6 papers
See More, Match Better: Multi-Source Feature Fusion for Two-View Correspondence Learning
Xiaojie Li, Xin Jiang, Luanyuan Dai +3
Two-view correspondence learning aims to distinguish true correspondences (inliers) from false ones (outliers) in image pairs by leveraging their underlying differences. Existing m…
DreamVAR: Taming Reinforced Visual Autoregressive Model for High-Fidelity Subject-Driven Image Generation
Xin Jiang, Jingwen Chen, Yehao Li +5
Recent advances in subject-driven image generation using diffusion models have attracted considerable attention for their remarkable capabilities in producing high-quality images.…
Fine-grained Image Retrieval via Dual-Vision Adaptation
Xin Jiang, Meiqi Cao, Hao Tang +2
Fine-Grained Image Retrieval~(FGIR) faces challenges in learning discriminative visual representations to retrieve images with similar fine-grained features. Current leading FGIR s…
OT-DETECTOR: Delving into Optimal Transport for Zero-shot Out-of-Distribution Detection
Yu Liu, Hao Tang, Haiqi Zhang +2
Out-of-distribution (OOD) detection is crucial for ensuring the reliability and safety of machine learning models in real-world applications. While zero-shot OOD detection, which r…
Rethinking Vision Transformer for Large-Scale Fine-Grained Image Retrieval
Xin Jiang, Hao Tang, Yonghua Pan +1
Large-scale fine-grained image retrieval (FGIR) aims to retrieve images belonging to the same subcategory as a given query by capturing subtle differences in a large-scale setting.…
Why pre-training is beneficial for downstream classification tasks?
Xin Jiang, Xu Cheng, Zechao Li
Pre-training has exhibited notable benefits to downstream tasks by boosting accuracy and speeding up convergence, but the exact reasons for these benefits still remain unclear. To…