• Publications
  • Influence
ImageNet: A large-scale hierarchical image database
TLDR
A new database called “ImageNet” is introduced, a large-scale ontology of images built upon the backbone of the WordNet structure, much larger in scale and diversity and much more accurate than the current image datasets.
Efficient k-nearest neighbor graph construction for generic similarity measures
TLDR
N-Descent is presented, a simple yet efficient algorithm for approximate K-NNG construction with arbitrary similarity measures that typically converges to above 90% recall with each point comparing only to several percent of the whole dataset on average.
Visual Semantic Reasoning for Image-Text Matching
TLDR
A simple and interpretable reasoning model to generate visual representation that captures key objects and semantic concepts of a scene that outperforms the current best method for image retrieval and caption retrieval on MS-COCO and Flickr30K datasets.
What Does Classifying More Than 10, 000 Image Categories Tell Us?
TLDR
A study of large scale categorization including a series of challenging experiments on classification with more than 10,000 image classes finds that computational issues become crucial in algorithm design and conventional wisdom from a couple of hundred image categories does not necessarily hold when the number of categories increases.
Search and replication in unstructured peer-to-peer networks
TLDR
This paper proposes a query algorithm based on multiple random walks that resolves queries almost as quickly as Gnutella's flooding method while reducing the network traffic by two orders of magnitude in many cases.
Diskless Checkpointing
TLDR
It is concluded that diskless checkpointing is a desirable alternative to disk-based checkpointing that can improve the performance of distributed applications in the face of failures.
Rethinking Zero-Shot Learning: A Conditional Visual Classification Perspective
TLDR
This work reformulates ZSL as a conditioned visual classification problem, i.e., classifying visual features based on the classifiers learned from the semantic descriptions, and develops algorithms targeting various ZSL settings.
InstaHide: Instance-hiding Schemes for Private Distributed Learning
TLDR
InstaHide, a simple encryption of training images, which can be plugged into existing distributed deep learning pipelines is introduced, which is efficient and applying it during training has minor effect on test accuracy.
Towards Scalable Dataset Construction: An Active Learning Approach
TLDR
This work presents a discriminative learning process which employs active, online learning to quickly classify many images with minimal user input, and demonstrates precision which is often superior to the state-of-the-art, with scalability which exceeds previous work.
TextHide: Tackling Data Privacy for Language Understanding Tasks
TLDR
The proposed TextHide requires all participants to add a simple encryption step to prevent an eavesdropping attacker from recovering private text data, and it fits well with the popular framework of fine-tuning pre-trained language models for any sentence or sentence-pair task.
...
...