Related papers: Self-Supervised Learning of Color Constancy

Convolutional neural networks (CNNs) have shown great success in computer vision, approaching human-level performance when trained for specific tasks via application-specific loss functions. In this paper, we propose a method for augmenting…

Adversarial examples resulting from instability of current computer vision models are an extremely important topic due to their potential to compromise any application. In this paper we demonstrate that instability is inevitable due to a)…

Human adaptability relies crucially on learning and merging knowledge from both supervised and unsupervised tasks: the parents point out few important concepts, but then the children fill in the gaps on their own. This is particularly…

Convolutional Sparse Coding (CSC) is a well-established image representation model especially suited for image restoration tasks. In this work, we extend the applicability of this model by proposing a supervised approach to convolutional…

People's associations between colors and concepts influence their ability to interpret the meanings of colors in information visualizations. Previous work has suggested such effects are limited to concepts that have strong, specific…

What makes an image appear realistic? In this work, we are answering this question from a data-driven perspective by learning the perception of visual realism directly from large amounts of data. In particular, we train a Convolutional…

Whilst contrastive learning yields powerful representations by matching different augmented views of the same instance, it lacks the ability to capture the similarities between different instances. One popular way to address this limitation…

Image harmonization aims to achieve visual consistency in composite images by adapting a foreground to make it compatible with a background. However, existing methods always only use the real image as the positive sample to guide the…

One of the well-known challenges in computer vision tasks is the visual diversity of images, which could result in an agreement or disagreement between the learned knowledge and the visual content exhibited by the current observation. In…

Learning with neural networks from a continuous stream of visual information presents several challenges due to the non-i.i.d. nature of the data. However, it also offers novel opportunities to develop representations that are consistent…

We propose a new contrastive objective for learning overcomplete pixel-level features that are invariant to motion blur. Other invariances (e.g., pose, illumination, or weather) can be learned by applying the corresponding transformations…

Beyond representing the external world, humans also represent their own cognitive processes. In the context of perception, this metacognition helps us identify unreliable percepts, such as when we recognize that we are seeing an illusion.…

Research in child development has shown that embodied experience handling physical objects contributes to many cognitive abilities, including visual learning. One characteristic of such experience is that the learner sees the same object…

Unsupervised object-centric learning from videos is a promising approach to extract structured representations from large, unlabeled collections of videos. To support downstream tasks like autonomous control, these representations must be…

Image colourisation is an ill-posed problem, with multiple correct solutions which depend on the context and object instances present in the input datum. Previous approaches attacked the problem either by requiring intense user interactions…

The perception of color is one of the most important aspects of human vision. From an evolutionary perspective, the accurate perception of color is crucial to distinguishing friend from foe, and food from fatal poison. As a result, humans…

Text-to-image generation models have advanced rapidly, yet achieving fine-grained control over generated images remains difficult, largely due to limited understanding of how semantic information is encoded. We develop an interpretation of…

In this paper we present a world model, which learns causal features using the invariance principle. In particular, we use contrastive unsupervised learning to learn the invariant causal features, which enforces invariance across…

Color and structure are the two pillars that combine to give an image its meaning. Interested in critical structures for neural network recognition, we isolate the influence of colors by limiting the color space to just a few bits, and find…

The continual learning problem has been widely studied in image classification, while rare work has been explored in object detection. Some recent works apply knowledge distillation to constrain the model to retain old knowledge, but this…