Skip to search formSkip to main contentSkip to account menu

Geodesic flow kernel for unsupervised domain adaptation

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.
View on IEEE (opens in a new tab)

Marginalized Denoising Autoencoders for Domain Adaptation

The approach of mSDA marginalizes noise and thus does not require stochastic gradient descent or other optimization algorithms to learn parameters--in fact, they are computed in closed-form, significantly speeds up SDAs by two orders of magnitude.
View PDF on arXiv (opens in a new tab)

Shallow Parsing with Conditional Random Fields

This work shows how to train a conditional random field to achieve performance as good as any reported base noun-phrase chunking method on the CoNLL task, and better than any reported single model.
View on ACL (opens in a new tab)

Video Summarization with Long Short-Term Memory

Long Short-Term Memory (LSTM), a special type of recurrent neural networks are used to model the variable-range dependencies entailed in the task of video summarization to improve summarization by reducing the discrepancies in statistical properties across those datasets.
View PDF on arXiv (opens in a new tab)

Synthesized Classifiers for Zero-Shot Learning

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.
View on IEEE (opens in a new tab)

Few-Shot Learning via Embedding Adaptation With Set-to-Set Functions

This paper proposes a novel approach to adapt the instance embeddings to the target classification task with a set-to-set function, yielding embeddeddings that are task-specific and are discriminative.
View on IEEE (opens in a new tab)

Actor-Attention-Critic for Multi-Agent Reinforcement Learning

  • Shariq IqbalFei Sha
  • Computer Science
    International Conference on Machine Learning
  • 27 September 2018
This work presents an actor-critic algorithm that trains decentralized policies in multi-agent settings, using centrally computed critics that share an attention mechanism which selects relevant information for each agent at every timestep, which enables more effective and scalable learning in complex multi- agent environments, when compared to recent approaches.
View PDF on arXiv (opens in a new tab)

An Empirical Study and Analysis of Generalized Zero-Shot Learning for Object Recognition in the Wild

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.
View PDF on arXiv (opens in a new tab)

Learning a kernel matrix for nonlinear dimensionality reduction

This work investigates how to learn a kernel matrix for high dimensional data that lies on or near a low dimensional manifold and shows how to discover a mapping that "unfolds" the underlying manifold from which the data was sampled.
View on ACM (opens in a new tab)

Deformable Spatial Pyramid Matching for Fast Dense Correspondences

This work introduces a fast deformable spatial pyramid (DSP) matching algorithm for computing dense pixel correspondences that simultaneously regularizes match consistency at multiple spatial extents-ranging from an entire image, to coarse grid cells, to every single pixel.
View on IEEE (opens in a new tab)
...
By clicking accept or continuing to use the site, you agree to the terms outlined in our Privacy Policy (opens in a new tab), Terms of Service (opens in a new tab), and Dataset License (opens in a new tab)