Search papers, labs, and topics across Lattice.
This paper introduces Kent-based Distributional Proxy Hashing (KDPH), a novel approach that replaces deterministic class proxies with flexible Kent distributions to address gradient conflicts in multi-label scenarios during cross-modal hashing. By dynamically adjusting the directional variance of these distributions, KDPH effectively absorbs gradient conflicts while maintaining a stable semantic mean direction, thus preventing optimization collapse. Experimental results on three benchmark datasets show that KDPH significantly outperforms existing state-of-the-art methods, demonstrating its efficacy in mitigating proxy collapse and chaotic oscillation.
KDPH's innovative use of Kent distributions allows it to absorb gradient conflicts, leading to superior performance in cross-modal hashing tasks.
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.
