Shedding the Facades, Connecting the Domains: Detecting Shifting Multimodal Hate Video with Test-Time Adaptation

TL;DR

This paper introduces SCANNER, a novel test-time adaptation framework for hate video detection that leverages invariant core features to improve robustness against evolving hateful content.

Contribution

SCANNER is the first TTA framework specifically designed for hate video detection, utilizing stable core features and adaptive alignment to handle semantic drift.

Findings

SCANNER achieves an average 4.69% gain in Macro-F1 over baselines.

It effectively connects source and target domains despite content evolution.

The method enhances detection robustness against semantic drift.

Abstract

Hate Video Detection (HVD) is crucial for online ecosystems. Existing methods assume identical distributions between training (source) and inference (target) data. However, hateful content often evolves into irregular and ambiguous forms to evade censorship, resulting in substantial semantic drift and rendering previously trained models ineffective. Test-Time Adaptation (TTA) offers a solution by adapting models during inference to narrow the cross-domain gap, while conventional TTA methods target mild distribution shifts and struggle with the severe semantic drift in HVD. To tackle these challenges, we propose SCANNER, the first TTA framework tailored for HVD. Motivated by the insight that, despite the evolving nature of hateful manifestations, their underlying cores remain largely invariant (i.e., targeting is still based on characteristics like gender, race, etc), we leverage these stable cores as a bridge to connect the source and target domains. Specifically, SCANNER initially reveals the stable cores from the ambiguous layout in evolving hateful content via a principled centroid-guided alignment mechanism. To alleviate the impact of outlier-like samples that are weakly correlated with centroids during the alignment process, SCANNER enhances the prior by incorporating a sample-level adaptive centroid alignment strategy, promoting more stable adaptation. Furthermore, to mitigate semantic collapse from overly uniform outputs within clusters, SCANNER introduces an intra-cluster diversity regularization that encourages the cluster-wise semantic richness. Experiments show that SCANNER outperforms all baselines, with an average gain of 4.69% in Macro-F1 over the best.