no code implementations • 11 Oct 2023 • Ziqi Wen, Tianqin Li, Zhi Jing, Tai Sing Lee
The current benchmark for evaluating a model's global shape bias is a set of style-transferred images with the assumption that resistance to the attack of style transfer is related to the development of global structure sensitivity in the model.
1 code implementation • ICLR 2022 • Yao-Hung Hubert Tsai, Tianqin Li, Weixin Liu, Peiyuan Liao, Ruslan Salakhutdinov, Louis-Philippe Morency
The first stage is to cluster data according to its auxiliary information.
1 code implementation • ICLR 2022 • Yao-Hung Hubert Tsai, Tianqin Li, Martin Q. Ma, Han Zhao, Kun Zhang, Louis-Philippe Morency, Ruslan Salakhutdinov
Conditional contrastive learning frameworks consider the conditional sampling procedure that constructs positive or negative data pairs conditioned on specific variables.
1 code implementation • ICCV 2021 • Andrew Luo, Tianqin Li, Wen-Hao Zhang, Tai Sing Lee
Recent advances in deep generative models have led to immense progress in 3D shape synthesis.
no code implementations • ICLR 2022 • Tianqin Li, Zijie Li, Andrew Luo, Harold Rockwell, Amir Barati Farimani, Tai Sing Lee
To test our proposal, we show in a few-shot image generation task, that having a prototype memory during attention can improve image synthesis quality, learn interpretable visual concept clusters, as well as improve the robustness of the model.
1 code implementation • ICLR 2022 • Zijie Li, Tianqin Li, Amir Barati Farimani
Our model, Temporal Point cloud Upsampling GAN (TPU-GAN), can implicitly learn the underlying temporal coherence from point cloud sequence, which in turn guides the generator to produce temporally coherent output.
no code implementations • 5 Jun 2021 • Yao-Hung Hubert Tsai, Tianqin Li, Weixin Liu, Peiyuan Liao, Ruslan Salakhutdinov, Louis-Philippe Morency
Our approach contributes as follows: 1) Comparing to conventional self-supervised representations, the auxiliary-information-infused self-supervised representations bring the performance closer to the supervised representations; 2) The presented Cl-InfoNCE can also work with unsupervised constructed clusters (e. g., k-means clusters) and outperform strong clustering-based self-supervised learning approaches, such as the Prototypical Contrastive Learning (PCL) method; 3) We show that Cl-InfoNCE may be a better approach to leverage the data clustering information, by comparing it to the baseline approach - learning to predict the clustering assignments with cross-entropy loss.