Search Results for author:
Found 19 papers, 4 papers with code
The Trifecta: Three simple techniques for training deeper Forward-Forward networks
Local learning, which focuses on updating subsets of a model's parameters at a time, has emerged as a promising technique to address these issues.
Considering Layerwise Importance in the Lottery Ticket Hypothesis
The Lottery Ticket Hypothesis (LTH) showed that by iteratively training a model, removing connections with the lowest global weight magnitude and rewinding the remaining connections, sparse networks can be extracted.
On The Coherence of Quantitative Evaluation of Visual Explanations
We complement our study with sanity checks on the studied evaluation methods as a means to investigate their reliability and the impact of characteristics of the explanations on the evaluation methods.
Deep set conditioned latent representations for action recognition
The proposed method achieves an improvement of around 1. 49% mAP in atomic action recognition and 17. 57% mAP in composite action recognition, over a I3D-NL baseline, on the CATER dataset.
Ranked #1 on
Atomic action recognition
on CATER
(using extra training data)
Towards Human-Understandable Visual Explanations: Human Imperceptible Cues Can Better Be Removed
Explainable AI (XAI) methods focus on explaining what a neural network has learned - in other words, identifying the features that are the most influential to the prediction.
MinMaxCAM: Improving object coverage for CAM-basedWeakly Supervised Object Localization
One of the most common problems of weakly supervised object localization is that of inaccurate object coverage.
Towards Human-Understandable Visual Explanations:Imperceptible High-frequency Cues Can Better Be Removed
Explainable AI (XAI) methods focus on explaining what a neural network has learned - in other words, identifying the features that are the most influential to the prediction.
Playing Atari with Capsule Networks: A systematic comparison of CNN and CapsNets-based agents.
In this paper, we conduct a systematic analysis to explore the potential of CapsNets-based agents in the deep reinforcement learning setting.
Can the state of relevant neurons in a deep neural networks serve as indicators for detecting adversarial attacks?
We present a method for adversarial attack detection based on the inspection of a sparse set of neurons.
Multiple Exemplars-based Hallucinationfor Face Super-resolution and Editing
Given a really low-resolution input image of a face (say 16x16 or 8x8 pixels), the goal of this paper is to reconstruct a high-resolution version thereof.
Information Compensation for Deep Conditional Generative Networks
In recent years, unsupervised/weakly-supervised conditional generative adversarial networks (GANs) have achieved many successes on the task of modeling and generating data.
In Defense of LSTMs for Addressing Multiple Instance Learning Problems
LSTMs have a proven track record in analyzing sequential data.
An Unpaired Shape Transforming Method for Image Translation and Cross-Domain Retrieval
We address the problem of unpaired geometric image-to-image translation.
Visual Explanation by Interpretation: Improving Visual Feedback Capabilities of Deep Neural Networks
In this paper, we propose a novel scheme for both interpretation as well as explanation in which, given a pretrained model, we automatically identify internal features relevant for the set of classes considered by the model, without relying on additional annotations.
An Analysis of Human-centered Geolocation
Experiments on the Fashion 144k and a Pinterest-based dataset show that the automatic methods succeed at this task to a reasonable extent.
Context-based Object Viewpoint Estimation: A 2D Relational Approach
To estimate the viewpoint (or pose) of an object, people have mostly looked at object intrinsic features, such as shape or appearance.
Reasoning about Body-Parts Relations for Sign Language Recognition
Over the years, hand gesture recognition has been mostly addressed considering hand trajectories in isolation.
Modeling Visual Compatibility through Hierarchical Mid-level Elements
At the base-level, our method identifies patterns of CNN activations with the aim of modeling different variations/styles in which objects of the classes of interest may occur.
Rank Pooling for Action Recognition
We show how the parameters of a function that has been fit to the video data can serve as a robust new video representation.
