[ACCV22] Visual Explanation Generation Based on Lambda Attention Branch Networks

Transcript

1. Tsumugi Iida1 Takumi Komatsu1 Kanta Kaneda1 Tsubasa Hirakawa2 Takayoshi Yamashita2 Hironobu Fujiyoshi2 Komei Sugiura1 1. Keio University 2. Chubu University Visual Explanation Generation Based on Lambda Attention Branch Networks
2. 1 Visual explanations for deep neural networks are important in terms of ・Enhancing accountability (e.g., health care) ・Providing scientific insight to experts (e.g., solar flare) 1 Magnetogram Visual explanation Introduction: Visual explanations can provide insights into unexplained phenomena
3. 1 Visual explanations for deep neural networks are important in terms of ・Enhancing accountability (e.g., health care) ・Providing scientific insight to experts (e.g., solar flare) 1 Magnetogram Visual explanation Introduction: Visual explanations can provide insights into unexplained phenomena
4. Problem Statement: Visual explanation generation for classification problem 2 Input: • Image 𝒙 ∈ ℝ!×#×$ Outputs: • Predicted class • Visual explanation • Attention map: 𝜶 ∈ ℝ%×#×$ Visual Explanation IDRiD Important Regions Unimportant Regions
5. Related Works: Explanation generation for transformers has not been fully established 3 Attention Branch Network [Fukui+, CVPR19] Generate explanation of CNN by branch structures Attention Rollout [Abnar+, 20] Explanation generation method chained with transformer attention Standard explanation generation method for transformers [Petsiuk+, BMCV18] Generic method for explanation generation (RiSE) Proposed a standard metric: Insertion-Deletion score (ID) Problem • Visual explanations for Lambda-based transformers has not been established • ID is inappropriate for images with sparse important regions Generic image Sparse image
6. 4 Lambda Layer • Compatible with CNNs • Captures a wide range of relationships with less computation than ViT ViT Lambda Related Works: Lambda Networks[Bello+, ICLR21]
7. 4 Lambda Layer 画像特化したtransformer ViTより少ない計算量で 全ピクセル間の関係を取得可能 Apply convolution to 𝒉 to generate query, key, value 𝑄 = Conv 𝒉 , 𝑉 = Conv(𝒉) 𝐾 = Softmax Conv 𝒉 Apply convolution to value to generate 𝝀! Compute the product of key and value to generate 𝝀" 𝝀! = Conv 𝑉 , 𝝀" = 𝐾#𝑉 Compute output 𝒉$ by the following equation: 𝒉$ = 𝝀! + 𝝀" # 𝑄 Related Works: Lambda Networks[Bello+, ICLR21]
8. 4 Lambda Layer 画像特化したtransformer ViTより少ない計算量で 全ピクセル間の関係を取得可能 𝝀! = Conv 𝑉 , 𝝀" = 𝐾#𝑉 𝒉$ = 𝝀! + 𝝀" # 𝑄 𝝀& : Compressed 𝑄 ◦Explanation generation strategy 1. Visualize 𝝀& 2. Introduce a new module to generate explanation Related Works: Lambda Networks[Bello+, ICLR21]
9. 5 Proposed Method: Lambda Attention Branch Networks can generate visual explanations for Lambda-based transformers
10. 5 extracted features Proposed Method: Lambda Attention Branch Networks can generate visual explanations for Lambda-based transformers
11. 5 Introduces a branch structure to generate an attention map 𝜶 ∈ ℝ%×'×( Proposed Method: Lambda Attention Branch Networks can generate visual explanations for Lambda-based transformers
12. 5 • Performs classification based on 𝜶 ⊙ 𝒉'() • 𝜶 contributes to both explanation and accuracy Proposed Method: Lambda Attention Branch Networks can generate visual explanations for Lambda-based transformers
13. 6 Proposed Method: Introduced Saliency–guided training [Ismail+, NeurIPS21] to reduce noise in the attention map 1. Generate mask image ) 𝒙 based on attention map Mask image ) 𝒙 Attention map Input 𝒙 2. Minimize KL-divergence between the output of the 𝒙 and ) 𝒙 ℒ*' = 𝐷*' 𝑓 𝒙 |𝑓 ) 𝒙
14. 7 Insertion-Deletion score: IDs = AUC Insertion − AUC(Deletion) Problem of Insertion-Deletion score (ID) • Out-of-distribution input • Prefer to generate coarse explanation Coarse attention map Deletion Input Fine-grained attention map Deletion Input Input Background of proposed metric: IDs is inappropriate for images with sparse important regions
15. 1. Divide 𝒙 into 𝑚 × 𝑚 patches 𝒑)* 2. Insert / Delete pixels according with the importance of attention map 3. Plot 𝑛 with predicted probability 4. Compute AUC 𝒙! = - 𝒑"# 𝑖, 𝑗 ∈ Top 𝑛 Importance (otherwise) Insertion Deletion 9 𝒃"# 𝑝(G 𝑦 = 1|𝒙! ) 𝑛 𝑛 Proposed Metric: Patch Insertion-Deletion score
16. Experimental Setting : Conducted experiments on two public datasets 10 Indian Diabetic Retinopathy Image Dataset (IDRiD) • Dataset for detecting diabetic retinopathy from retinal fundus images • Binary classification task DeFN Magnetogram Dataset • Dataset for solar flare prediction • Binary classification task IDRiD Num of samples Training 330 Validation 83 Test 103 DeFN Magnetograms Time Period Num of samples Training 2010-2015 45530 Validation 2016 7795 Test 2017 7790
17. IDRiD ID PID 𝑚 = 2 𝑚 = 4 𝑚 = 8 𝑚 = 16 RISE [Petsiuk+, BMVC18] 0.319 0.179 0.130 0.136 0.148 Lambda -0.101 -0.105 -0.116 -0.123 0.093 Ours 0.431 0.458 0.473 0.470 0.455 Quantitative Results: IDRiD Outperform baseline methods in IDs and PIDs 10 𝑚 : patch size IDRiD Visual Explanation
18. Quantitative Results: Magnetograms Outperform baseline methods in IDs and PIDs 10 𝑚 : patch size DeFN ID PID 𝑚 = 16 𝑚 = 32 𝑚 = 64 𝑚 = 128 RISE [Petsiuk+, BMVC18] 0.235 0.261 0.296 0.379 0.461 Lambda 0.374 0.414 0.403 0.378 0.291 Ours 0.506 0.748 0.755 0.757 0.756 Magnetogram Visual explanation
19. Ours Fine-grained / appropriate RISE Coarse / inappropriate Lambda Focus on outside corners RISE Lambda Ours 11 Input Qualitative Results: IDRiD The proposed method generated fine-grained explanation
20. RISE Lambda Ours 11 Ours Fine-grained / appropriate RISE Coarse / inappropriate Lambda Focus on outside corners Input Qualitative Results: Magnetograms Generate Fine-grained explanation
21. RISE Lambda Ours 11 Ours Fine-grained / appropriate RISE Coarse / inappropriate Lambda Focus on outside corners Input Qualitative Results: Magnetograms Generate Fine-grained explanation
22. RISE Lambda Ours 11 Ours Fine-grained / appropriate RISE Coarse / inappropriate Lambda Focus on outside corners Input Qualitative Results: Magnetograms Generate Fine-grained explanation
23. RISE Lambda Ours 11 Ours Fine-grained / appropriate RISE Coarse / inappropriate Lambda Focus on outside corners Input Qualitative Results: Magnetograms Generate Fine-grained explanation
24. • We proposed Lambda Attention Branch Network, which has a parallel branching structure to obtain clear visual explanations • We also proposed the PID score, an effective evaluation metric for images with sparse important regions • LABN outperformed the baseline method in terms of the ID and PID scores 13 Conclusion