# INTENT: Invariance and Discrimination-aware Noise Mitigation for Robust Composed Image Retrieval

arXiv: https://arxiv.org/abs/2604.18051 · HTML: https://mlsanity.com/paper/2604.18051/

## Key facts

- Cited by 26 papers in the map (data through 14 Oct 2026).
- Builds on 53 of its 117 references that are in the map.
- First posted on arXiv 20 Apr 2026.

## Builds on (most cited first, 30 of 53)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Similarity of Neural Network Representations Revisited](https://mlsanity.com/paper/1905.00414/) (2019)
- [Noise2Self: Blind Denoising by Self-Supervision](https://mlsanity.com/paper/1901.11365/) (2019)
- [Counterfactual VQA: A Cause-Effect Look at Language Bias](https://mlsanity.com/paper/2006.04315/) (2020)
- [Image Retrieval on Real-life Images with Pre-trained Vision-and-Language Models](https://mlsanity.com/paper/2108.04024/) (2021)
- [TFB: Towards Comprehensive and Fair Benchmarking of Time Series Forecasting Methods](https://mlsanity.com/paper/2403.20150/) (2024)
- [Composing Text and Image for Image Retrieval - An Empirical Odyssey](https://mlsanity.com/paper/1812.07119/) (2018)
- [GigaWorld-Policy: An Efficient Action-Centered World--Action Model](https://mlsanity.com/paper/2603.17240/) (2026)
- [ReconDreamer: Crafting World Models for Driving Scene Reconstruction via Online Restoration](https://mlsanity.com/paper/2411.19548/) (2024)
- [Set You Straight: Auto-Steering Denoising Trajectories to Sidestep Unwanted Concepts](https://mlsanity.com/paper/2504.12782/) (2025)
- [PRISM: Self-Pruning Intrinsic Selection Method for Training-Free Multimodal Data Selection](https://mlsanity.com/paper/2502.12119/) (2025)
- [Noisy-Correspondence Learning for Text-to-Image Person Re-identification](https://mlsanity.com/paper/2308.09911/) (2023)
- [Co-learning: Learning from Noisy Labels with Self-supervision](https://mlsanity.com/paper/2108.04063/) (2021)
- [LLaVA Steering: Visual Instruction Tuning with 500x Fewer Parameters through Modality Linear Representation-Steering](https://mlsanity.com/paper/2412.12359/) (2024)
- [CoT-Kinetics: A Theoretical Modeling Assessing LRM Reasoning Process](https://mlsanity.com/paper/2505.13408/) (2025)
- [Compact Transformer Tracker with Correlative Masked Modeling](https://mlsanity.com/paper/2301.10938/) (2023)
- [Composed Image Retrieval with Text Feedback via Multi-grained Uncertainty Regularization](https://mlsanity.com/paper/2211.07394/) (2022)
- [FastPillars: A Deployment-friendly Pillar-based 3D Detector](https://mlsanity.com/paper/2302.02367/) (2023)
- [ASCD: Attention-Steerable Contrastive Decoding for Reducing Hallucination in MLLM](https://mlsanity.com/paper/2506.14766/) (2025)
- [BALF: Simple and Efficient Blur Aware Local Feature Detector](https://mlsanity.com/paper/2211.14731/) (2022)
- [Chat-Driven Text Generation and Interaction for Person Retrieval](https://mlsanity.com/paper/2509.12662/) (2025)
- [WonderTurbo: Generating Interactive 3D World in 0.72 Seconds](https://mlsanity.com/paper/2504.02261/) (2025)
- [Does FLUX Already Know How to Perform Physically Plausible Image Composition?](https://mlsanity.com/paper/2509.21278/) (2025)
- [Visual Document Understanding and Reasoning: A Multi-Agent Collaboration Framework with Agent-Wise Adaptive Test-Time Scaling](https://mlsanity.com/paper/2508.03404/) (2025)
- [DragFlow: Unleashing DiT Priors with Region Based Supervision for Drag Editing](https://mlsanity.com/paper/2510.02253/) (2025)
- [ReconDreamer-RL: Enhancing Reinforcement Learning via Diffusion-based Scene Reconstruction](https://mlsanity.com/paper/2508.08170/) (2025)
- [Noisy Correspondence Learning with Meta Similarity Correction](https://mlsanity.com/paper/2304.06275/) (2023)
- [DVLO: Deep Visual-LiDAR Odometry with Local-to-Global Feature Fusion and Bi-Directional Structure Alignment](https://mlsanity.com/paper/2403.18274/) (2024)
- [STABLE: Efficient Hybrid Nearest Neighbor Search via Magnitude-Uniformity and Cardinality-Robustness](https://mlsanity.com/paper/2604.01617/) (2026)
- [SF2T: Self-supervised Fragment Finetuning of Video-LLMs for Fine-Grained Understanding](https://mlsanity.com/paper/2504.07745/) (2025)

## Built on by (most cited first, 26 of 26)

- [Air-Know: Arbiter-Calibrated Knowledge-Internalizing Robust Network for Composed Image Retrieval](https://mlsanity.com/paper/2604.19386/) (2026)
- [ConeSep: Cone-based Robust Noise-Unlearning Compositional Network for Composed Image Retrieval](https://mlsanity.com/paper/2604.20358/) (2026)
- [COMBINER: Composed Image Retrieval Guided by Attribute-based Neighbor Relations](https://mlsanity.com/paper/2606.04604/) (2026)
- [EgoAction: Egocentric Action Composition with Reliability-Aware Temporal Fusion for the EPIC-KITCHENS Action Detection Challenge at CVPR 2026](https://mlsanity.com/paper/2605.24496/) (2026)
- [EgoAdapt: A Multi-Scene Egocentric Adaptation Method for CVPR 2026 HD-EPIC VQA Challenge](https://mlsanity.com/paper/2605.24500/) (2026)
- [Rethinking Layer-Wise Information Allocation for Vision Foundation Model Adaptation](https://mlsanity.com/paper/2607.21973/) (2026)
- [NativeMEM: Native Memory Compression for Long-Horizon Robotic Manipulation](https://mlsanity.com/paper/2607.06678/) (2026)
- [Seeing Further and Wider: Joint Spatio-Temporal Enlargement for Micro-Video Popularity Prediction](https://mlsanity.com/paper/2604.20311/) (2026)
- [TempRet: Temporal Enhancement and Two-Stage Reranking for CVPR 2026 EPIC-KITCHENS-100 Multi-Instance Retrieval Challenge](https://mlsanity.com/paper/2605.24470/) (2026)
- [OmniEgo-R2: A Routed Reasoning Framework for the 1st Cross-Domain EgoCross Challenge at CVPR 2026](https://mlsanity.com/paper/2605.24481/) (2026)
- [R^3: Composed Video Retrieval via Reasoning-Guided Recalling and Re-ranking](https://mlsanity.com/paper/2606.01113/) (2026)
- [HotComment: A Benchmark for Evaluating Popularity of Online Comments](https://mlsanity.com/paper/2604.25614/) (2026)
- [CurEvo: Curriculum-Guided Self-Evolution for Video Understanding](https://mlsanity.com/paper/2604.26707/) (2026)
- [OmniTrend: Content-Context Modeling for Scalable Social Popularity Prediction](https://mlsanity.com/paper/2604.26252/) (2026)
- [L-Drive: Beyond a Single Mapping-Latent Context Drives Time Series Forecasting](https://mlsanity.com/paper/2605.17730/) (2026)
- [IMAGINE: Adaptive Schema-Imagery Enhanced Composition for Composed Video Retrieval](https://mlsanity.com/paper/2606.08144/) (2026)
- [GateMOT: Q-Gated Attention for Dense Object Tracking](https://mlsanity.com/paper/2604.26353/) (2026)
- [Chain of Evidence: Pixel-Level Visual Attribution for Iterative Retrieval-Augmented Generation](https://mlsanity.com/paper/2605.01284/) (2026)
- [Grounding Multi-Hop Reasoning in Structural Causal Models via Group Relative Policy Optimization](https://mlsanity.com/paper/2605.01482/) (2026)
- [PESD-TSF: A Period-Aware and Explicit Structured Decomposition Framework for Long-Term Time Series Forecasting](https://mlsanity.com/paper/2605.16449/) (2026)
- [MHMamba: Multi-Head Mamba for 3D Brain Tumor Segmentation](https://mlsanity.com/paper/2605.16464/) (2026)
- [On the Controllability-Fidelity Frontier in Diffusion Editing](https://mlsanity.com/paper/2606.09901/) (2026)
- [RankVR: Low-Rank Structure Perception and Value Recalibration for Robust Composed Image Retrieval](https://mlsanity.com/paper/2606.11689/) (2026)
- [VigilFormer: Deformable Attention for Video Anomaly Detection with Causal Risk Inference](https://mlsanity.com/paper/2606.14724/) (2026)
- [URDF Synthesis from RGB-D Sequences via Differentiable Joint Inference and Energy-Consistent Verification](https://mlsanity.com/paper/2606.18861/) (2026)
- [DGNet: Dual-knowledge Guided Network for Infrared Small Target Detection](https://mlsanity.com/paper/2609.00666/) (2026)

## Abstract (arXiv)

Composed Image Retrieval (CIR) is a challenging image retrieval paradigm that enables to retrieve target images based on multimodal queries consisting of reference images and modification texts. Although substantial progress has been made in recent years, existing methods assume that all samples are correctly matched. However, in real-world scenarios, due to high triplet annotation costs, CIR datasets inevitably contain annotation errors, resulting in incorrectly matched triplets. To address this issue, the problem of Noisy Triplet Correspondence (NTC) has attracted growing attention. We argue that noise in CIR can be categorized into two types: cross-modal correspondence noise and modality-inherent noise. The former arises from mismatches across modalities, whereas the latter originates from intra-modal background interference or visual factors irrelevant to the coarse-grained modification annotations. However, modality-inherent noise is often overlooked, and research on cross-modal correspondence noise remains nascent. To tackle above issues, we propose the Invariance and discrimiNaTion-awarE Noise neTwork (INTENT), comprising two components: Visual Invariant Composition and Bi-Objective Discriminative Learning, specifically designed to handle the two-aspect noise. The former applies causal intervention on the visual side via Fast Fourier Transform (FFT) to generate intervened composed features, enforcing visual invariance and enabling the model to ignore modality-inherent noise during composition. The latter adopts collaborative optimization with both positive and negative samples, and constructs a scalable decision boundary that dynamically adjusts decisions based on the loyalty degree, enabling robust correspondence discrimination. Extensive experiments on two widely used benchmark datasets demonstrate the superiority and robustness of INTENT.