Search Results for author:
Found 11 papers, 0 papers with code
On Deep Neural Network Calibration by Regularization and its Impact on Refinement
We find that many calibration approaches with the likes of label smoothing, mixup etc.
Exploring Target Driven Image Classification
We argue that, for any arbitrary category $\mathit{\tilde{y}}$, the composed question 'Is this image of an object category $\mathit{\tilde{y}}$' serves as a viable approach for image classification via.
Assessing The Importance Of Colours For CNNs In Object Recognition
In this paper, we empirically investigate the importance of colours in object recognition for CNNs.
Filtering Point Targets via Online Learning of Motion Models
Filtering point targets in highly cluttered and noisy data frames can be very challenging, especially for complex target motions.
Real-time tracker with fast recovery from target loss
When the confidence is low, we avoid updating the object's position through the feature map; instead, the tracker passes to a single-frame failure mode, during which the patch's low-level visual content is used to swiftly update the object's position, before recovering from the target loss in the next frame.
Convolutional Recurrent Predictor: Implicit Representation for Multi-target Filtering and Tracking
Defining a multi-target motion model, which is an important step of tracking algorithms, can be very challenging.
Hide and Seek tracker: Real-time recovery from target loss
In the case of a low confidence, the position update is rejected and the tracker passes to a single-frame failure mode, during which the patch low-level visual content is used to swiftly update the object position, before recovering from the target loss in the next frame.
Deep Recurrent Neural Network for Multi-target Filtering
This paper addresses the problem of fixed motion and measurement models for multi-target filtering using an adaptive learning framework.
GeoSeq2Seq: Information Geometric Sequence-to-Sequence Networks
The Fisher information metric is an important foundation of information geometry, wherein it allows us to approximate the local geometry of a probability distribution.
StackSeq2Seq: Dual Encoder Seq2Seq Recurrent Networks
A widely studied non-deterministic polynomial time (NP) hard problem lies in finding a route between the two nodes of a graph.
Approximating meta-heuristics with homotopic recurrent neural networks
We show the viability of recurrent neural network solutions on a graph that has over 300 nodes and argue that a sequence-to-sequence network rather than other recurrent networks has improved approximation quality.
