Search Results for author:
Found 12 papers, 7 papers with code
Maximally Compact and Separated Features with Regular Polytope Networks
Convolutional Neural Networks (CNNs) trained with the Softmax loss are widely used classification models for several vision tasks.
CL2R: Compatible Lifelong Learning Representations
We identify stationarity as the property that the feature representation is required to hold to achieve compatibility and propose a novel training procedure that encourages local and global stationarity on the learned representation.
Contrastive Supervised Distillation for Continual Representation Learning
In this paper, we propose a novel training procedure for the continual representation learning problem in which a neural network model is sequentially learned to alleviate catastrophic forgetting in visual search tasks.
CoReS: Compatible Representations via Stationarity
Compatible features enable the direct comparison of old and new learned features allowing to use them interchangeably over time.
Fine-Grained Adversarial Semi-supervised Learning
Our approach leverages unlabeled data with an adversarial optimization strategy in which the internal features representation is obtained with a second-order pooling model.
Regular Polytope Networks
Typically, a learnable transformation (i. e. the classifier) is placed at the end of such models returning a value for each class used for classification.
Temporal Binary Representation for Event-Based Action Recognition
In this paper we present an event aggregation strategy to convert the output of an event camera into frames processable by traditional Computer Vision algorithms.
Ranked #3 on
Gesture Recognition
on DVS128 Gesture
(using extra training data)
Class-incremental Learning with Pre-allocated Fixed Classifiers
Contrarily to the standard expanding classifier, this allows: (a) the output nodes of future unseen classes to firstly see negative samples since the beginning of learning together with the positive samples that incrementally arrive; (b) to learn features that do not change their geometric configuration as novel classes are incorporated in the learning model.
Fix Your Features: Stationary and Maximally Discriminative Embeddings using Regular Polytope (Fixed Classifier) Networks
Typically, a learnable transformation (i. e. the classifier) is placed at the end of such models returning a value for each class used for classification.
Memory Based Online Learning of Deep Representations from Video Streams
It is shown that the proposed learning procedure is asymptotically stable and can be effectively used in relevant applications like multiple face identification and tracking from unconstrained video streams.
Unsupervised Incremental Learning of Deep Descriptors From Video Streams
We present a novel unsupervised method for face identity learning from video sequences.
Continuous Localization and Mapping of a Pan Tilt Zoom Camera for Wide Area Tracking
Pan-tilt-zoom (PTZ) cameras are powerful to support object identification and recognition in far-field scenes.
