Deep Learning
CAPro: Webly Supervised Learning with Cross-Modality Aligned Prototypes Y ulei Qin 1 Xingyu Chen
For instance, web images retrieved with queries of " tiger cat " (a cat species) and " drumstick " (a musical instrument) are almost dominated by images of tigers and
Weakly Supervised 3D Open-vocabulary Segmentation
Given the super-rich semantics in 3D scenes, a crucial aspect of this task is achieving open-vocabulary segmentation that can handle regions and objects of various semantics including those with long-tail distributions.
A Benchmark Task Details
In the United States, health insurance is a critical component of individuals' ability to access health care.
Im-Promptu: In-Context Composition from Image Prompts
In this work, we investigate whether analogical reasoning can enable in-context composition over composable elements of visual stimuli.
Sample-Efficient and Safe Deep Reinforcement Learning via Reset Deep Ensemble Agents
We show that the proposed method significantly improves the performance of the baseline algorithm in the considered environments.
Module-wise Training of Neural Networks via the Minimizing Movement Scheme Anonymous Author(s) Affiliation Address email
End-to-end backpropagation is the standard training method of neural networks.
Module-wise Training of Neural Networks via the Minimizing Movement Scheme
End-to-end backpropagation is the standard training method of neural networks.