Semantic image segmentation is an essential component of modern autonomous driving systems, as an accurate understanding of the surrounding scene is crucial to navigation and action planning. Current ...state-of-the-art approaches in semantic image segmentation rely on pre-trained networks that were initially developed for classifying images as a whole. While these networks exhibit outstanding recognition performance (i.e., what is visible?), they lack localization accuracy (i.e., where precisely is something located?). Therefore, additional processing steps have to be performed in order to obtain pixel-accurate segmentation masks at the full image resolution. To alleviate this problem we propose a novel ResNet-like architecture that exhibits strong localization and recognition performance. We combine multi-scale context with pixel-level accuracy by using two processing streams within our network: One stream carries information at the full image resolution, enabling precise adherence to segment boundaries. The other stream undergoes a sequence of pooling operations to obtain robust features for recognition. The two streams are coupled at the full image resolution using residuals. Without additional processing steps and without pre-training, our approach achieves an intersection-over-union score of 71.8% on the Cityscapes dataset.
Many real-world applications require artificial agents to compete and coordinate with other agents in complex environments. As a stepping stone to this goal, the domain of StarCraft has emerged as an ...important challenge for artificial intelligence research, owing to its iconic and enduring status among the most difficult professional esports and its relevance to the real world in terms of its raw complexity and multi-agent challenges. Over the course of a decade and numerous competitions
, the strongest agents have simplified important aspects of the game, utilized superhuman capabilities, or employed hand-crafted sub-systems
. Despite these advantages, no previous agent has come close to matching the overall skill of top StarCraft players. We chose to address the challenge of StarCraft using general-purpose learning methods that are in principle applicable to other complex domains: a multi-agent reinforcement learning algorithm that uses data from both human and agent games within a diverse league of continually adapting strategies and counter-strategies, each represented by deep neural networks
. We evaluated our agent, AlphaStar, in the full game of StarCraft II, through a series of online games against human players. AlphaStar was rated at Grandmaster level for all three StarCraft races and above 99.8% of officially ranked human players.
Semantic segmentation of modular furniture Pohlen, Tobias; Badami, Ishrat; Mathias, Markus ...
2016 IEEE Winter Conference on Applications of Computer Vision (WACV),
03/2016
Conference Proceeding
This paper proposes an approach for the semantic segmentation and structural parsing of modular furniture items, such as cabinets, wardrobes, and bookshelves, into so called interaction elements. ...Such a segmentation into functional units is challenging not only due to the visual similarity of the different elements but also because of their often uniformly colored and low-texture appearance. Our method addresses these challenges by merging structural and appearance likelihoods of each element and jointly optimizing over shape, relative location, and class labels using Markov Chain Monte Carlo (MCMC) sampling. We propose a novel concept called rectangle coverings which provides a tight bound on the number of structural elements and hence narrows down the search space. We evaluate our approach's performance on a novel dataset of furniture items and demonstrate its applicability in practice.
To solve complex real-world problems with reinforcement learning, we cannot rely on manually specified reward functions. Instead, we can have humans communicate an objective to the agent directly. In ...this work, we combine two approaches to learning from human feedback: expert demonstrations and trajectory preferences. We train a deep neural network to model the reward function and use its predicted reward to train an DQN-based deep reinforcement learning agent on 9 Atari games. Our approach beats the imitation learning baseline in 7 games and achieves strictly superhuman performance on 2 games without using game rewards. Additionally, we investigate the goodness of fit of the reward model, present some reward hacking problems, and study the effects of noise in the human labels.
Semantic image segmentation is an essential component of modern autonomous driving systems, as an accurate understanding of the surrounding scene is crucial to navigation and action planning. Current ...state-of-the-art approaches in semantic image segmentation rely on pre-trained networks that were initially developed for classifying images as a whole. While these networks exhibit outstanding recognition performance (i.e., what is visible?), they lack localization accuracy (i.e., where precisely is something located?). Therefore, additional processing steps have to be performed in order to obtain pixel-accurate segmentation masks at the full image resolution. To alleviate this problem we propose a novel ResNet-like architecture that exhibits strong localization and recognition performance. We combine multi-scale context with pixel-level accuracy by using two processing streams within our network: One stream carries information at the full image resolution, enabling precise adherence to segment boundaries. The other stream undergoes a sequence of pooling operations to obtain robust features for recognition. The two streams are coupled at the full image resolution using residuals. Without additional processing steps and without pre-training, our approach achieves an intersection-over-union score of 71.8% on the Cityscapes dataset.
Despite significant advances in the field of deep Reinforcement Learning (RL), today's algorithms still fail to learn human-level policies consistently over a set of diverse tasks such as Atari 2600 ...games. We identify three key challenges that any algorithm needs to master in order to perform well on all games: processing diverse reward distributions, reasoning over long time horizons, and exploring efficiently. In this paper, we propose an algorithm that addresses each of these challenges and is able to learn human-level policies on nearly all Atari games. A new transformed Bellman operator allows our algorithm to process rewards of varying densities and scales; an auxiliary temporal consistency loss allows us to train stably using a discount factor of \(\gamma = 0.999\) (instead of \(\gamma = 0.99\)) extending the effective planning horizon by an order of magnitude; and we ease the exploration problem by using human demonstrations that guide the agent towards rewarding states. When tested on a set of 42 Atari games, our algorithm exceeds the performance of an average human on 40 games using a common set of hyper parameters. Furthermore, it is the first deep RL algorithm to solve the first level of Montezuma's Revenge.
•The majority (75.3%) of patients with MTLE-HS remain refractory to 2 or more appropriate AED trials.•Newer AEDs are not more likely to control seizures in MTLE-HS than older AEDs.•Duration of ...epilepsy significantly correlates with number of AED trials in seizure free but not pharmacoresistant patients.
This study aims to evaluate the overall prognosis, prognostic factors, and efficacy of treatment in patients with mesial temporal lobe epilepsy with hippocampal sclerosis (MTLE-HS) who have access to third generation anti-epileptic drugs but not to epilepsy surgery. Eighty-five MTLE-HS patients were retrospectively placed into a seizure-free (seizure-free for >1year) or drug-resistant group, and the two groups were compared on the basis of age, sex, age at onset of seizures, duration of epilepsy, side of lesion, handedness, EEG findings, history of CNS infection, history of febrile convulsions, history of head trauma, history of cognitive impairment, family history of seizures, number of current anti-epileptic drugs (AEDs), total number of AED trials, and presence of individual AEDs. Only 24.7% of MTLE-HS patients had achieved seizure freedom for >1 year. Poor prognosis and drug-resistance were associated with younger age at onset of seizures (p=0.002), longer duration of epilepsy (p=0.018), greater number of current AEDs (p<0.001), and greater total number of AED trials (p<0.001). In addition, regimens with newer AEDs had no greater efficacy than regimens with older AEDs. Most medically managed MTLE-HS patients do not achieve seizure freedom despite multiple AED trials, and treatment with third generation AEDs should not preclude evaluation for epilepsy surgery.