Artificial Intelligence

2606 Submissions

[2] viXra:2606.0022 [pdf] submitted on 2026-06-05 18:00:10

Decoupled Prompting and Topology-Aware Optimal Transport for CLIP-Based Unsupervised Cross-Modal Re-Identiffcation

Authors: Xiaohao Xie, Wenhua Jiao, Wei Meng
Comments: 14 Pages. (Note by viXra Admin: Please submit article written with AI assistance to ai.viXra.org)

Unsupervised Visible-Infrared Person Re-identification (USL-VI-ReID) is critical for cross-modal intelligent surveillance. While vision-language models (e.g., CLIP) present powerful representational capabilities, directly fine-tuning them for USL-VI-ReID often causes catastrophic feature collapse and prompt degradation due to massive domain gaps and noisy pseudo-labels. Furthermore, traditional discrete matching and heuristic denoising strategies suffer from severe cross-modal information starvation and numerical bias against hard positives. To address these challenges, we propose a robust, CLIP-based unsupervised cross-modal fine-tuning framework. First, we design an implicit adapter fine-tuning strategy coupled with decoupled multi-dimensional semantic prompting to isolate domain biases without destroying pre-trained priors. Second, a Cluster-Aware Cross-Modal Semantic Alignment (CCSA) mechanism maps dynamic visual centers to modality-shared textual proxies via visual-conditioned prompting, facilitating an implicit soft alignment decoupled from hard clustering noise. Third, we frame cross-modal association as a Topology-Aware Optimal Transport (TOTO) problem. Utilizing Fused Gromov-Wasserstein (FGW) constraints and Argmax assignments, TOTO injects potent hard regularization to overcome optimization inertia on difficult samples. Finally, our Pure Relative Confidence Ratio and Dual Adaptive Denoising (RCR-DAD) module eliminates numerical bias, formulating a robust self-paced learning trajectory. Extensive experiments on SYSU-MM01 and RegDB demonstrate our framework achieves state-of-the-art performance. The code will be released.
Category: Artificial Intelligence

[1] viXra:2606.0018 [pdf] submitted on 2026-06-06 14:18:10

Visual Space, Neural Networks, and AI Algorithm Models

Authors: Taiwei Song
Comments: 4 Pages. 4

This paper briefly discusses the concept of visual space discovered by the author [1-4], its transformation equation with the natural space-time, and points out that this transformation relationship is the key algorithm for AI embodied agents to automatically recognize the surrounding "world". It also briefly demonstrates that neural networks inherently possess the properties of "iterative convergence" and "self-learning evolution", and the "emergence of intelligence" in large AI models based on neural networks is inevitable.
Category: Artificial Intelligence