Search Results for author:
Found 7 papers, 4 papers with code
Does resistance to style-transfer equal Global Shape Bias? Measuring network sensitivity to global shape configuration
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.
Learning Weakly-Supervised Contrastive Representations
The first stage is to cluster data according to its auxiliary information.
Conditional Contrastive Learning with Kernel
Conditional contrastive learning frameworks consider the conditional sampling procedure that constructs positive or negative data pairs conditioned on specific variables.
SurfGen: Adversarial 3D Shape Synthesis with Explicit Surface Discriminators
Recent advances in deep generative models have led to immense progress in 3D shape synthesis.
TPU-GAN: Learning temporal coherence from dynamic point cloud sequences
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.
Prototype memory and attention mechanisms for few shot image generation
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.
Integrating Auxiliary Information in Self-supervised Learning
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.
