BIFRNet: A Brain-Inspired Feature Restoration DNN for Partially Occluded Image Recognition
Not on the map. Why?
Abstract (arXiv)
The partially occluded image recognition (POIR) problem has been a challenge for artificial intelligence for a long time. A common strategy to handle the POIR problem is using the non-occluded features for classification. Unfortunately, this strategy will lose effectiveness when the image is severely occluded, since the visible parts can only provide limited information. Several studies in neuroscience reveal that feature restoration which fills in the occluded information and is called amodal completion is essential for human brains to recognize partially occluded images. However, feature restoration is commonly ignored by CNNs, which may be the reason why CNNs are ineffective for the POIR problem. Inspired by this, we propose a novel brain-inspired feature restoration network (BIFRNet) to solve the POIR problem. It mimics a ventral visual pathway to extract image features and a dorsal visual pathway to distinguish occluded and visible image regions. In addition, it also uses a knowledge module to store object prior knowledge and uses a completion module to restore occluded features based on visible features and prior knowledge. Thorough experiments on synthetic and real-world occluded image datasets show that BIFRNet outperforms the existing methods in solving the POIR problem. Especially for severely occluded images, BIRFRNet surpasses other methods by a large margin and is close to the human brain performance. Furthermore, the brain-inspired design makes BIFRNet more interpretable.
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 21 of its 52 references that are in the map. First posted on arXiv 2 Mar 2023.
Builds on
21 of 52 references.
References · 21
- 2015Deep Residual Learning for Image Recognitioncited by 52,096
- 2014Adam: A Method for Stochastic Optimizationcited by 37,240
- 2014Microsoft COCO: Common Objects in Contextcited by 17,608
- 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,364
- 2016Layer Normalizationcited by 5,669
- 2019CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Featurescited by 2,884
- 2017Improved Regularization of Convolutional Neural Networks with Cutoutcited by 1,628
- 2015Convolutional LSTM Network: A Machine Learning Approach for Precipitation Nowcastingcited by 1,436
- 2018Generative Image Inpainting with Contextual Attentioncited by 580
- 2018Deep Face Recognition: A Surveycited by 276
- 2021Deep Occlusion-Aware Instance Segmentation with Overlapping BiLayerscited by 104
- 2019Occlusion Robust Face Recognition Based on Mask Learning with PairwiseDifferential Siamese Networkcited by 51
9 more
- 2019Mask-Guided Attention Network for Occluded Pedestrian Detectioncited by 36
- 2017Comparing deep neural networks against humans: object recognition when the signal gets weakercited by 34
- 2019Combining Compositional Models and Deep Networks For Robust Object Classification under Occlusioncited by 24
- 2021End2End Occluded Face Recognition by Masking Corrupted Featurescited by 24
- 2021Capturing the objects of vision with neural networkscited by 21
- 2019Face De-occlusion using 3D Morphable Model and Generative Adversarial Networkcited by 11
- 2017Detecting Semantic Parts on Partially Occluded Objectscited by 6
- 2016Towards Deep Compositional Networkscited by 3
- 2020SD-GAN: Structural and Denoising GAN reveals facial parts under occlusioncited by 1
Built on by
Citing papers per year: 2023: 1.
1 paper.