Related papers: ReCoRe: Regularized Contrastive Representation Lea…
Reinforcement learning (RL) algorithms are designed to optimize problem-solving by learning actions that maximize rewards, a task that becomes particularly challenging in random and nonstationary environments. Even advanced RL algorithms…
Most existing learning-based methods for solving imaging inverse problems can be roughly divided into two classes: iterative algorithms, such as plug-and-play and diffusion methods leveraging pretrained denoisers, and unrolled architectures…
Dealing with high variance is a significant challenge in model-free reinforcement learning (RL). Existing methods are unreliable, exhibiting high variance in performance from run to run using different initializations/seeds. Focusing on…
At the core of self-supervised learning for vision is the idea of learning invariant or equivariant representations with respect to a set of data transformations. This approach, however, introduces strong inductive biases, which can render…
Contrastive representation learning seeks to acquire useful representations by estimating the shared information between multiple views of data. Here, the choice of data augmentation is sensitive to the quality of learned representations:…
Modern reinforcement learning (RL) algorithms have found success by using powerful probabilistic models, such as transformers, energy-based models, and diffusion/flow-based models. To this end, RL researchers often choose to pay the price…
Reinforcement learning (RL) has improved guided image generation with diffusion models by directly optimizing rewards that capture image quality, aesthetics, and instruction following capabilities. However, the resulting generative policies…
We present a generic and flexible Reinforcement Learning (RL) based meta-learning framework for the problem of few-shot learning. During training, it learns the best optimization algorithm to produce a learner (ranker/classifier, etc) by…
Reinforcement learning (RL) is a powerful approach for robot learning. However, model-free RL (MFRL) requires a large number of environment interactions to learn successful control policies. This is due to the noisy RL training updates and…
Training visual reinforcement learning (RL) in practical scenarios presents a significant challenge, $\textit{i.e.,}$ RL agents suffer from low sample efficiency in environments with variations. While various approaches have attempted to…
In visual recognition, both the object of interest (referred to as foreground, FG, for simplicity) and its surrounding context (background, BG) play an important role. However, standard supervised learning often leads to unintended…
Image harmonization task aims at harmonizing different composite foreground regions according to specific background image. Previous methods would rather focus on improving the reconstruction ability of the generator by some internal…
We design a new iterative algorithm, called REINFORCE-OPT, for solving a general type of optimization problems. This algorithm parameterizes the solution search rule and iteratively updates the parameter using a reinforcement learning (RL)…
We propose a general formulation for addressing reinforcement learning (RL) problems in settings with observational data. That is, we consider the problem of learning good policies solely from historical data in which unobserved factors…
Recently, model-free reinforcement learning algorithms have been shown to solve challenging problems by learning from extensive interaction with the environment. A significant issue with transferring this success to the robotics domain is…
Inverse reinforcement learning (IRL) offers a powerful and general framework for learning humans' latent preferences in route recommendation, yet no approach has successfully addressed planetary-scale problems with hundreds of millions of…
Recently, reinforcement learning models have achieved great success, completing complex tasks such as mastering Go and other games with higher scores than human players. Many of these models collect considerable data on the tasks and…
Data augmentation has been proven to be an effective technique for developing machine learning models that are robust to known classes of distributional shifts (e.g., rotations of images), and alignment regularization is a technique often…
Person re-identification (ReID) aims at searching the same identity person among images captured by various cameras. Unsupervised person ReID attracts a lot of attention recently, due to it works without intensive manual annotation and thus…
Contrastive Learning (CL) has been proved to be a powerful self-supervised approach for a wide range of domains, including computer vision and graph representation learning. However, the incremental learning issue of CL has rarely been…