Related papers: MonoCon: A general framework for learning ultra-co…

Human performance capture is a highly important computer vision problem with many applications in movie production and virtual/augmented reality. Many previous performance capture approaches either required expensive multi-view setups or…

The Information Contrastive (I-Con) framework revealed that over 23 representation learning methods implicitly minimize KL divergence between data and learned distributions that encode similarities between data points. However, a KL-based…

Unsupervised disentangled representation learning is a long-standing problem in computer vision. This work proposes a novel framework for performing image clustering from deep embeddings by combining instance-level contrastive learning with…

Multimodal learning robust to missing modality has attracted increasing attention due to its practicality. Existing methods tend to address it by learning a common subspace representation for different modality combinations. However, we…

The problem of high-dimensional and large-scale representation of visual data is addressed from an unsupervised learning perspective. The emphasis is put on discrete representations, where the description length can be measured in bits and…

Strand-level hair geometry reconstruction is a fundamental problem in virtual human modeling and the digitization of hairstyles. However, existing methods still suffer from a significant trade-off between accuracy and efficiency. Implicit…

Monocular 3D object detection (Mono3D) aims to infer object locations and dimensions in 3D space from a single RGB image. Despite recent progress, existing methods remain highly sensitive to camera intrinsics and struggle to generalize…

Artificial and biological agents cannon learn given completely random and unstructured data. The structure of data is encoded in the metric relationships between data points. In the context of neural networks, neuronal activity within a…

Unsupervised multi-object representation learning depends on inductive biases to guide the discovery of object-centric representations that generalize. However, we observe that methods for learning these representations are either…

Implicit neural networks, a.k.a., deep equilibrium networks, are a class of implicit-depth learning models where function evaluation is performed by solving a fixed point equation. They generalize classic feedforward models and are…

We propose Automatic Feature Explanation using Contrasting Concepts (FALCON), an interpretability framework to explain features of image representations. For a target feature, FALCON captions its highly activating cropped images using a…

Multimodal representation learning aims to capture both shared and complementary semantic information across multiple modalities. However, the intrinsic heterogeneity of diverse modalities presents substantial challenges to achieve…

Self-supervised monocular depth estimation has gathered notable interest since it can liberate training from dependency on depth annotations. In monocular video training case, recent methods only conduct view synthesis between existing…

Adversarial examples pose a significant challenge to the robustness, reliability and alignment of deep neural networks. We propose a novel, easy-to-use approach to achieving high-quality representations that lead to adversarial robustness…

Contrastive learning has become pivotal in unsupervised representation learning, with frameworks like Momentum Contrast (MoCo) effectively utilizing large negative sample sets to extract discriminative features. However, traditional…

Learning latent representations from long text sequences is an important first step in many natural language processing applications. Recurrent Neural Networks (RNNs) have become a cornerstone for this challenging task. However, the quality…

While advanced image captioning systems are increasingly describing images coherently and exactly, recent progress in continual learning allows deep learning models to avoid catastrophic forgetting. However, the domain where image…

Deep neural networks are widely used in various domains. However, the nature of computations at each layer of the deep networks is far from being well understood. Increasing the interpretability of deep neural networks is thus important.…

Image-based single-modality compression learning approaches have demonstrated exceptionally powerful encoding and decoding capabilities in the past few years , but suffer from blur and severe semantics loss at extremely low bitrates. To…

Many vision-related tasks benefit from reasoning over multiple modalities to leverage complementary views of data in an attempt to learn robust embedding spaces. Most deep learning-based methods rely on a late fusion technique whereby…