Related papers: Adaptive ROI Generation for Video Object Segmentat…
This paper presents a novel approach for unsupervised video summarization using reinforcement learning (RL), addressing limitations like unstable adversarial training and reliance on heuristic-based reward functions. The method operates on…
Interactive image segmentation aims at segmenting a target region through a way of human-computer interaction. Recent works based on deep learning have achieved excellent performance, while most of them focus on improving the accuracy of…
We present an approach for reconfiguration of dynamic visual sensor networks with deep reinforcement learning (RL). Our RL agent uses a modified asynchronous advantage actor-critic framework and the recently proposed Relational Network…
First-person object-interaction tasks in high-fidelity, 3D, simulated environments such as the AI2Thor virtual home-environment pose significant sample-efficiency challenges for reinforcement learning (RL) agents learning from sparse task…
Object detection in aerial images is an active yet challenging task in computer vision because of the birdview perspective, the highly complex backgrounds, and the variant appearances of objects. Especially when detecting densely packed…
The significant growth of surveillance camera networks necessitates scalable AI solutions to efficiently analyze the large amount of video data produced by these networks. As a typical analysis performed on surveillance footage, video…
Current deep reinforcement learning (RL) approaches incorporate minimal prior knowledge about the environment, limiting computational and sample efficiency. \textit{Objects} provide a succinct and causal description of the world, and many…
Reinforcement Learning (RL) is notoriously data-inefficient, which makes training on a real robot difficult. While model-based RL algorithms (world models) improve data-efficiency to some extent, they still require hours or days of…
Reinforcement learning (RL) struggles to scale to large, combinatorial action spaces common in many real-world problems. This paper introduces a novel framework for training discrete diffusion models as highly effective policies in these…
This work concerns itself with the task of reconstructing all edges of an arbitrary 3D wire-frame model projected to an image plane. We explore a bottom-up part-wise procedure undertaken by an RL agent to segment and reconstruct these 2D…
Imitation learning holds tremendous promise in learning policies efficiently for complex decision making problems. Current state-of-the-art algorithms often use inverse reinforcement learning (IRL), where given a set of expert…
The success of Reinforcement Learning (RL) heavily relies on the ability to learn robust representations from the observations of the environment. In most cases, the representations learned purely by the reinforcement learning loss can…
The performance of a trained object detection neural network depends a lot on the image quality. Generally, images are pre-processed before feeding them into the neural network and domain knowledge about the image dataset is used to choose…
Cross-domain offline reinforcement learning (RL) aims to train a well-performing agent in the target environment, leveraging both a limited target domain dataset and a source domain dataset with (possibly) sufficient data coverage. Due to…
Traditionally, an object detector is applied to every part of the scene of interest, and its accuracy and computational cost increases with higher resolution images. However, in some application domains such as remote sensing, purchasing…
The endeavor of artificial intelligence (AI) is to design autonomous agents capable of achieving complex tasks. Namely, reinforcement learning (RL) proposes a theoretical background to learn optimal behaviors. In practice, RL algorithms…
To avoid the exhaustive search over locations and scales, current state-of-the-art object detection systems usually involve a crucial component generating a batch of candidate object proposals from images. In this paper, we present a simple…
Semantic segmentation requires large amounts of pixel-wise annotations to learn accurate models. In this paper, we present a video prediction-based methodology to scale up training sets by synthesizing new training samples in order to…
Despite many advances in deep-learning based semantic segmentation, performance drop due to distribution mismatch is often encountered in the real world. Recently, a few domain adaptation and active learning approaches have been proposed to…
Many AI problems, in robotics and other domains, are goal-based, essentially seeking trajectories leading to various goal states. Reinforcement learning (RL), building on Bellman's optimality equation, naturally optimizes for a single goal,…