Related papers: DragonPaint: Rule based bootstrapping for small da…
Deep learning demands a huge amount of well-labeled data to train the network parameters. How to use the least amount of labeled data to obtain the desired classification accuracy is of great practical significance, because for many…
We investigate a novel approach for image restoration by reinforcement learning. Unlike existing studies that mostly train a single large network for a specialized task, we prepare a toolbox consisting of small-scale convolutional networks…
Data augmentation is a commonly used approach to improving the generalization of deep learning models. Recent works show that learned data augmentation policies can achieve better generalization than hand-crafted ones. However, most of…
When cast into the Deep Reinforcement Learning framework, many robotics tasks require solving a long horizon and sparse reward problem, where learning algorithms struggle. In such context, Imitation Learning (IL) can be a powerful approach…
Scarcity of labeled data has motivated the development of semi-supervised learning methods, which learn from large portions of unlabeled data alongside a few labeled samples. Consistency Regularization between model's predictions under…
We demonstrate that self-learning techniques like entropy minimization and pseudo-labeling are simple and effective at improving performance of a deployed computer vision model under systematic domain shifts. We conduct a wide range of…
Self-supervised representation learning often uses data augmentations to induce some invariance to "style" attributes of the data. However, with downstream tasks generally unknown at training time, it is difficult to deduce a priori which…
Most existing works in few-shot learning rely on meta-learning the network on a large base dataset which is typically from the same domain as the target dataset. We tackle the problem of cross-domain few-shot learning where there is a large…
Large-scale supervised classification algorithms, especially those based on deep convolutional neural networks (DCNNs), require vast amounts of training data to achieve state-of-the-art performance. Decreasing this data requirement would…
Deep reinforcement learning (DRL) has exhibited considerable promise in the training of control agents for mapless robot navigation. However, DRL-trained agents are limited to the specific robot dimensions used during training, hindering…
Supervised deep learning methods for segmentation require large amounts of labelled training data, without which they are prone to overfitting, not generalizing well to unseen images. In practice, obtaining a large number of annotations…
Real-world data often follows a long-tailed distribution, which makes the performance of existing classification algorithms degrade heavily. A key issue is that samples in tail categories fail to depict their intra-class diversity. Humans…
We address the problem of semi-supervised domain adaptation of classification algorithms through deep Q-learning. The core idea is to consider the predictions of a source domain network on target domain data as noisy labels, and learn a…
Recent advances in image captioning have focused on scaling the data and model size, substantially increasing the cost of pre-training and finetuning. As an alternative to large models, we present SmallCap, which generates a caption…
Vision and learning have made significant progress that could improve robotics policies for complex tasks and environments. Learning deep neural networks for image understanding, however, requires large amounts of domain-specific visual…
Authoring an appealing animation for a virtual character is a challenging task. In computer-aided keyframe animation artists define the key poses of a character by manipulating its underlying skeletons. To look plausible, a character pose…
Learning Based Robot Grasping currently involves the use of labeled data. This approach has two major disadvantages. Firstly, labeling data for grasp points and angles is a strenuous process, so the dataset remains limited. Secondly, human…
While deep learning methods have shown great success in medical image analysis, they require a number of medical images to train. Due to data privacy concerns and unavailability of medical annotators, it is oftentimes very difficult to…
One of the key criticisms of deep learning is that large amounts of expensive and difficult-to-acquire training data are required in order to train models with high performance and good generalization capabilities. Focusing on the task of…
Cartoon editing, appreciated by both professional illustrators and hobbyists, allows extensive creative freedom and the development of original narratives within the cartoon domain. However, the existing literature on cartoon editing is…