Related papers: Idempotent Unsupervised Representation Learning fo…

Adversarially trained generative models (GANs) have recently achieved compelling image synthesis results. But despite early successes in using GANs for unsupervised representation learning, they have since been superseded by approaches…

Neural networks are prone to catastrophic forgetting when trained incrementally on different tasks. Popular incremental learning methods mitigate such forgetting by retaining a subset of previously seen samples and replaying them during the…

We introduce Equilibrium Matching (EqM), a generative modeling framework built from an equilibrium dynamics perspective. EqM discards the non-equilibrium, time-conditional dynamics in traditional diffusion and flow-based generative models…

A good representation for arbitrarily complicated data should have the capability of semantic generation, clustering and reconstruction. Previous research has already achieved impressive performance on either one. This paper aims at…

Feature-based image matching has extensive applications in computer vision. Keypoints detected in images can be naturally represented as graph structures, and Graph Neural Networks (GNNs) have been shown to outperform traditional deep…

Self-paced learning has been beneficial for tasks where some initial knowledge is available, such as weakly supervised learning and domain adaptation, to select and order the training sample sequence, from easy to complex. However its…

Skeleton-based action recognition aims to project skeleton sequences to action categories, where skeleton sequences are derived from multiple forms of pre-detected points. Compared with earlier methods that focus on exploring single-form…

Unsupervised learning of generative models has seen tremendous progress over recent years, in particular due to generative adversarial networks (GANs), variational autoencoders, and flow-based models. GANs have dramatically improved sample…

We propose a novel system for unsupervised skeleton-based action recognition. Given inputs of body keypoints sequences obtained during various movements, our system associates the sequences with actions. Our system is based on an…

We introduce a novel backbone architecture to improve target-perception ability of feature representation for tracking. Specifically, having observed that de facto frameworks perform feature matching simply using the outputs from backbone…

We consider the problem of learning deep generative models from data. We formulate a method that generates an independent sample via a single feedforward pass through a multilayer perceptron, as in the recently proposed generative…

Robust generalization to new concepts has long remained a distinctive feature of human intelligence. However, recent progress in deep generative models has now led to neural architectures capable of synthesizing novel instances of unknown…

Skeleton-based action recognition has recently received considerable attention. Current approaches to skeleton-based action recognition are typically formulated as one-hot classification tasks and do not fully exploit the semantic relations…

We introduce a new approach to probabilistic unsupervised learning based on the recognition-parametrised model (RPM): a normalised semi-parametric hypothesis class for joint distributions over observed and latent variables. Under the key…

Rapid progress in deep reinforcement learning has made it increasingly feasible to train controllers for high-dimensional humanoid bodies. However, methods that use pure reinforcement learning with simple reward functions tend to produce…

Perceptual features (PFs) have been used with great success in tasks such as transfer learning, style transfer, and super-resolution. However, the efficacy of PFs as key source of information for learning generative models is not well…

Unified Multimodal Models (UMMs) integrate both visual understanding and generation within a single framework. Their ultimate aspiration is to create a cycle where understanding and generation mutually reinforce each other. While recent…

Representation (feature) space is an environment where data points are vectorized, distances are computed, patterns are characterized, and geometric structures are embedded. Extracting a good representation space is critical to address the…

Memory units have been widely used to enrich the capabilities of deep networks on capturing long-term dependencies in reasoning and prediction tasks, but little investigation exists on deep generative models (DGMs) which are good at…

Unified multimodal models (UMMs) achieve strong performance in both understanding and generation by learning a shared latent space, yet they often exhibit functional inconsistency between these two capabilities. We observe that this issue…