• Publications
  • Influence
Facial Attributes Classification Using Multi-task Representation Learning
TLDR
This paper presents a new approach for facial attribute classification using a multi-task learning approach that learns a shared feature representation that is wellsuited for multiple attribute classification and shows superior classification performance improvement over the state-of-the-art. Expand
Quantization Guided JPEG Artifact Correction
TLDR
This work creates a novel architecture which is parameterized by the JPEG files quantization matrix, which allows a single model to achieve state-of-the-art performance over models trained for specific quality settings. Expand
Deep Residual Learning in the JPEG Transform Domain
  • Max Ehrlich, L. Davis
  • Computer Science, Mathematics
  • IEEE/CVF International Conference on Computer…
  • 31 December 2018
TLDR
A general method of performing Residual Network inference and learning in the JPEG transform domain that allows the network to consume compressed images as input and shows that the sparsity of the JPEG format allows for faster processing of images with little to no penalty in the network accuracy. Expand
Stacked U-Nets for Ground Material Segmentation in Remote Sensing Imagery
TLDR
A semantic segmentation algorithm for RGB remote sensing images based on the Dilated Stacked U-Nets architecture that gives competitive results on the DeepGlobe dataset is presented. Expand
Action-Affect-Gender Classification Using Multi-task Representation Learning
TLDR
This work proposes a new model that enhances the CRBM model with a factored multi-task component that enables scaling over larger number of classes without increasing the number of parameters. Expand
Analyzing and Mitigating Compression Defects in Deep Learning
TLDR
It is shown that there is a significant penalty on common performance metrics for high compression, and several methods are tested for mitigating this penalty, including a novel method based on artifact correction which requires no labels to train. Expand
Action-Affect Classification and Morphing using Multi-Task Representation Learning
TLDR
This work proposes a new model that enhances the CRBM model with a factored multi-task component to become Multi-Task Conditional Restricted Boltzmann Machines (MTCRBMs), and shows superior classification performance improvement over the state-of-the-art, as well as the generative abilities of the model. Expand
Analyzing and Mitigating JPEG Compression Defects in Deep Learning
TLDR
It is shown that there is a significant penalty on common performance metrics for high compression, and several methods are tested for mitigating this penalty, including a novel method based on artifact correction which requires no labels to train. Expand
A Frequency Perspective of Adversarial Robustness
TLDR
This analysis shows that adversarial examples are neither in high-frequency nor in low-frequency components, but are simply dataset dependent, and proposes a frequency-based explanation for the commonly observed accuracy vs. robustness trade-off. Expand
Interpretable Automated Diagnosis of Retinal Disease using Deep OCT Analysis
TLDR
This work developed a CNN-based model for accurate classification of CNV, DME, Drusen, and Normal OCT scans and placed an emphasis on producing both qualitative and quantitative explanations of the model’s decisions. Expand
...
1
2
...