{"type":"ScholarlyArticle","title":"Absorbing Gradient Conflicts: Modeling Semantic Variance via Kent Distributions for Cross-Modal Hashing","authors":[{"name":"Hengjie Zhu","slug":"hengjie-zhu","given":"Hengjie","family":"Zhu","affiliation":""},{"name":"Dayan Wu","slug":"dayan-wu","given":"Dayan","family":"Wu","affiliation":""},{"name":"Zihao Zhang","slug":"zihao-zhang","given":"Zihao","family":"Zhang","affiliation":""},{"name":"Xinze Liu","slug":"xinze-liu","given":"Xinze","family":"Liu","affiliation":""},{"name":"Jingxuan Yu","slug":"jingxuan-yu","given":"Jingxuan","family":"Yu","affiliation":""},{"name":"Peng Fu","slug":"peng-fu","given":"Peng","family":"Fu","affiliation":""},{"name":"Zheng Lin","slug":"zheng-lin","given":"Zheng","family":"Lin","affiliation":""},{"name":"Weiping Wang","slug":"weiping-wang","given":"Weiping","family":"Wang","affiliation":""}],"abstract":"Supervised proxy-based deep cross-modal hashing has become the dominant paradigm for large-scale retrieval. However, prevalent methods model class proxies as deterministic points in the embedding space. This rigid assumption causes severe gradient conflicts in multi-label scenarios, where gradient conflicts arising from label co-occurrence lead to severe gradient contention and optimization collapse.To resolve this, we propose Kent-based Distributional Proxy Hashing (KDPH), a novel framework that shifts proxy representation from static points to flexible anisotropic Kent distributions on the hypersphere. Unlike point proxies that must shift their positions to accommodate conflicting gradients, KDPH absorbs these conflicts by dynamically adjusting its directional variance. This allows the proxy to maintain a stable semantic mean direction while stretching to cover diverse label correlations. Furthermore, to ensure stable training of these geometric parameters, we derive a tailored loss function incorporating the Cayley transform to enforce strict orthogonality. To the best of our knowledge, KDPH is the first framework to successfully introduce the Kent distributions into cross-modal hashing.Experiments on three benchmark datasets demonstrate that KDPH mitigates proxy collapse and chaotic oscillation, significantly outperforms state-of-the-art methods. Code is available at https://github.com/Senmo996/KDPH-official-code.","doi":"10.24963/ijcai.2026/239","url":"https://ijcai.org/proceedings/2026/239","pdf":"https://ijcai.org/proceedings/2026/0239.pdf","markdown":"https://ijcai.org/proceedings/2026/239.md","bibtex":"https://ijcai.org/proceedings/2026/bibtex/239","volume":{"slug":"2026","title":"Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2026","url":"https://ijcai.org/proceedings/2026/","year":2026,"location":"Bremen, Germany","dates":"15-21 August 2026","editors":"Diego Calvanese","isbn":"978-1-956792-09-6","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2026"},"section":"Computer Vision","track":"Main Track","number":239,"pages":{"first":2145,"last":2153},"keywords":["Computer Vision: Multimodal learning","Computer Vision: Representation learning","Computer Vision: Image and video retrieval"],"videos":[],"references":[],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}