Distorted Representation Space Characterization Through Backpropagated Gradients

Kwon, Gukyeong; Prabhushankar, Mohit; Temel, Dogancan; AlRegib, Ghassan

doi:10.1109/icip.2019.8803228

Cited by 20 publications

(15 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…With the other steps remaining the same, a contrast-importance score α c k weighted contrast mask is given by C = ReLU ( K k=1 α c k A k ) for predicted and contrast classes P and Q. Note that gradients are used as features in multiple works including [20,21,22].…”

Section: Background and Related Workmentioning

confidence: 99%

Extracting Causal Visual Features for Limited label Classification

Prabhushankar¹,

AlRegib²

2021

Preprint

Self Cite

View full text Add to dashboard Cite

Neural networks trained to classify images do so by identifying features that allow them to distinguish between classes. These sets of features are either causal or context dependent. Grad-CAM is a popular method of visualizing both sets of features. In this paper, we formalize this feature divide and provide a methodology to extract causal features from Grad-CAM. We do so by defining context features as those features that allow contrast between predicted class and any contrast class. We then apply a set theoretic approach to separate causal from contrast features for COVID-19 CT scans. We show that on average, the image regions with the proposed causal features require 15% less bits when encoded using Huffman encoding, compared to Grad-CAM, for an average increase of 3% classification accuracy, over Grad-CAM. Moreover, we validate the transfer-ability of causal features between networks and comment on the non-human interpretable causal nature of current networks.

show abstract

Section: Background and Related Workmentioning

confidence: 99%

Extracting Causal Visual Features for Limited label Classification

Prabhushankar¹,

AlRegib²

2021

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…The authors in [3], [2] characterize information encoded in the neural network and utilize Fisher information to represent tasks. In [15], the gradients of the neural network are utilized to classify distorted images and objectively estimate the quality of them. The gradients have been also studied as a local liner approximation to a neural network [19].…”

Section: Backpropagated Gradientsmentioning

confidence: 99%

Backpropagated Gradient Representations for Anomaly Detection

Kwon

Prabhushankar

Temel

et al. 2020

Lecture Notes in Computer Science

Self Cite

View full text Add to dashboard Cite

Learning representations that clearly distinguish between normal and abnormal data is key to the success of anomaly detection. Most of existing anomaly detection algorithms use activation representations from forward propagation while not exploiting gradients from backpropagation to characterize data. Gradients capture model updates required to represent data. Anomalies require more drastic model updates to fully represent them compared to normal data. Hence, we propose the utilization of backpropagated gradients as representations to characterize model behavior on anomalies and, consequently, detect such anomalies. We show that the proposed method using gradient-based representations achieves state-of-the-art anomaly detection performance in benchmark image recognition datasets. Also, we highlight the computational efficiency and the simplicity of the proposed method in comparison with other state-of-the-art methods relying on adversarial networks or autoregressive models, which require at least 27 times more model parameters than the proposed method.

show abstract

“…On contrary to adversarial studies in the literature that require model information to design input images, we designed challenging conditions independent of the detection algorithms, which enables a black-box performance assessment. Previously, we performed black-box assessment of object detection APIs with realistic challenging conditions in [22,23], and investigated the robustness and out-of-distribution classification performance of traffic sign classifiers in [24,25].…”

Section: Traffic Sign Detection Under Challenging Conditions: a Deepementioning

confidence: 99%

Traffic Sign Detection Under Challenging Conditions: A Deeper Look into Performance Variations and Spectral Characteristics

Temel

Chen

AlRegib

2020

IEEE Trans. Intell. Transport. Syst.

Self Cite

View full text Add to dashboard Cite

Traffic signs are critical for maintaining the safety and efficiency of our roads. Therefore, we need to carefully assess the capabilities and limitations of automated traffic sign detection systems. Existing traffic sign datasets are limited in terms of type and severity of challenging conditions. Metadata corresponding to these conditions are unavailable and it is not possible to investigate the effect of a single factor because of simultaneous changes in numerous conditions. To overcome the shortcomings in existing datasets, we introduced the CURE-TSD-Real dataset, which is based on simulated challenging conditions that correspond to adversaries that can occur in real-world environments and systems. We test the performance of two benchmark algorithms and show that severe conditions can result in an average performance degradation of 29% in precision and 68% in recall. We investigate the effect of challenging conditions through spectral analysis and show that challenging conditions can lead to distinct magnitude spectrum characteristics. Moreover, we show that mean magnitude spectrum of changes in video sequences under challenging conditions can be an indicator of detection performance. CURE-TSD-Real dataset is available online at https://github.com/olivesgatech/CURE-TSD.

show abstract

Distorted Representation Space Characterization Through Backpropagated Gradients

Cited by 20 publications

References 24 publications

Extracting Causal Visual Features for Limited label Classification

Extracting Causal Visual Features for Limited label Classification

Backpropagated Gradient Representations for Anomaly Detection

Traffic Sign Detection Under Challenging Conditions: A Deeper Look into Performance Variations and Spectral Characteristics

Contact Info

Product

Resources

About