Unbiased Scene Graph Generation

9 papers with code • 1 benchmarks • 1 datasets

Unbiased Scene Graph Generation (Unbiased SGG) aims to predict more informative scene graphs composed of more "tail predicates" *(in contrast to "head predicates" in terms of class frequencies) by dealing with the skewed, long-tailed predicate class distribution. (Definition from Chiou et al. "Recovering the Unbiased Scene Graphs from the Biased Ones")

Most implemented papers

Unbiased Scene Graph Generation from Biased Training

KaihuaTang/Scene-Graph-Benchmark.pytorch CVPR 2020

Today's scene graph generation (SGG) task is still far from practical, mainly due to the severe training bias, e. g., collapsing diverse "human walk on / sit on / lay on beach" into "human on beach".

Bipartite Graph Network with Adaptive Message Passing for Unbiased Scene Graph Generation

Scarecrow0/BGNN-SGG CVPR 2021

Scene graph generation is an important visual understanding task with a broad range of vision applications.

PCPL: Predicate-Correlation Perception Learning for Unbiased Scene Graph Generation

coldmanck/recovering-unbiased-scene-graphs 2 Sep 2020

Today, scene graph generation(SGG) task is largely limited in realistic scenarios, mainly due to the extremely long-tailed bias of predicate annotation distribution.

CogTree: Cognition Tree Loss for Unbiased Scene Graph Generation

CYVincent/Scene-Graph-Transformer-CogTree 16 Sep 2020

We first build a cognitive structure CogTree to organize the relationships based on the prediction of a biased SGG model.

Recovering the Unbiased Scene Graphs from the Biased Ones

coldmanck/recovering-unbiased-scene-graphs 5 Jul 2021

Given input images, scene graph generation (SGG) aims to produce comprehensive, graphical representations describing visual relationships among salient objects.

Resistance Training using Prior Bias: toward Unbiased Scene Graph Generation

chch1999/rtpb 18 Jan 2022

To address this problem, we propose Resistance Training using Prior Bias (RTPB) for the scene graph generation.

Stacked Hybrid-Attention and Group Collaborative Learning for Unbiased Scene Graph Generation

dongxingning/sha-gcl-for-sgg CVPR 2022

Scene Graph Generation, which generally follows a regular encoder-decoder pipeline, aims to first encode the visual contents within the given image and then parse them into a compact summary graph.

Fine-Grained Scene Graph Generation with Data Transfer

waxnkw/ietrans-sgg.pytorch 22 Mar 2022

Scene graph generation (SGG) is designed to extract (subject, predicate, object) triplets in images.

Dual-branch Hybrid Learning Network for Unbiased Scene Graph Generation

aa200647963/sgg-dhl 16 Jul 2022

Experiments show that our approach achieves a new state-of-the-art performance on VG and GQA datasets and makes a trade-off between the performance of tail predicates and head ones.