activity
20212023
most citedLessons learned from the NeurIPS 2021 MetaDL challenge: Backbone fine-tuning without episodic meta-learning dominates for few-shot learning image classification

7 citations · 16 across the 7 of their papers we have counts for

collaborators

7 papers

stat.ML2023

Understanding the Generalization Ability of Deep Learning Algorithms: A Kernelized Renyi's Entropy Perspective

Yuxin Dong, Tieliang Gong, Hong Chen +1

Recently, information theoretic analysis has become a popular framework for understanding the generalization behavior of deep neural networks. It allows a direct analysis for stoch…

cs.LG2023

Stability-based Generalization Analysis for Mixtures of Pointwise and Pairwise Learning

Jiahuan Wang, Jun Chen, Hong Chen +3

Recently, some mixture algorithms of pointwise and pairwise learning (PPL) have been formulated by employing the hybrid error metric of "pointwise loss + pairwise loss" and have sh…

stat.ML2023

On the Stability and Generalization of Triplet Learning

Jun Chen, Hong Chen, Xue Jiang +4

Triplet learning, i.e. learning from triplet data, has attracted much attention in computer vision tasks with an extremely large number of categories, e.g., face recognition and pe…

cs.CL20237 cited

RESDSQL: Decoupling Schema Linking and Skeleton Parsing for Text-to-SQL

Haoyang Li, Jing Zhang, Cuiping Li +1

One of the recent best attempts at Text-to-SQL is the pre-trained language model. Due to the structural property of the SQL queries, the seq2seq model takes the responsibility of p…

cs.CV2022

Bag of Tricks for Out-of-Distribution Generalization

Zining Chen, Weiqiu Wang, Zhicheng Zhao +2

Recently, out-of-distribution (OOD) generalization has attracted attention to the robustness and generalization ability of deep learning based models, and accordingly, many strateg…

cs.LG20227 cited

Lessons learned from the NeurIPS 2021 MetaDL challenge: Backbone fine-tuning without episodic meta-learning dominates for few-shot learning image classification

Adrian El Baz, Ihsan Ullah, Edesio Alcobaça +17

Although deep neural networks are capable of achieving performance superior to humans on various tasks, they are notorious for requiring large amounts of data and computing resourc…