TY - JOUR AU - Zheng, Feng AU - Huang, Heng PY - 2018/04/29 Y2 - 2024/03/28 TI - Direct Hashing Without Pseudo-Labels JF - Proceedings of the AAAI Conference on Artificial Intelligence JA - AAAI VL - 32 IS - 1 SE - AAAI Technical Track: Machine Learning DO - 10.1609/aaai.v32i1.11675 UR - https://ojs.aaai.org/index.php/AAAI/article/view/11675 SP - AB - <p> Recently, binary hashing has been widely applied to data compression, ranking and nearest-neighbor search. Although some promising results have been achieved, effectively optimizing sign function related objectives is still highly challenging and thus pseudo-labels are inevitably used. In this paper, we propose a novel general framework to simultaneously minimize the measurement distortion and the quantization loss, which enable to learn hash functions directly without requiring the pseudo-labels. More significantly, a novel W-Shape Loss (WSL) is specifically developed for hashing so that both the two separate steps of relaxation and the NP-hard discrete optimization are successfully discarded. The experimental results demonstrate that the retrieval performance both in uni-modal and cross-modal settings can be improved. </p> ER -