BIFRNet: A Brain-Inspired Feature Restoration DNN for Partially Occluded Image Recognition
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.
Code (1)
Similar Papers 제목 키워드 기반
GraLoD: Graphics-Inspired Continuous Level-of-Detail Learning for Image Restoration
The spatial support required for image restoration varies across degradation types, image regions, and reconstruction stages. However, most existing methods rely on predefined multi-scale hierarchies and aggregate featur…
Image RestorationDISYRE: Diffusion-Inspired SYnthetic REstoration for Unsupervised Anomaly Detection
Unsupervised Anomaly Detection (UAD) techniques aim to identify and localize anomalies without relying on annotations, only leveraging a model trained on a dataset known to be free of anomalies. Diffusion models learn to…
Anomaly DetectionUnsupervised Anomaly DetectionSpikingBrain: Spiking Brain-inspired Large Models
Mainstream Transformer-based large language models face major efficiency bottlenecks: training computation scales quadratically with sequence length, and inference memory grows linearly, limiting long-context processing.…
RAN4IQA: Restorative Adversarial Nets for No-Reference Image Quality Assessment
Inspired by the free-energy brain theory, which implies that human visual system (HVS) tends to reduce uncertainty and restore perceptual details upon seeing a distorted image, we propose restorative adversarial net (RAN…
Image Quality AssessmentNo-Reference Image Quality AssessmentNR-IQAPerceptual DistancePhysically Interpretable Multi-Degradation Image Restoration via Deep Unfolding and Explainable Convolution
Although image restoration has advanced significantly, most existing methods target only a single type of degradation. In real-world scenarios, images often contain multiple degradations simultaneously, such as rain, noi…
Image Restoration