# Biasing Like Human: A Cognitive Bias Framework for Scene Graph Generation Source: [Biasing Like Human: A Cognitive Bias Framework for Scene Graph Generation]() Collection index: [llms.txt]() Data updated: 2026-01-04T03:38:06.509Z Authors: Xiaoguang Chang, Teng Wang, Changyin Sun, Wenzhe Cai Published: 2022-03-17T08:29:52.000Z ## Abstract Scene graph generation is a sophisticated task because there is no specific recognition pattern (e.g., "looking at" and "near" have no conspicuous difference concerning vision, whereas "near" could occur between entities with different morphology). Thus some scene graph generation methods are trapped into most frequent relation predictions caused by capricious visual features and trivial dataset annotations. Therefore, recent works emphasized the "unbiased" approaches to balance predictions for a more informative scene graph. However, human's quick and accurate judgments over relations between numerous objects should be attributed to "bias" (i.e., experience and linguistic knowledge) rather than pure vision. To enhance the model capability, inspired by the "cognitive bias" mechanism, we propose a novel 3-paradigms framework that simulates how humans incorporate the label linguistic features as guidance of vision-based representations to better mine hidden relation patterns and alleviate noisy visual propagation. Our framework is model-agnostic to any scene graph model. Comprehensive experiments prove our framework outperforms baseline modules in several metrics with minimum parameters increment and achieves new SOTA performance on Visual Genome dataset. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Scene Graph Classification on VG150 (test)](): Scene Graph Classification; VG150 (test); mR@50: 28.01. - [Predicate Classification on VG (test)](): Predicate Classification; VG (test); mR@100: 63.02. - [Scene Graph Generation on VG (test)](): Scene Graph Generation; VG (test); mR@50: 17.07. ## Original sources and implementation [Original paper]() [PDF]()