Paper Reading AI Learner

What Do Deep Nets Learn? Class-wise Patterns Revealed in the Input Space

2021-01-18 06:38:41
Shihao Zhao, Xingjun Ma, Yisen Wang, James Bailey, Bo Li, Yu-Gang Jiang

Abstract

Deep neural networks (DNNs) have been widely adopted in different applications to achieve state-of-the-art performance. However, they are often applied as a black box with limited understanding of what the model has learned from the data. In this paper, we focus on image classification and propose a method to visualize and understand the class-wise patterns learned by DNNs trained under three different settings including natural, backdoored and adversarial. Different from existing class-wise deep representation visualizations, our method searches for a single predictive pattern in the input (i.e. pixel) space for each class. Based on the proposed method, we show that DNNs trained on natural (clean) data learn abstract shapes along with some texture, and backdoored models learn a small but highly predictive pattern for the backdoor target class. Interestingly, the existence of class-wise predictive patterns in the input space indicates that even DNNs trained on clean data can have backdoors, and the class-wise patterns identified by our method can be readily applied to "backdoor" attack the model. In the adversarial setting, we show that adversarially trained models learn more simplified shape patterns. Our method can serve as a useful tool to better understand DNNs trained on different datasets under different settings.

Abstract (translated)

URL

https://arxiv.org/abs/2101.06898

PDF

https://arxiv.org/pdf/2101.06898.pdf


Tags
3D Action Action_Localization Action_Recognition Activity Adversarial Agent Attention Autonomous Bert Boundary_Detection Caption Chat Classification CNN Compressive_Sensing Contour Contrastive_Learning Deep_Learning Denoising Detection Dialog Diffusion Drone Dynamic_Memory_Network Edge_Detection Embedding Embodied Emotion Enhancement Face Face_Detection Face_Recognition Facial_Landmark Few-Shot Gait_Recognition GAN Gaze_Estimation Gesture Gradient_Descent Handwriting Human_Parsing Image_Caption Image_Classification Image_Compression Image_Enhancement Image_Generation Image_Matting Image_Retrieval Inference Inpainting Intelligent_Chip Knowledge Knowledge_Graph Language_Model Matching Medical Memory_Networks Multi_Modal Multi_Task NAS NMT Object_Detection Object_Tracking OCR Ontology Optical_Character Optical_Flow Optimization Person_Re-identification Point_Cloud Portrait_Generation Pose Pose_Estimation Prediction QA Quantitative Quantitative_Finance Quantization Re-identification Recognition Recommendation Reconstruction Regularization Reinforcement_Learning Relation Relation_Extraction Represenation Represenation_Learning Restoration Review RNN Salient Scene_Classification Scene_Generation Scene_Parsing Scene_Text Segmentation Self-Supervised Semantic_Instance_Segmentation Semantic_Segmentation Semi_Global Semi_Supervised Sence_graph Sentiment Sentiment_Classification Sketch SLAM Sparse Speech Speech_Recognition Style_Transfer Summarization Super_Resolution Surveillance Survey Text_Classification Text_Generation Tracking Transfer_Learning Transformer Unsupervised Video_Caption Video_Classification Video_Indexing Video_Prediction Video_Retrieval Visual_Relation VQA Weakly_Supervised Zero-Shot