Eliminating Hallucination in Diffusion-Augmented Interactive Text-to-Image Retrieval

• URL: http://arxiv.org/abs/2601.20391v1
• Date: Wed, 28 Jan 2026 08:58:57 GMT
• Title: Eliminating Hallucination in Diffusion-Augmented Interactive Text-to-Image Retrieval
• Authors: Zhuocheng Zhang, Kangheng Liang, Guanxuan Li, Paul Henderson, Richard Mccreadie, Zijun Long,
• Abstract summary: Diffusion-Augmented Interactive Text-to-Image Retrieval (DAI-TIR) is a promising paradigm that improves retrieval performance by generating query images via diffusion models.<n>We propose Diffusion-aware Multi-view Contrastive Learning (DMCL), a hallucination-robust training framework that casts DAI-TIR as joint optimization over representations of query intent and the target image.
• Score: 11.644783748459787
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Diffusion-Augmented Interactive Text-to-Image Retrieval (DAI-TIR) is a promising paradigm that improves retrieval performance by generating query images via diffusion models and using them as additional ``views'' of the user's intent. However, these generative views can be incorrect because diffusion generation may introduce hallucinated visual cues that conflict with the original query text. Indeed, we empirically demonstrate that these hallucinated cues can substantially degrade DAI-TIR performance. To address this, we propose Diffusion-aware Multi-view Contrastive Learning (DMCL), a hallucination-robust training framework that casts DAI-TIR as joint optimization over representations of query intent and the target image. DMCL introduces semantic-consistency and diffusion-aware contrastive objectives to align textual and diffusion-generated query views while suppressing hallucinated query signals. This yields an encoder that acts as a semantic filter, effectively mapping hallucinated cues into a null space, improving robustness to spurious cues and better representing the user's intent. Attention visualization and geometric embedding-space analyses corroborate this filtering behavior. Across five standard benchmarks, DMCL delivers consistent improvements in multi-round Hits@10, reaching as high as 7.37\% over prior fine-tuned and zero-shot baselines, which indicates it is a general and robust training framework for DAI-TIR.

Related papers

• Guiding Diffusion-based Reconstruction with Contrastive Signals for Balanced Visual Representation [81.40978077888693]
  Contrastive Language-Image Pre-training (CLIP) has become a key bottleneck for downstream performance.<n>Recent solutions use diffusion models to enhance representations by conditioning image reconstruction on CLIP visual tokens.<n>We integrate contrastive signals into diffusion-based reconstruction to pursue more comprehensive visual representations.
  arXiv  Detail & Related papers  (2026-03-05T04:45:49Z)
• Seeing Through the Chain: Mitigate Hallucination in Multimodal Reasoning Models via CoT Compression and Contrastive Preference Optimization [78.94590726578014]
  multimodal reasoning models (MLRMs) remain prone to hallucinations, and effective solutions are still underexplored.<n>We propose C3PO, a training-based mitigation framework comprising textbfCompression and textbfPreference textbfOptimization.
  arXiv  Detail & Related papers  (2026-02-03T11:00:55Z)
• Generative Editing in the Joint Vision-Language Space for Zero-Shot Composed Image Retrieval [11.724675700368316]
  Composed Image Retrieval (CIR) enables fine-grained visual search by combining a reference image with a textual modification.<n>We propose Fusion-Diff, a novel generative editing framework with high effectiveness and data efficiency designed for multimodal alignment.
  arXiv  Detail & Related papers  (2025-12-01T13:04:55Z)
• CIR-CoT: Towards Interpretable Composed Image Retrieval via End-to-End Chain-of-Thought Reasoning [93.05917922306196]
  Composed Image Retrieval (CIR) aims to find a target image from a reference image and a modification text.<n>CIR-CoT is the first end-to-end retrieval-oriented MLLM designed to integrate explicit Chain-of-Thought (CoT) reasoning.
  arXiv  Detail & Related papers  (2025-10-09T09:41:45Z)
• Explaining multimodal LLMs via intra-modal token interactions [55.27436637894534]
  Multimodal Large Language Models (MLLMs) have achieved remarkable success across diverse vision-language tasks, yet their internal decision-making mechanisms remain insufficiently understood.<n>We propose enhancing interpretability by leveraging intra-modal interaction.
  arXiv  Detail & Related papers  (2025-09-26T14:39:13Z)
• Do You Keep an Eye on What I Ask? Mitigating Multimodal Hallucination via Attention-Guided Ensemble Decoding [5.71478837100808]
  Large Vision-Language Models (LVLMs) generate descriptions that inaccurately reflect the visual content by including nonexistent objects or misrepresenting existing ones.<n>We propose Ensemble Decoding (ED), a novel strategy that splits the input image into sub-images and combines logit distributions by assigning weights through the attention map.<n>Our proposed method achieves state-of-the-art performance, validating the effectiveness of our approach.
  arXiv  Detail & Related papers  (2025-05-23T06:35:43Z)
• Generalized Visual Relation Detection with Diffusion Models [94.62313788626128]
  Visual relation detection (VRD) aims to identify relationships (or interactions) between object pairs in an image.<n>We propose to model visual relations as continuous embeddings, and design diffusion models to achieve generalized VRD in a conditional generative manner.<n>Our Diff-VRD is able to generate visual relations beyond the pre-defined category labels of datasets.
  arXiv  Detail & Related papers  (2025-04-16T14:03:24Z)
• TMCIR: Token Merge Benefits Composed Image Retrieval [13.457620649082504]
  Composed Image Retrieval (CIR) retrieves target images using a multi-modal query that combines a reference image with text describing desired modifications.<n>Current cross-modal feature fusion approaches for CIR exhibit an inherent bias in intention interpretation.<n>We propose a novel framework that advances composed image retrieval through two key innovations.
  arXiv  Detail & Related papers  (2025-04-15T09:14:04Z)
• Bridging Generative and Discriminative Models for Unified Visual Perception with Diffusion Priors [56.82596340418697]
  We propose a simple yet effective framework comprising a pre-trained Stable Diffusion (SD) model containing rich generative priors, a unified head (U-head) capable of integrating hierarchical representations, and an adapted expert providing discriminative priors. Comprehensive investigations unveil potential characteristics of Vermouth, such as varying granularity of perception concealed in latent variables at distinct time steps and various U-net stages. The promising results demonstrate the potential of diffusion models as formidable learners, establishing their significance in furnishing informative and robust visual representations.
  arXiv  Detail & Related papers  (2024-01-29T10:36:57Z)
• DiffAugment: Diffusion based Long-Tailed Visual Relationship Recognition [43.01467525231004]
  We introduce DiffAugment -- a method which augments the tail classes in the linguistic space by making use of WordNet. We demonstrate the effectiveness of hardness-aware diffusion in generating visual embeddings for the tail classes. We also propose a novel subject and object based seeding strategy for diffusion sampling which improves the discriminative capability of the generated visual embeddings.
  arXiv  Detail & Related papers  (2024-01-01T21:20:43Z)
• Towards Generalizable Referring Image Segmentation via Target Prompt and Visual Coherence [48.659338080020746]
  Referring image segmentation (RIS) aims to segment objects in an image conditioning on free-from text descriptions. We present a novel RIS approach, which substantially improves the generalization ability by addressing the two dilemmas mentioned above. Specially, to deal with unconstrained texts, we propose to boost a given expression with an explicit and crucial prompt, which complements the expression in a unified context.
  arXiv  Detail & Related papers  (2023-12-01T09:31:24Z)
• Good Visual Guidance Makes A Better Extractor: Hierarchical Visual Prefix for Multimodal Entity and Relation Extraction [88.6585431949086]
  We propose a novel Hierarchical Visual Prefix fusion NeTwork (HVPNeT) for visual-enhanced entity and relation extraction. We regard visual representation as pluggable visual prefix to guide the textual representation for error insensitive forecasting decision. Experiments on three benchmark datasets demonstrate the effectiveness of our method, and achieve state-of-the-art performance.
  arXiv  Detail & Related papers  (2022-05-07T02:10:55Z)

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.