Related papers: Learning to Transfer Privileged Information

Existing RNN-based approaches for action recognition from depth sequences require either skeleton joints or hand-crafted depth features as inputs. An end-to-end manner, mapping from raw depth maps to action classes, is non-trivial to design…

Image clustering is a particularly challenging computer vision task, which aims to generate annotations without human supervision. Recent advances focus on the use of self-supervised learning strategies in image clustering, by first…

Discriminative self-supervised learning allows training models on any random group of internet images, and possibly recover salient information that helps differentiate between the images. Applied to ImageNet, this leads to object centric…

Deep Learning requires large amounts of data to train models that work well. In data-deficient settings, performance can be degraded. We investigate which Deep Learning methods benefit training models in a data-deficient setting, by…

Humans can quickly learn new visual concepts, perhaps because they can easily visualize or imagine what novel objects look like from different views. Incorporating this ability to hallucinate novel instances of new concepts might help…

While the majority of today's object class models provide only 2D bounding boxes, far richer output hypotheses are desirable including viewpoint, fine-grained category, and 3D geometry estimate. However, models trained to provide richer…

Image-based Reinforcement Learning is known to suffer from poor sample efficiency and generalisation to unseen visuals such as distractors (task-independent aspects of the observation space). Visual domain randomisation encourages transfer…

Identification of an entity that is of interest is prominent in any intelligent system. The visual intelligence of the model is enhanced when the capability of recognition is added. Several methods such as transfer learning and zero shot…

Classifiers embedded within human in the loop visual object recognition frameworks commonly utilise two sources of information: one derived directly from the imagery data of an object, and the other obtained interactively from user…

Self-supervised learning holds promise in leveraging large numbers of unlabeled data. However, its success heavily relies on the highly-curated dataset, e.g., ImageNet, which still needs human cleaning. Directly learning representations…

Human perception is structured around objects which form the basis for our higher-level cognition and impressive systematic generalization abilities. Yet most work on representation learning focuses on feature learning without even…

The exponential growth of astronomical data from large-scale surveys has created both opportunities and challenges for the astrophysics community. This paper explores the possibilities offered by transfer learning techniques in addressing…

We consider the problem of discovering novel object categories in an image collection. While these images are unlabelled, we also assume prior knowledge of related but different image classes. We use such prior knowledge to reduce the…

We present the first diffusion-based framework that can learn an unknown distribution using only highly-corrupted samples. This problem arises in scientific applications where access to uncorrupted samples is impossible or expensive to…

Semantic segmentation, which aims to acquire a detailed understanding of images, is an essential issue in computer vision. However, in practical scenarios, new categories that are different from the categories in training usually appear.…

Power-law scaling indicates that large-scale training with uniform sampling is prohibitively slow. Active learning methods aim to increase data efficiency by prioritizing learning on the most relevant examples. Despite their appeal, these…

Transfer learning enables to re-use knowledge learned on a source task to help learning a target task. A simple form of transfer learning is common in current state-of-the-art computer vision models, i.e. pre-training a model for image…

Scene labeling task is to segment the image into meaningful regions and categorize them into classes of objects which comprised the image. Commonly used methods typically find the local features for each segment and label them using…

Collecting and labeling the registered 3D point cloud is costly. As a result, 3D resources for training are typically limited in quantity compared to the 2D images counterpart. In this work, we deal with the data scarcity challenge of 3D…

We propose an approach to self-supervised representation learning based on maximizing mutual information between features extracted from multiple views of a shared context. For example, one could produce multiple views of a local…