AI Paper Atlas

Research map / Vision-language and multimodal / Visual question answering

U-CAM: Visual Explanation Using Uncertainty Based Class Activation Maps

Badri N. Patro, Mayank Lunayach, Shivansh Patel, Vinay P. Namboodiri

ICCV 2019 · Vision-language and multimodal › Visual question answering · approach: Attention and prior-robust VQA · 80 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add predictive uncertainty loss (PUL) to MCB (ablation)MCB · VQA-v1 test-dev (ablation)accuracy (All): 63.8 -> 64.9Improved
add aleatoric uncertainty loss (AUL) to MCB (ablation)MCB · VQA-v1 test-dev (ablation)accuracy (All): 63.8 -> 64.7Improved
add variance equalizer (VE) loss to MCB (ablation)MCB · VQA-v1 test-dev (ablation)accuracy (All): 63.8 -> 64.1Improved
add uncertainty distorted loss (UDL) to MCB (ablation)MCB · VQA-v1 test-dev (ablation)accuracy (All): 63.8 -> 64.4Improved
combine PUL and UDL instead of PUL alone (ablation)MCB · VQA-v1 test-dev (ablation)accuracy (All): 64.9 -> 65.9Improved
add UDL+VE on top of AUL+UDL (full A-GCA) (ablation)MCB · VQA-v1 test-dev (ablation)accuracy (All): 65.6 -> 66.3Improved
add VE and UDL on top of PUL (full P-GCA) (ablation)MCB · VQA-v1 test-dev (ablation)accuracy (All): 65.9 -> 66.5Improved
add PUL loss to MCB (ablation)MCB · VQA-HAT (human attention)rank correlation: 0.2790 -> 0.3012Improved
full P-GCA instead of baseline (ablation)MCB · VQA-HAT (human attention)rank correlation: 0.2790 -> 0.3341Improved
full P-GCA instead of baseline (ablation)MCB · VQA-HAT (human attention)EMD: 0.3931 -> 0.3721Improved
add VE loss to MCB (ablation)MCB · VQA-HAT (human attention)EMD: 0.3931 -> 0.3931No clear effect
add P-GCA to SANSAN · VQA-v2 test-devaccuracy (All): SAN-2 56.9 -> 59.2Mixed

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy