• Publications
  • Influence
Large-Scale Video Classification with Convolutional Neural Networks
TLDR
This work studies multiple approaches for extending the connectivity of a CNN in time domain to take advantage of local spatio-temporal information and suggests a multiresolution, foveated architecture as a promising way of speeding up the training.
MentorNet: Learning Data-Driven Curriculum for Very Deep Neural Networks on Corrupted Labels
TLDR
Experimental results demonstrate that the proposed novel technique of learning another neural network, called MentorNet, to supervise the training of the base deep networks, namely, StudentNet, can significantly improve the generalization performance of deep networks trained on corrupted training data.
Learning Fine-Grained Image Similarity with Deep Ranking
TLDR
A deep ranking model that employs deep learning techniques to learn similarity metric directly from images has higher learning capability than models based on hand-crafted features and deep classification models.
No Fuss Distance Metric Learning Using Proxies
TLDR
This paper proposes to optimize the triplet loss on a different space of triplets, consisting of an anchor data point and similar and dissimilar proxy points which are learned as well, and proposes a proxy-based loss which improves on state-of-art results for three standard zero-shot learning datasets.
MatchNet: Unifying feature and metric learning for patch-based matching
TLDR
A unified approach to combining feature computation and similarity networks for training a patch matching system that improves accuracy over previous state-of-the-art results on patch matching datasets, while reducing the storage requirement for descriptors is confirmed.
Deep Convolutional Ranking for Multilabel Image Annotation
TLDR
It is shown that a significant performance gain could be obtained by combining convolutional architectures with approximate top-$k$ ranking objectives, as thye naturally fit the multilabel tagging problem.
Improving the Robustness of Deep Neural Networks via Stability Training
TLDR
This paper presents a general stability training method to stabilize deep networks against small input distortions that result from various types of common image processing, such as compression, rescaling, and cropping.
MentorNet: Regularizing Very Deep Neural Networks on Corrupted Labels
TLDR
This work proposes a novel technique to regularize deep networks in the data dimension by learning a neural network called MentorNet to supervise the training of the base network, namely, StudentNet and demonstrates the efficacy of Mentor net on several benchmarks.
Geo-Aware Networks for Fine-Grained Recognition
TLDR
This is the first paper which systematically examined various ways of incorporating geolocated information into fine-grained image classification through the use of geolocation priors, post-processing or feature modulation, and makes a strong case for incorporatingGeolocation information in fine-grade recognition models for both server and on-device.
Handling label noise in video classification via multiple instance learning
TLDR
Experiments show that when training classifiers with noisy data, MILBoost provides an improvement in performance, and the effects of different bag sizes on different levels of noise on the final classifier performance are explored.
...
...