Search Results for author:
Found 10 papers, 2 papers with code
Semantic Generative Augmentations for Few-Shot Counting
This requires to generate images that correspond to a given input number of objects.
Ranked #5 on
Object Counting
on FSC147
(using extra training data)
Multimodal Representations for Teacher-Guided Compositional Visual Reasoning
Neural Module Networks (NMN) are a compelling method for visual question answering, enabling the translation of a question into a program consisting of a series of reasoning sub-tasks that are sequentially executed on the image to produce an answer.
Curriculum Learning for Compositional Visual Reasoning
Visual Question Answering (VQA) is a complex task requiring large datasets and expensive training.
Wasserstein Loss for Semantic Editing in the Latent Space of GANs
The latent space of GANs contains rich semantics reflecting the training data.
Why is the prediction wrong? Towards underfitting case explanation via meta-classification
In this paper we present a heuristic method to provide individual explanations for those elements in a dataset (data points) which are wrongly predicted by a given classifier.
Multi-Attribute Balanced Sampling for Disentangled GAN Controls
We propose to address disentanglement by subsampling the generated data to remove over-represented co-occuring attributes thus balancing the semantics of the dataset before training the classifiers.
Zero-shot Learning with Deep Neural Networks for Object Recognition
The general approach is to learn a mapping from visual data to semantic prototypes, then use it at inference to classify visual samples from the class prototypes only.
Using Sentences as Semantic Representations in Large Scale Zero-Shot Learning
Zero-shot learning aims to recognize instances of unseen classes, for which no visual instance is available during training, by learning multimodal relations between samples from seen classes and corresponding class semantic representations.
From Classical to Generalized Zero-Shot Learning: a Simple Adaptation Process
Zero-shot learning (ZSL) is concerned with the recognition of previously unseen classes.
Aggregating Image and Text Quantized Correlated Components
To address this problem, we first put forward here a new representation method that aggregates information provided by the projections of both modalities on their aligned subspaces.
