ConeSep: Cone-based Robust Noise-Unlearning Compositional Network for Composed Image Retrieval

• URL: http://arxiv.org/abs/2604.20358v1
• Date: Wed, 22 Apr 2026 08:59:21 GMT
• Title: ConeSep: Cone-based Robust Noise-Unlearning Compositional Network for Composed Image Retrieval
• Abstract summary: This paper systematically investigates the Noisy Triplet Correspondence (NTC) problem introduced by annotations.<n>We propose a Cone-based robuSt noisE-unlearning comPositional network (ConeSep) to address these challenges.
• Score: 60.051600134831226
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The Composed Image Retrieval (CIR) task provides a flexible retrieval paradigm via a reference image and modification text, but it heavily relies on expensive and error-prone triplet annotations. This paper systematically investigates the Noisy Triplet Correspondence (NTC) problem introduced by annotations. We find that NTC noise, particularly ``hard noise'' (i.e., the reference and target images are highly similar but the modification text is incorrect), poses a unique challenge to existing Noise Correspondence Learning (NCL) methods because it breaks the traditional ``small loss hypothesis''. We identify and elucidate three key, yet overlooked, challenges in the NTC task, namely (C1) Modality Suppression, (C2) Negative Anchor Deficiency, and (C3) Unlearning Backlash. To address these challenges, we propose a Cone-based robuSt noisE-unlearning comPositional network (ConeSep). Specifically, we first propose Geometric Fidelity Quantization, theoretically establishing and practically estimating a noise boundary to precisely locate noisy correspondence. Next, we introduce Negative Boundary Learning, which learns a ``diagonal negative combination'' for each query as its explicit semantic opposite-anchor in the embedding space. Finally, we design Boundary-based Targeted Unlearning, which models the noisy correction process as an optimal transport problem, elegantly avoiding Unlearning Backlash. Extensive experiments on benchmark datasets (FashionIQ and CIRR) demonstrate that ConeSep significantly outperforms current state-of-the-art methods, which fully demonstrates the effectiveness and robustness of our method.

Related papers

• INTENT: Invariance and Discrimination-aware Noise Mitigation for Robust Composed Image Retrieval [33.738463561724444]
  We argue that noise in Composed Image Retrieval (CIR) can be categorized into two types: cross-modal correspondence noise and modality-inherent noise.<n>The latter arises from mismatches across modalities, whereas the latter originates from intra-modal background interference or visual factors irrelevant to the coarse-grained modification annotations.<n>We propose the Invariance and discrimiNaTion-awarE Noise neTwork (INTENT) to handle the two-aspect noise.
  arXiv  Detail & Related papers  (2026-04-20T10:19:07Z)
• HABIT: Chrono-Synergia Robust Progressive Learning Framework for Composed Image Retrieval [32.85064790572752]
  Composed Image Retrieval (CIR) is a flexible image retrieval paradigm that enables users to accurately locate the target image.<n>This paper proposes a cHrono-synergiA roBust progressIve learning framework for composed image reTrieval (HABIT)<n>Experiments conducted on two standard CIR datasets demonstrate that HABIT significantly outperforms most methods under various noise ratios.
  arXiv  Detail & Related papers  (2026-04-20T10:02:18Z)
• Robust Remote Sensing Image-Text Retrieval with Noisy Correspondence [24.863417464867776]
  We propose a novel Robust Remote Sensing Image-Text Retrieval (RRSITR) paradigm that designs a self-paced learning strategy to mimic human cognitive learning patterns.<n>Experiments on three popular benchmark datasets demonstrate that the proposed RRSITR significantly outperforms the state-of-the-art methods.
  arXiv  Detail & Related papers  (2026-03-30T07:55:07Z)
• Noisy Correspondence Learning with Self-Reinforcing Errors Mitigation [63.180725016463974]
  Cross-modal retrieval relies on well-matched large-scale datasets that are laborious in practice. We introduce a novel noisy correspondence learning framework, namely textbfSelf-textbfReinforcing textbfErrors textbfMitigation (SREM)
  arXiv  Detail & Related papers  (2023-12-27T09:03:43Z)
• Noisy Pair Corrector for Dense Retrieval [59.312376423104055]
  We propose a novel approach called Noisy Pair Corrector (NPC) NPC consists of a detection module and a correction module. We conduct experiments on text-retrieval benchmarks Natural Question and TriviaQA, code-search benchmarks StaQC and SO-DS.
  arXiv  Detail & Related papers  (2023-11-07T08:27:14Z)
• Cross-modal Active Complementary Learning with Self-refining Correspondence [54.61307946222386]
  We propose a Cross-modal Robust Complementary Learning framework (CRCL) to improve the robustness of existing methods. ACL exploits active and complementary learning losses to reduce the risk of providing erroneous supervision. SCC utilizes multiple self-refining processes with momentum correction to enlarge the receptive field for correcting correspondences.
  arXiv  Detail & Related papers  (2023-10-26T15:15:11Z)
• Noisy-Correspondence Learning for Text-to-Image Person Re-identification [50.07634676709067]
  We propose a novel Robust Dual Embedding method (RDE) to learn robust visual-semantic associations even with noisy correspondences. Our method achieves state-of-the-art results both with and without synthetic noisy correspondences on three datasets.
  arXiv  Detail & Related papers  (2023-08-19T05:34:13Z)
• Graph Matching with Bi-level Noisy Correspondence [43.071988798418886]
  Bi-level Noisy Correspondence (BNC) refers to node-level noisy correspondence (NNC) and edge-level noisy correspondence (ENC)
  arXiv  Detail & Related papers  (2022-12-08T05:42:00Z)
• Warp Consistency for Unsupervised Learning of Dense Correspondences [116.56251250853488]
  Key challenge in learning dense correspondences is lack of ground-truth matches for real image pairs. We propose Warp Consistency, an unsupervised learning objective for dense correspondence regression. Our approach sets a new state-of-the-art on several challenging benchmarks, including MegaDepth, RobotCar and TSS.
  arXiv  Detail & Related papers  (2021-04-07T17:58:22Z)

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.