Adaptive Self-training Framework for Fine-grained Scene Graph Generation

TL;DR

This paper introduces a novel self-training framework with adaptive pseudo-labeling and graph learning to improve fine-grained scene graph generation, addressing long-tailed predicate distribution and annotation issues.

Contribution

It proposes a model-agnostic self-training framework with a new pseudo-labeling technique and graph structure learner for better scene graph generation.

Findings

Enhanced predicate classification performance.

Effective handling of long-tailed predicate distribution.

Improved results on various SGG models.

Abstract

Scene graph generation (SGG) models have suffered from inherent problems regarding the benchmark datasets such as the long-tailed predicate distribution and missing annotation problems. In this work, we aim to alleviate the long-tailed problem of SGG by utilizing unannotated triplets. To this end, we introduce a Self-Training framework for SGG (ST-SGG) that assigns pseudo-labels for unannotated triplets based on which the SGG models are trained. While there has been significant progress in self-training for image recognition, designing a self-training framework for the SGG task is more challenging due to its inherent nature such as the semantic ambiguity and the long-tailed distribution of predicate classes. Hence, we propose a novel pseudo-labeling technique for SGG, called Class-specific Adaptive Thresholding with Momentum (CATM), which is a model-agnostic framework that can be applied to any existing SGG models. Furthermore, we devise a graph structure learner (GSL) that is beneficial when adopting our proposed self-training framework to the state-of-the-art message-passing neural network (MPNN)-based SGG models. Our extensive experiments verify the effectiveness of ST-SGG on various SGG models, particularly in enhancing the performance on fine-grained predicate classes.