Related papers: Exploring Visual Engagement Signals for Representa…

In this study, a novel self-supervised learning (SSL) method is proposed, which considers SSL in terms of variational inference to learn not only representation but also representation uncertainties. SSL is a method of learning…

The recently advanced unsupervised learning approaches use the siamese-like framework to compare two "views" from the same image for learning representations. Making the two views distinctive is a core to guarantee that unsupervised methods…

Cross-modal retrieval between visual data and natural language description remains a long-standing challenge in multimedia. While recent image-text retrieval methods offer great promise by learning deep representations aligned across…

As the intermediate-level representations bridging the two levels, structured representations of visual scenes, such as visual relationships between pairwise objects, have been shown to not only benefit compositional models in learning to…

The success of deep learning in computer vision is rooted in the ability of deep networks to scale up model complexity as demanded by challenging visual tasks. As complexity is increased, so is the need for large amounts of labeled data to…

To truly understand vision models, we must not only interpret their learned features but also validate these interpretations through controlled experiments. While earlier work offers either rich semantics or direct control, few post-hoc…

The field of visual representation learning has seen explosive growth in the past years, but its benefits in robotics have been surprisingly limited so far. Prior work uses generic visual representations as a basis to learn (task-specific)…

Image feature representation plays an essential role in image recognition and related tasks. The current state-of-the-art feature learning paradigm is supervised learning from labeled data. However, this paradigm requires large-scale…

We describe a novel weakly supervised deep learning framework that combines both the discriminative and generative models to learn meaningful representation in the multiple instance learning (MIL) setting. MIL is a weakly supervised…

Human-annotated attributes serve as powerful semantic embeddings in zero-shot learning. However, their annotation process is labor-intensive and needs expert supervision. Current unsupervised semantic embeddings, i.e., word embeddings,…

As digital medical imaging becomes more prevalent and archives increase in size, representation learning exposes an interesting opportunity for enhanced medical decision support systems. On the other hand, medical imaging data is often…

Learning robust representations that allow to reliably establish relations between images is of paramount importance for virtually all of computer vision. Annotating the quadratic number of pairwise relations between training images is…

Recently, contrastive learning has largely advanced the progress of unsupervised visual representation learning. Pre-trained on ImageNet, some self-supervised algorithms reported higher transfer learning performance compared to…

State-of-the-art approaches for image captioning require supervised training data consisting of captions with paired image data. These methods are typically unable to use unsupervised data such as textual data with no corresponding images,…

Automated discovery of early visual concepts from raw image data is a major open challenge in AI research. Addressing this problem, we propose an unsupervised approach for learning disentangled representations of the underlying factors of…

Automation of tasks can have critical consequences when humans lose agency over decision processes. Deep learning models are particularly susceptible since current black-box approaches lack explainable reasoning. We argue that both the…

Learning precise representations of users and items to fit observed interaction data is the fundamental task of collaborative filtering. Existing studies usually infer entangled representations to fit such interaction data, neglecting to…

As a subset of unsupervised representation learning, self-supervised representation learning adopts self-defined signals as supervision and uses the learned representation for downstream tasks, such as object detection and image captioning.…

Weakly supervised point cloud semantic segmentation methods that require 1\% or fewer labels, hoping to realize almost the same performance as fully supervised approaches, which recently, have attracted extensive research attention. A…

Most self-supervised learning (SSL) methods learn continuous visual representations by aligning different views of the same input, offering limited control over how information is structured across representation dimensions. In this work,…