Zobrazeno 1 - 10
of 66
pro vyhledávání: '"Sasaki, Tomotake"'
Autor:
Rahimi, Amir, D'Amario, Vanessa, Yamada, Moyuru, Takemoto, Kentaro, Sasaki, Tomotake, Boix, Xavier
Systematic generalization is a crucial aspect of intelligence, which refers to the ability to generalize to novel tasks by combining known subtasks and concepts. One critical factor that has been shown to influence systematic generalization is the di
Externí odkaz:
http://arxiv.org/abs/2309.08798
By default neural networks are not robust to changes in data distribution. This has been demonstrated with simple image corruptions, such as blurring or adding noise, degrading image classification performance. Many methods have been proposed to miti
Externí odkaz:
http://arxiv.org/abs/2306.09005
Human-Object Interaction (HOI) detection is a task to localize humans and objects in an image and predict the interactions in human-object pairs. In real-world scenarios, HOI detection models need systematic generalization, i.e., generalization to no
Externí odkaz:
http://arxiv.org/abs/2305.09948
Deep Neural Networks (DNNs) often fail in out-of-distribution scenarios. In this paper, we introduce a tool to visualize and understand such failures. We draw inspiration from concepts from neural electrophysiology, which are based on inspecting the
Externí odkaz:
http://arxiv.org/abs/2303.11912
Recent rapid developments in reinforcement learning algorithms have been giving us novel possibilities in many fields. However, due to their exploring property, we have to take the risk into consideration when we apply those algorithms to safety-crit
Externí odkaz:
http://arxiv.org/abs/2209.15452
Transformers achieve great performance on Visual Question Answering (VQA). However, their systematic generalization capabilities, i.e., handling novel combinations of known concepts, is unclear. We reveal that Neural Module Networks (NMNs), i.e., que
Externí odkaz:
http://arxiv.org/abs/2201.11316
Autor:
Villalobos, Kimberly, Štih, Vilim, Ahmadinejad, Amineh, Sundaram, Shobhita, Dozier, Jamell, Francl, Andrew, Azevedo, Frederico, Sasaki, Tomotake, Boix, Xavier
Publikováno v:
Neural Computation 33 (2021) 2511-2549
The insideness problem is an aspect of image segmentation that consists of determining which pixels are inside and outside a region. Deep Neural Networks (DNNs) excel in segmentation benchmarks, but it is unclear if they have the ability to solve the
Externí odkaz:
http://arxiv.org/abs/2201.10664
Symmetry is omnipresent in nature and perceived by the visual system of many species, as it facilitates detecting ecologically important classes of objects in our environment. Symmetry perception requires abstraction of long-range spatial dependencie
Externí odkaz:
http://arxiv.org/abs/2112.04162
Autor:
Sakai, Akira, Sunagawa, Taro, Madan, Spandan, Suzuki, Kanata, Katoh, Takashi, Kobashi, Hiromichi, Pfister, Hanspeter, Sinha, Pawan, Boix, Xavier, Sasaki, Tomotake
The training data distribution is often biased towards objects in certain orientations and illumination conditions. While humans have a remarkable capability of recognizing objects in out-of-distribution (OoD) orientations and illuminations, Deep Neu
Externí odkaz:
http://arxiv.org/abs/2111.00131
Stream-based active learning (AL) is an efficient training data collection method, and it is used to reduce human annotation cost required in machine learning. However, it is difficult to say that the human cost is low enough because most previous st
Externí odkaz:
http://arxiv.org/abs/2110.00947