Absence is Presence: Understanding Visual Scene Negative Events Under Safety Cognitive Constraint

2026-09-17

AI Summary

研究解决了安全关键领域中理解图像中缺失信息的问题，通过提出基于反事实重构和对比解码的框架来推断应存在但实际不存在的关键信息。

Abstract

Traditional scene understanding focuses on affirmative information objectively present in images. However, in safety-critical domains, comprehending key information that should exist but is actually absent is vital for risk mitigation. To bridge this gap, we focus on visual scene negative captioning with safety as the cognitive constraint. The core challenge is to convert physical absence into semantic negative events. Existing vision-language models (VLMs) struggle with this process because affirmation bias suppresses negative reasoning, while limited mental filling capability and representation bias further hinder the inference of absent information. To address these challenges, we propose a negative captioning framework based on counterfactual reconstruction and contrastive decoding (CRCD). Inspired by human cognition, CRCD reformulates the task as counterfactual latent change captioning to bypass affirmation bias. It contrasts a synthesized safe expectation with reality to identify semantic omissions. To address limited mental filling, we design a dual-branch counterfactual reconstruction architecture. The amodal completion branch restores defective objects, while the functional association branch infers completely absent safety objects. Concurrently, a multi-condition representation learning mechanism is integrated to mitigate representation bias by projecting universal features onto predefined safety criteria subspaces, thereby capturing information across more dimensions. By decoding feature-level semantic residuals between the reconstructed scene prototype and raw input, CRCD bounds the non-existence search space and activates the decoder's negative logic. Extensive experiments validate the effectiveness of CRCD, establishing a high-performance baseline for this pioneering task.

Problem

• visual scene negative events
• safety cognitive constraint
• affirmation bias
• mental filling capability
• representation bias

Innovation

• counterfactual reconstruction and contrastive decoding (CRCD)
• safety cognitive constraint
• visual scene negative captioning
• representation bias
• multi-condition representation learning