CIMON: Towards High-quality Hash Codes
원문 초록
Recently, hashing is widely used in approximate nearest neighbor search for its storage and computational efficiency. Most of the unsupervised hashing methods learn to map images into semantic similarity-preserving hash codes by constructing local semantic similarity structure from the pre-trained model as the guiding information, i.e., treating each point pair similar if their distance is small in feature space. However, due to the inefficient representation ability of the pre-trained model, many false positives and negatives in local semantic similarity will be introduced and lead to error propagation during the hash code learning. Moreover, few of the methods consider the robustness of models, which will cause instability of hash codes to disturbance. In this paper, we propose a new method named {\textbf{C}}omprehensive s{\textbf{I}}milarity {\textbf{M}}ining and c{\textbf{O}}nsistency lear{\textbf{N}}ing (CIMON). First, we use global refinement and similarity statistical distribution to obtain reliable and smooth guidance. Second, both semantic and contrastive consistency learning are introduced to derive both disturb-invariant and discriminative hash codes. Extensive experiments on several benchmark datasets show that the proposed method outperforms a wide range of state-of-the-art methods in both retrieval performance and robustness.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
ImpliRet: Benchmarking the Implicit Fact Retrieval Challenge
SARA: Selective and Adaptive Retrieval-augmented Generation with Context Compression
LineRetriever: Planning-Aware Observation Reduction for Web Agents
Enhancing Automatic Term Extraction with Large Language Models via Syntactic Retrieval
InsertRank: LLMs can reason over BM25 scores to Improve Listwise Reranking
BIOSSES: A Semantic Sentence Similarity Estimation System for the Biomedical Domain
토론
이 논문과 연결된 포럼 글이 아직 없습니다.