Bi-Drop: Enhancing Fine-tuning Generalization via Synchronous sub-net Estimation and Optimization

no code implementations • 24 May 2023 • Shoujie Tong, Heming Xia, Damai Dai, Runxin Xu, Tianyu Liu, Binghuai Lin, Yunbo Cao, Zhifang Sui

Also, Bi-Drop needs only one mini-batch to estimate the sub-net so it achieves higher utility of training data.

Natural Language Understanding

Robust Fine-tuning via Perturbation and Interpolation from In-batch Instances

1 code implementation • 2 May 2022 • Shoujie Tong, Qingxiu Dong, Damai Dai, YiFan Song, Tianyu Liu, Baobao Chang, Zhifang Sui

For each instance in a batch, we involve other instances in the same batch to interact with it.

Premise-based Multimodal Reasoning: Conditional Inference on Joint Textual and Visual Clues

no code implementations • ACL 2022 • Qingxiu Dong, Ziwei Qin, Heming Xia, Tian Feng, Shoujie Tong, Haoran Meng, Lin Xu, Weidong Zhan, Sujian Li, Zhongyu Wei, Tianyu Liu, Zuifang Sui

It is a common practice for recent works in vision language cross-modal reasoning to adopt a binary or multi-choice classification formulation taking as input a set of source image(s) and textual query.

Multimodal Reasoning Natural Language Inference +1