Related papers: RELO: Reinforcement Learning to Localize for Visua…

In this work, we propose Adversarial Complementary Learning (ACoL) to automatically localize integral objects of semantic interest with weak supervision. We first mathematically prove that class localization maps can be obtained by directly…

In reinforcement learning (RL), value-based algorithms learn to associate each observation with the states and rewards that are likely to be reached from it. We observe that many self-supervised image pre-training methods bear similarity to…

Visual localization on standard-definition (SD) maps has emerged as a promising low-cost and scalable solution for autonomous driving. However, existing regression-based approaches often overlook inherent geometric priors, resulting in…

Current reinforcement learning (RL) algorithms can be brittle and difficult to use, especially when learning goal-reaching behaviors from sparse rewards. Although supervised imitation learning provides a simple and stable alternative, it…

Reinforcement Learning frameworks, particularly those utilizing human annotations, have become an increasingly popular method for preference fine-tuning, where the outputs of a language model are tuned to match a certain set of behavioral…

In recent years, reinforcement learning (RL) has gained increasing attention in control engineering. Especially, policy gradient methods are widely used. In this work, we improve the tracking performance of proximal policy optimization…

Goal-conditioned reinforcement learning (GCRL) allows agents to learn diverse objectives using a unified policy. The success of GCRL, however, is contingent on the choice of goal representation. In this work, we propose a mask-based goal…

Weakly-supervised learning approaches have gained significant attention due to their ability to reduce the effort required for human annotations in training neural networks. This paper investigates a framework for weakly-supervised object…

Recognizing multiple labels of images is a fundamental but challenging task in computer vision, and remarkable progress has been attained by localizing semantic-aware image regions and predicting their labels with deep convolutional neural…

While reinforcement learning (RL) has the potential to enable robots to autonomously acquire a wide range of skills, in practice, RL usually requires manual, per-task engineering of reward functions, especially in real world settings where…

Visual localization aims to determine the camera pose of a query image relative to a database of posed images. In recent years, deep neural networks that directly regress camera poses have gained popularity due to their fast inference…

Learning multiple tasks sequentially without forgetting previous knowledge, called Continual Learning(CL), remains a long-standing challenge for neural networks. Most existing methods rely on additional network capacity or data replay. In…

World models simulate dynamic environments, enabling agents to interact with diverse input modalities. Although recent advances have improved the visual quality and temporal consistency of video world models, their ability of accurately…

In this paper we tackle the problem of deformable object manipulation through model-free visual reinforcement learning (RL). In order to circumvent the sample inefficiency of RL, we propose two key ideas that accelerate learning. First, we…

With the spread of tampered images, locating the tampered regions in digital images has drawn increasing attention. The existing image tampering localization methods, however, suffer from severe performance degradation when the tampered…

We transform reinforcement learning (RL) into a form of supervised learning (SL) by turning traditional RL on its head, calling this Upside Down RL (UDRL). Standard RL predicts rewards, while UDRL instead uses rewards as task-defining…

Multimodal Large Language Models (MLLMs) excel in vision-language reasoning but often struggle with structured perception tasks requiring precise localization and robustness. We propose a reinforcement learning framework that augments Group…

Self-supervised feature learning enables perception systems to benefit from the vast raw data recorded by vehicle fleets worldwide. While video-level self-supervised learning approaches have shown strong generalizability on classification…

We introduce Talk2Move, a reinforcement learning (RL) based diffusion framework for text-instructed spatial transformation of objects within scenes. Spatially manipulating objects in a scene through natural language poses a challenge for…

The visual camera is an attractive device in beyond visual line of sight (B-VLOS) drone operation, since they are low in size, weight, power, and cost, and can provide redundant modality to GPS failures. However, state-of-the-art visual…