Graph convolutional label noise cleaner: Train a plug-and-play action classifier for anomaly detection
JX Zhong, N Li, W Kong, S Liu… - Proceedings of the …, 2019 - openaccess.thecvf.com
Video anomaly detection under weak labels is formulated as a typical multiple-instance
learning problem in previous works. In this paper, we provide a new perspective, ie, a …
learning problem in previous works. In this paper, we provide a new perspective, ie, a …
Multiple instance learning: A survey of problem characteristics and applications
Multiple instance learning (MIL) is a form of weakly supervised learning where training
instances are arranged in sets, called bags, and a label is provided for the entire bag. This …
instances are arranged in sets, called bags, and a label is provided for the entire bag. This …
Classification with asymmetric label noise: Consistency and maximal denoising
In many real-world classification problems, the labels of training examples are randomly
corrupted. Thus, the set of training examples for each class is contaminated by examples of …
corrupted. Thus, the set of training examples for each class is contaminated by examples of …
All grains, one scheme (AGOS): Learning multigrain instance representation for aerial scene classification
Aerial scene classification remains challenging as: 1) the size of key objects in determining
the scene scheme varies greatly and 2) many objects irrelevant to the scene scheme are …
the scene scheme varies greatly and 2) many objects irrelevant to the scene scheme are …
Learning theory for distribution regression
We focus on the distribution regression problem: regressing to vector-valued outputs from
probability measures. Many important machine learning and statistical tasks fit into this …
probability measures. Many important machine learning and statistical tasks fit into this …
A theoretical and empirical analysis of support vector machine methods for multiple-instance classification
The standard support vector machine (SVM) formulation, widely used for supervised
learning, possesses several intuitive and desirable properties. In particular, it is convex and …
learning, possesses several intuitive and desirable properties. In particular, it is convex and …
Multiple instance learning for efficient sequential data classification on resource-constrained devices
D Dennis, C Pabbaraju… - Advances in Neural …, 2018 - proceedings.neurips.cc
We study the problem of fast and efficient classification of sequential data (such as time-
series) on tiny devices, which is critical for various IoT related applications like audio …
series) on tiny devices, which is critical for various IoT related applications like audio …
Algorithms and hardness for learning linear thresholds from label proportions
R Saket - Advances in Neural Information Processing …, 2022 - proceedings.neurips.cc
We study the learnability of linear threshold functions (LTFs) in the learning from label
proportions (LLP) framework. In this, the feature-vector classifier is learnt from bags of …
proportions (LLP) framework. In this, the feature-vector classifier is learnt from bags of …
Learning neural networks with two nonlinear layers in polynomial time
S Goel, AR Klivans - Conference on Learning Theory, 2019 - proceedings.mlr.press
We give a polynomial-time algorithm for learning neural networks with one layer of sigmoids
feeding into any Lipschitz, monotone activation function (eg, sigmoid or ReLU). The …
feeding into any Lipschitz, monotone activation function (eg, sigmoid or ReLU). The …
An efficient and provable approach for mixture proportion estimation using linear independence assumption
In this paper, we study the mixture proportion estimation (MPE) problem in a new setting:
given samples from the mixture and the component distributions, we identify the proportions …
given samples from the mixture and the component distributions, we identify the proportions …