Interpreting Object-Dependent Concept Brittleness in Text-to-Image Diffusion Models

• URL: http://arxiv.org/abs/2609.09909v1
• Date: Wed, 09 Sep 2026 09:07:40 GMT
• Title: Interpreting Object-Dependent Concept Brittleness in Text-to-Image Diffusion Models
• Abstract summary: We term this phenomenon object-dependent concept brittleness.<n>We present an interpretability-oriented framework to audit and minimally correct these failures.<n>We evaluate the proposed framework on style and attribute failure cases across multiple diffusion backbones.
• Score: 105.53190946111586
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Although text-to-image diffusion models generally exhibit strong prompt-following ability, we identify a persistent and previously underexplored failure pattern in which a small subset of prompts differing only in the object consistently fails to realize the same target concept under identical generation settings. We term this phenomenon object-dependent concept brittleness. Such cases suggest systematic internal blind spots rather than random sampling noise. In this paper, we present an interpretability-oriented framework to audit and minimally correct these failures. Our key idea is to analyze denoising trajectories in a step-wise sparse autoencoder (SAE) space, where abstract style and attribute concepts become more separable than in the raw denoising representation. This sparse space enables us to compare successful and failed generations, identify concept dimensions whose evidence is missing, weakened, or temporally delayed, and construct class-level concept prototypes from reliable class-consistent samples. Based on this audit process, we introduce a lightweight inference-time correction strategy that interpolates denoising features toward the corresponding prototype in SAE space. Rather than serving as a task-specific retraining method, this intervention acts as a validation of the diagnosed concept deficiency. We evaluate the proposed framework on style and attribute failure cases across multiple diffusion backbones, with significant improvements in concept consistency, text fidelity, and repair success. Further analyses show that deeper denoising representations provide clearer concept structure, while early-stage intervention offers the strongest correction leverage. Code is available at https://github.com/Metecade/Object-Dependent-Concept-Brittleness.

Related papers

• Revisiting Lossy Verification in Speculative Decoding: Mechanisms, Trade-offs, and Failure Modes [19.68865985432786]
  We present a principled analysis of the distributions induced by lossy verification methods.<n>We show that many seemingly distinct approaches differ only superficially and can be classified into two categories: truncation-based verification and collaborative verification.
  arXiv  Detail & Related papers  (2026-07-29T08:54:27Z)
• DriftScope: Measuring The Hidden Effects of Diffusion Model Adaptation [50.584834483403675]
  Adapting pre-trained text-to-image diffusion models, whether to learn new visual concepts or erase unwanted ones, is routinely evaluated on its intended effects alone.<n>We demonstrate that adaptation systematically damages semantically unrelated concepts in ways that aggregate metrics structurally cannot surface.<n>We introduce DriftScope, a prompt-level diagnostic tool that takes any two model checkpoints and returns a ranked list of tokens whose visual concepts have shifted most between them.
  arXiv  Detail & Related papers  (2026-06-30T20:57:51Z)
• Hierarchical Consistency Learning for Test-time Adaptation in Camouflage Perception [50.278200968044665]
  Camouflaged object detection (COD) aims to localize targets that exhibit minimal perceptual differences from backgrounds through physical attributes.<n>Existing methods, constrained by the static train-then-freeze paradigm, suffer from domain rigidity and dependency annotation.<n>We propose the hierarchical consistency learning framework, which integrates test-time adaptation for dynamic representation recalibration.
  arXiv  Detail & Related papers  (2026-05-25T09:57:46Z)
• Beyond Heuristic Prompting: A Concept-Guided Bayesian Framework for Zero-Shot Image Recognition [81.2779530670268]
  Vision-Language Models (VLMs) have significantly advanced zero-shot image recognition.<n>This paper enhances prompt by incorporating class-specific concepts.<n>Our method consistently outperforms state-of-the-art approaches.
  arXiv  Detail & Related papers  (2026-03-09T03:11:11Z)
• Diversity over Uniformity: Rethinking Representation in Generated Image Detection [22.020742109848317]
  We argue that reliably generated image detection should not depend on a single decision path but should preserve multiple judgment perspectives.<n>We propose an anti-feature-collapse learning framework that filters task-irrelevant components and suppresses excessive overlap among different forgery cues in the representation space.<n>This design maintains diverse and complementary evidence within the model, reduces reliance on a small set of salient cues, and enhances robustness under unseen generative settings.
  arXiv  Detail & Related papers  (2026-02-28T15:42:12Z)
• Temporal Concept Dynamics in Diffusion Models via Prompt-Conditioned Interventions [70.87254264798341]
  PCI is a training-free and model-agnostic framework for analyzing concept dynamics through diffusion time.<n>It reveals diverse temporal behaviors across diffusion models, in which certain phases of the trajectory are more favorable to specific concepts even within the same concept type.
  arXiv  Detail & Related papers  (2025-12-09T11:05:08Z)
• Representation-Level Counterfactual Calibration for Debiased Zero-Shot Recognition [36.36218470387896]
  We recast this issue as a causal inference problem and ask: Would the prediction remain if the object appeared in a different environment?<n>To answer this at inference time, we estimate object and background expectations within CLIP's representation space, and synthesize counterfactual embeddings.<n>Without retraining or prompt design, our method substantially improves both worst-group and average accuracy on context-sensitive benchmarks.
  arXiv  Detail & Related papers  (2025-10-30T13:11:23Z)
• Semantic Discrepancy-aware Detector for Image Forgery Identification [21.695863229449742]
  The misalignment between the forgery and semantic concept spaces hinders the model's forgery detection performance.<n>We propose a novel Semantic Discrepancy-aware Detector (SDD) that leverages reconstruction learning to align the two spaces at a fine-grained visual level.<n>A concept-level forgery discrepancy learning module, built upon a visual reconstruction paradigm, is proposed to strengthen the interaction between visual semantic concepts and forgery traces.
  arXiv  Detail & Related papers  (2025-08-17T12:11:09Z)
• "Principal Components" Enable A New Language of Images [79.45806370905775]
  We introduce a novel visual tokenization framework that embeds a provable PCA-like structure into the latent token space.<n>Our approach achieves state-of-the-art reconstruction performance and enables better interpretability to align with the human vision system.
  arXiv  Detail & Related papers  (2025-03-11T17:59:41Z)
• ConsistencyDet: A Few-step Denoising Framework for Object Detection Using the Consistency Model [22.34776007498307]
  We introduce a novel framework designed to articulate object detection as a denoising diffusion process.<n>The framework, termed textbfConsistencyDet, leverages an innovative denoising concept known as the Consistency Model.
  arXiv  Detail & Related papers  (2024-04-11T14:08:45Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.