Pruned vision models can outperform dense ones on interpretability, object discovery, and distortion robustness, but only at architecture-dependent sparsity levels.
Exploring the Lottery Ticket Hypothesis with Explainability Methods: Insights into Sparse Network Performance
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
Discovering a high-performing sparse network within a massive neural network is advantageous for deploying them on devices with limited storage, such as mobile phones. Additionally, model explainability is essential to fostering trust in AI. The Lottery Ticket Hypothesis (LTH) finds a network within a deep network with comparable or superior performance to the original model. However, limited study has been conducted on the success or failure of LTH in terms of explainability. In this work, we examine why the performance of the pruned networks gradually increases or decreases. Using Grad-CAM and Post-hoc concept bottleneck models (PCBMs), respectively, we investigate the explainability of pruned networks in terms of pixels and high-level concepts. We perform extensive experiments across vision and medical imaging datasets. As more weights are pruned, the performance of the network degrades. The discovered concepts and pixels from the pruned networks are inconsistent with the original network -- a possible reason for the drop in performance.
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
When Does Pruning Benefit Vision Representations?
Pruned vision models can outperform dense ones on interpretability, object discovery, and distortion robustness, but only at architecture-dependent sparsity levels.