Related papers: Representation Learning by Learning to Count
We present a new method to learn video representations from unlabeled data. Given large-scale unlabeled video data, the objective is to benefit from such data by learning a generic and transferable representation space that can be directly…
We study the problem of learning permutation invariant representations that can capture "flexible" notions of containment. We formalize this problem via a measure theoretic definition of multisets, and obtain a theoretically-motivated…
A variety of representation learning approaches have been investigated for reinforcement learning; much less attention, however, has been given to investigating the utility of sparse coding. Outside of reinforcement learning, sparse coding…
This paper presents a novel approach, called Prototype-based Self-Distillation (ProS), for unsupervised face representation learning. The existing supervised methods heavily rely on a large amount of annotated training facial data, which…
Contrastive approaches to representation learning have recently shown great promise. In contrast to generative approaches, these contrastive models learn a deterministic encoder with no notion of uncertainty or confidence. In this paper, we…
Deep neural networks have gained tremendous success in a broad range of machine learning tasks due to its remarkable capability to learn semantic-rich features from high-dimensional data. However, they often require large-scale labelled…
Self-supervised pretraining has been shown to yield powerful representations for transfer learning. These performance gains come at a large computational cost however, with state-of-the-art methods requiring an order of magnitude more…
In this work we propose a technique that transfers supervision between images from different modalities. We use learned representations from a large labeled modality as a supervisory signal for training representations for a new unlabeled…
One of the key challenges in visual imitation learning is collecting large amounts of expert demonstrations for a given task. While methods for collecting human demonstrations are becoming easier with teleoperation methods and the use of…
It has recently been argued that AI models' representations are becoming aligned as their scale and performance increase. Empirical analyses have been designed to support this idea and conjecture the possible alignment of different…
Visual reinforcement learning has proven effective in solving control tasks with high-dimensional observations. However, extracting reliable and generalizable representations from vision-based observations remains a central challenge.…
A fundamental challenge in artificial intelligence is learning useful representations of data that yield good performance on a downstream task, without overfitting to spurious input features. Extracting such task-relevant predictive…
Few-shot classification aims to learn to classify new object categories well using only a few labeled examples. Transferring feature representations from other models is a popular approach for solving few-shot classification problems. In…
Real world learning scenarios involve a nonstationary distribution of classes with sequential dependencies among the samples, in contrast to the standard machine learning formulation of drawing samples independently from a fixed, typically…
Deep learning models develop successive representations of their input in sequential layers, the last of which maps the final representation to the output. Here we investigate the informational content of these representations by observing…
Self-supervised learning is a powerful paradigm for representation learning on unlabelled images. A wealth of effective new methods based on instance matching rely on data-augmentation to drive learning, and these have reached a rough…
Contrastive self-supervised learning has emerged as a promising approach to unsupervised visual representation learning. In general, these methods learn global (image-level) representations that are invariant to different views (i.e.,…
Despite the importance of image representations such as histograms of oriented gradients and deep Convolutional Neural Networks (CNN), our theoretical understanding of them remains limited. Aiming at filling this gap, we investigate three…
We propose a transfer learning method that utilizes data representations in a semiparametric regression model. Our aim is to perform statistical inference on the parameter of primary interest in the target model while accounting for…
Continual learning aims to improve the ability of modern learning systems to deal with non-stationary distributions, typically by attempting to learn a series of tasks sequentially. Prior art in the field has largely considered supervised…