Collaborating Authors

SAND: Semi-Supervised Adaptive Novel Class Detection and Classification over Data Stream

AAAI Conferences

Most approaches to classifying data streams either divide the stream into fixed-size chunks or use gradual forgetting. Due to evolving nature of data streams, finding a proper size or choosing a forgetting rate without prior knowledge about time-scale of change is not a trivial task. These approaches hence suffer from a trade-off between performance and sensitivity. Existing dynamic sliding window based approaches address this problem by tracking changes in classifier error rate, but are supervised in nature. We propose an efficient semi-supervised framework in this paper which uses change detection on classifier confidence to detect concept drifts, and to determine chunk boundaries dynamically. It also addresses concept evolution problem by detecting outliers having strong cohesion among themselves. Experiment results on benchmark and synthetic data sets show effectiveness of the proposed approach.

Streaming Classification with Emerging New Class by Class Matrix Sketching

AAAI Conferences

Streaming classification with emerging new class is an important problem of great research challenge and practical value. In many real applications, the task often needs to handle large matrices issues such as textual data in the bag-of-words model and large-scale image analysis. However, the methodologies and approaches adopted by the existing solutions, most of which involve massive distance calculation, have so far fallen short of successfully addressing a real-time requested task. In this paper, the proposed method dynamically maintains two low-dimensional matrix sketches to 1) detect emerging new classes; 2) classify known classes; and 3) update the model in the data stream. The update efficiency is superior to the existing methods. The empirical evaluation shows the proposed method not only receives the comparable performance but also strengthens modelling on large-scale data sets.

Incremental Few-Shot Learning with Attention Attractor Networks

Neural Information Processing Systems

Machine learning classifiers are often trained to recognize a set of pre-defined classes. However, in many applications, it is often desirable to have the flexibility of learning additional concepts, with limited data and without re-training on the full training set. This paper addresses this problem, incremental few-shot learning, where a regular classification network has already been trained to recognize a set of base classes, and several extra novel classes are being considered, each with only a few labeled examples. After learning the novel classes, the model is then evaluated on the overall classification performance on both base and novel classes. To this end, we propose a meta-learning model, the Attention Attractor Network, which regularizes the learning of novel classes.

Robust Anomaly Detection in Images using Adversarial Autoencoders Machine Learning

Reliably detecting anomalies in a given set of images is a task of high practical relevance for visual quality inspection, surveillance, or medical image analysis. Autoencoder neural networks learn to reconstruct normal images, and hence can classify those images as anomalies, where the reconstruction error exceeds some threshold. Here we analyze a fundamental problem of this approach when the training set is contaminated with a small fraction of outliers. We find that continued training of autoencoders inevitably reduces the reconstruction error of outliers, and hence degrades the anomaly detection performance. In order to counteract this effect, an adversarial autoencoder architecture is adapted, which imposes a prior distribution on the latent representation, typically placing anomalies into low likelihood-regions. Utilizing the likelihood model, potential anomalies can be identified and rejected already during training, which results in an anomaly detector that is significantly more robust to the presence of outliers during training.

Transfer Learning in a Transductive Setting

Neural Information Processing Systems

Category models for objects or activities typically rely on supervised learning requiring sufficiently large training sets. Transferring knowledge from known categories to novel classes with no or only a few labels however is far less researched even though it is a common scenario. In this work, we extend transfer learning with semi-supervised learning to exploit unlabeled instances of (novel) categories with no or only a few labeled instances. Our proposed approach Propagated Semantic Transfer combines three main ingredients. First, we transfer information from known to novel categories by incorporating external knowledge, such as linguistic or expert-specified information, e.g., by a mid-level layer of semantic attributes.