232 citations · 541 across the 19 of their papers we have counts for
19 papers
OpenIns3D: Snap and Lookup for 3D Open-vocabulary Instance Segmentation
Zhening Huang, Xiaoyang Wu, Xi Chen +3
In this work, we introduce OpenIns3D, a new 3D-input-only framework for 3D open-vocabulary scene understanding. The OpenIns3D framework employs a "Mask-Snap-Lookup" scheme. The "Ma…
PaLI-X: On Scaling up a Multilingual Vision and Language Model
Xi Chen, Josip Djolonga, Piotr Padlewski +40
We present the training recipe and results of scaling up PaLI-X, a multilingual vision and language model, both in terms of size of the components and the breadth of its training t…
Detecting Everything in the Open World: Towards Universal Object Detection
Zhenyu Wang, Yali Li, Xi Chen +4
In this paper, we formally address universal object detection, which aims to detect every scene and predict every category. The dependence on human annotations, the limited visual…
Open-vocabulary Panoptic Segmentation with Embedding Modulation
Xi Chen, Shuang Li, Ser-Nam Lim +2
Open-vocabulary image segmentation is attracting increasing attention due to its critical applications in the real world. Traditional closed-vocabulary segmentation methods are not…
Improving Robust Generalization by Direct PAC-Bayesian Bound Minimization
Zifan Wang, Nan Ding, Tomer Levinboim +2
Recent research in robust optimization has shown an overfitting-like phenomenon in which models trained against adversarial attacks exhibit higher robustness on the training set co…
Dissecting Deep Metric Learning Losses for Image-Text Retrieval
Hong Xuan, Xi Chen
Visual-Semantic Embedding (VSE) is a prevalent approach in image-text retrieval by learning a joint embedding space between the image and language modalities where semantic similar…