Deformable Convolutional Networkscited by 1,481
  6. 2018ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustnesscited by 1,430
  7. 2017Scene Graph Generation by Iterative Message Passingcited by 462
  8. 2017Neural Motifs: Scene Graph Parsing with Global Contextcited by 413
  9. 2020Unbiased Scene Graph Generation from Biased Trainingcited by 355
  10. 2018Learning to Compose Dynamic Tree Structures for Visual Contextscited by 258
  11. 2018Auto-Encoding Scene Graphs for Image Captioningcited by 254
  12. 2021ViTAE: Vision Transformer Advanced by Exploring Intrinsic Inductive Biascited by 216
11 more
  1. 2019Knowledge-Embedded Routing Network for Scene Graph Generationcited by 163
  2. 2021Bipartite Graph Network with Adaptive Message Passing for Unbiased Scene Graph Generationcited by 137
  3. 2022Panoptic Scene Graph Generationcited by 114
  4. 2020Bridging Knowledge Graphs to Generate Scene Graphscited by 86
  5. 2020PCPL: Predicate-Correlation Perception Learning for Unbiased Scene Graph Generationcited by 75
  6. 2021On the Integration of Self-Attention and Convolutioncited by 74
  7. 2022Stacked Hybrid-Attention and Group Collaborative Learning for Unbiased Scene Graph Generationcited by 67
  8. 2022Fine-Grained Scene Graph Generation with Data Transfercited by 57
  9. 2018Zoom-Net: Mining Deep Feature Interactions for Visual Relationship Recognitioncited by 41
  10. 2021In Defense of Scene Graphs for Image Captioningcited by 31
  11. 2022RU-Net: Regularized Unrolling Network for Scene Graph Generationcited by 28

Built on by

Not cited yet.