ViewAL: Active Learning with Viewpoint Entropy for Semantic Segmentation. (arXiv:1911.11789v1 [cs.CV])

We propose ViewAL, a novel active learning strategy for semantic segmentation that exploits viewpoint consistency in multi-view datasets. Our core idea is that inconsistencies in model predictions across viewpoints provide a very reliable measure of uncertainty and encourage the model to perform well irrespective of the viewpoint under which objects are observed. To incorporate this…

A Preliminary Study of Disentanglement With Insights on the Inadequacy of Metrics. (arXiv:1911.11791v1 [cs.LG])

Disentangled encoding is an important step towards a better representation learning. However, despite the numerous efforts, there still is no clear winner that captures the independent features of the data in an unsupervised fashion. In this work we empirically evaluate the performance of six unsupervised disentanglement approaches on the mpi3d toy dataset curated and released…

A Quadratic Lower Bound for Algebraic Branching Programs. (arXiv:1911.11793v1 [cs.CC])

We show that any Algebraic Branching Program (ABP) computing the polynomial $\sum_{i = 1}^n x_i^n$ has at least $\Omega(n^2)$ vertices. This improves upon the lower bound of $\Omega(n\log n)$, which follows from the classical result of Baur and Strassen [Str73, BS83], and extends the results in [K19], which showed a quadratic lower bound for \emph{homogeneous}…

TimeCaps: Capturing Time Series Data with Capsule Networks. (arXiv:1911.11800v1 [cs.LG])

Capsule networks excel in understanding spatial relationships in 2D data for vision related tasks. Even though they are not designed to capture 1D temporal relationships, with TimeCaps we demonstrate that given the ability, capsule networks excel in understanding temporal relationships. To this end, we generate capsules along the temporal and channel dimensions creating two temporal…

Federated Learning for Ranking Browser History Suggestions. (arXiv:1911.11807v1 [cs.LG])

Federated Learning is a new subfield of machine learning that allows fitting models without collecting the training data itself. Instead of sharing data, users collaboratively train a model by only sending weight updates to a server. To improve the ranking of suggestions in the Firefox URL bar, we make use of Federated Learning to train…

Multi-Object Portion Tracking in 4D Fluorescence Microscopy Imagery with Deep Feature Maps. (arXiv:1911.11808v1 [eess.IV])

3D fluorescence microscopy of living organisms has increasingly become an essential and powerful tool in biomedical research and diagnosis. An exploding amount of imaging data has been collected, whereas efficient and effective computational tools to extract information from them are still lagging behind. This is largely due to the challenges in analyzing biological data. Interesting…

Local Model Poisoning Attacks to Byzantine-Robust Federated Learning. (arXiv:1911.11815v1 [cs.CR])

In federated learning, multiple client devices jointly learn a machine learning model: each client device maintains a local model for its local training dataset, while a master device maintains a global model via aggregating the local models from the client devices. The machine learning community recently proposed several federated learning methods that were claimed to…

GOOL: A Generic Object-Oriented Language (extended version). (arXiv:1911.11824v1 [cs.PL])

We present GOOL, a Generic Object-Oriented Language. It demonstrates that a language, with the right abstractions, can capture the essence of object-oriented programs. We show how GOOL programs can be used to generate human-readable, documented and idiomatic source code in multiple languages. Moreover, in GOOL, it is possible to express common programming idioms and patterns,…

Towards Fairness in Visual Recognition: Effective Strategies for Bias Mitigation. (arXiv:1911.11834v1 [cs.CV])

Computer vision models learn to perform a task by capturing relevant statistics from training data. It has been shown that models learn spurious age, gender, and race correlations when trained for seemingly unrelated tasks like activity recognition or image captioning. Various mitigation techniques have been presented to prevent models from utilizing or learning such biases.…