5 papers
Enhancing Open-Vocabulary Object Detection through Multi-Level Fine-Grained Visual-Language Alignment
Tianyi Zhang, Antoine Simoulin, Kai Li +5
Traditional object detection systems are typically constrained to predefined categories, limiting their applicability in dynamic environments. In contrast, open-vocabulary object d…
Context-Aware Token Selection and Packing for Enhanced Vision Transformer
Tianyi Zhang, Baoxin Li, Jae-sun Seo +1
In recent years, the long-range attention mechanism of vision transformers has driven significant performance breakthroughs across various computer vision tasks. However, the tradi…
Uncertainty-Based Extensible Codebook for Discrete Federated Learning in Heterogeneous Data Silos
Tianyi Zhang, Yu Cao, Dianbo Liu
Federated learning (FL), aimed at leveraging vast distributed datasets, confronts a crucial challenge: the heterogeneity of data across different silos. While previous studies have…
Transformer-based Selective Super-Resolution for Efficient Image Refinement
Tianyi Zhang, Kishore Kasichainula, Yaoxin Zhuo +3
Conventional super-resolution methods suffer from two drawbacks: substantial computational cost in upscaling an entire large image, and the introduction of extraneous or potentiall…
Patch-based Selection and Refinement for Early Object Detection
Tianyi Zhang, Kishore Kasichainula, Yaoxin Zhuo +3
Early object detection (OD) is a crucial task for the safety of many dynamic systems. Current OD algorithms have limited success for small objects at a long distance. To improve th…