• Publications
  • Influence
Geodesic flow kernel for unsupervised domain adaptation
TLDR
This paper proposes a new kernel-based method that takes advantage of low-dimensional structures that are intrinsic to many vision datasets, and introduces a metric that reliably measures the adaptability between a pair of source and target domains. Expand
Synthesized Classifiers for Zero-Shot Learning
TLDR
This work introduces a set of "phantom" object classes whose coordinates live in both the semantic space and the model space and demonstrates superior accuracy of this approach over the state of the art on four benchmark datasets for zero-shot learning. Expand
Large-Scale Long-Tailed Recognition in an Open World
TLDR
An integrated OLTR algorithm is developed that maps an image to a feature space such that visual concepts can easily relate to each other based on a learned metric that respects the closed-world classification while acknowledging the novelty of the open world. Expand
An Empirical Study and Analysis of Generalized Zero-Shot Learning for Object Recognition in the Wild
TLDR
It is shown that there is a large gap between the performance of existing approaches and the performance limit of GZSL, suggesting that improving the quality of class semantic embeddings is vital to improving ZSL. Expand
Diverse Sequential Subset Selection for Supervised Video Summarization
TLDR
This work proposes the sequential determinantal point process (seqDPP), a probabilistic model for diverse sequential subset selection, which heeds the inherent sequential structures in video data, thus overcoming the deficiency of the standard DPP. Expand
Connecting the Dots with Landmarks: Discriminatively Learning Domain-Invariant Features for Unsupervised Domain Adaptation
TLDR
This paper automatically discovers the existence of landmarks and uses them to bridge the source to the target by constructing provably easier auxiliary domain adaptation tasks, and shows how this composition can be optimized discriminatively without requiring labels from the target domain. Expand
Curriculum Domain Adaptation for Semantic Segmentation of Urban Scenes
TLDR
This work proposes a curriculum-style learning approach to minimize the domain gap in semantic segmentation, which significantly outperforms the baselines as well as the only known existing approach to the same problem. Expand
Adversarial Examples Improve Image Recognition
TLDR
This work proposes AdvProp, an enhanced adversarial training scheme which treats adversarial examples as additional examples, to prevent overfitting, and shows that AdvProp improves a wide range of models on various image recognition tasks and performs better when the models are bigger. Expand
Improving the Improved Training of Wasserstein GANs: A Consistency Term and Its Dual Effect
TLDR
This paper proposes a novel approach to enforcing the Lipschitz continuity in the training procedure of WGANs, which gives rise to not only better photo-realistic samples than the previous methods but also state-of-the-art semi-supervised learning results. Expand
Reshaping Visual Datasets for Domain Adaptation
TLDR
This work devise a nonparametric formulation and efficient optimization procedure that can successfully discover domains among both training and test data and ensures that a strong discriminative model can be learned from the domain. Expand
...
1
2
3
4
5
...