Are deep video architectures (also) biased toward texture rather than shape?
Convolutional neural networks (CNNs) have achieved high accuracy on several different perceptual tasks, such as object recognition and action recognition. Interpretability is required due to the significant impact of CNNs and the requirement of model improvement. Geirhos et al. suggested that ImageN...
Main Author: | Li, Boyu |
---|---|
Format: | Others |
Language: | English |
Published: |
KTH, Skolan för elektroteknik och datavetenskap (EECS)
2021
|
Subjects: | |
Online Access: | http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-304892 |
Similar Items
-
Video Saliency Detection using Deep Learning
by: Wiesinger, Jakob
Published: (2019) -
Batch Active Learning for Deep Object Detection in Videos
by: Matosevic, Antonio
Published: (2021) -
A performance-driven SoC architecture for video synthesis
by: BOURDEAUDUCQ, SÉBASTIEN
Published: (2010) -
Is QUIC a Better Choice than TCP in the 5G Core Network Service Based Architecture?
by: Gärdborn, Pethrus
Published: (2020) -
One-Shot Neural Architecture Search for Deep Multi-Task Learning in Computer Vision
by: Silvestri, Gianluigi
Published: (2020)