activity
20152023
most citedClass-Balanced Loss Based on Effective Number of Samples

130 citations · 330 across the 17 of their papers we have counts for

collaborators
Showing cs.CVShow all

10 papers · 1 filter

cs.CV2023

TractGeoNet: A geometric deep learning framework for pointwise analysis of tract microstructure to predict language assessment performance

Yuqian Chen, Leo R. Zekelman, Chaoyi Zhang +8

We propose a geometric deep-learning-based framework, TractGeoNet, for performing regression using diffusion magnetic resonance imaging (dMRI) tractography and associated pointwise…

cs.CV2022

Towards Bi-directional Skip Connections in Encoder-Decoder Architectures and Beyond

Tiange Xiang, Chaoyi Zhang, Xinyi Wang +4

U-Net, as an encoder-decoder architecture with forward skip connections, has achieved promising results in various medical image analysis tasks. Many recent approaches have also ex…

cs.CV2019

Geo-Aware Networks for Fine-Grained Recognition

Grace Chu, Brian Potetz, Weijun Wang +5

Fine-grained recognition distinguishes among categories with subtle visual differences. In order to differentiate between these challenging visual categories, it is helpful to leve…

cs.CV2019130 cited

Class-Balanced Loss Based on Effective Number of Samples

Yin Cui, Menglin Jia, Tsung-Yi Lin +2

With the rapid increase of large-scale, real-world datasets, it becomes critical to address the problem of long-tailed data distribution (i.e., a few classes account for most of th…

cs.CV2018

Large Scale Fine-Grained Categorization and Domain-Specific Transfer Learning

Yin Cui, Yang Song, Chen Sun +2

Transferring the knowledge learned from large scale datasets (e.g., ImageNet) via fine-tuning offers an effective solution for domain-specific fine-grained visual categorization (F…

cs.CV20186 cited

Decoupled Learning for Conditional Adversarial Networks

Zhifei Zhang, Yang Song, Hairong Qi

Incorporating encoding-decoding nets with adversarial nets has been widely adopted in image generation tasks. We observe that the state-of-the-art achievements were obtained by car…