CF-CAM: Gradient Perturbation Mitigation and Feature Stabilization for Reliable Interpretability

As deep learning continues to advance, the opacity of neural network decision-making remains a critical challenge, limiting trust and applicability in high-stakes domains. Class Activation Mapping (CAM) techniques have emerged as a key approach to visualizing model decisions, yet existing methods face inherent trade-offs. Gradient-based CAM variants suffer from sensitivity to gradient perturbations, leading to unstable and unreliable explanations. Conversely, gradient-free approaches mitigate gradient instability but incur significant computational overhead and inference latency. To address these limitations, we propose Cluster Filter Class Activation Map (CF-CAM), a novel framework that reintroduces gradient-based weighting while enhancing robustness against gradient noise. CF-CAM employs a hierarchical importance weighting strategy to balance discriminative feature preservation and noise elimination. A density-aware channel clustering via Density-Based Spatial Clustering of Applications with Noise (DBSCAN) groups semantically relevant feature channels and discard noise-prone activations. Additionally, cluster-conditioned gradient filtering leverages bilateral filters to refine gradient signals, preserving edge-aware localization while suppressing noise impact. Experiment results demonstrate that CF-CAM achieves superior interpretability performance while maintaining resilience to gradient perturbations, outperforming state-of-the-art CAM methods in faithfulness and robustness. By effectively mitigating gradient instability without excessive computational cost, CF-CAM provides a reliable solution for enhancing the interpretability of deep neural networks in critical applications such as medical diagnosis and autonomous driving.

Multi-Instance Multi-Label Learning Networks for Aspect-Category Sentiment Analysis

Aspect-category sentiment analysis (ACSA) aims to predict sentiment polarities of sentences with respect to given aspect categories. To detect the sentiment toward a particular aspect category in a sentence, most previous methods first generate an aspect category-specific sentence representation for the aspect category, then predict the sentiment polarity based on the representation. These methods ignore the fact that the sentiment of an aspect category mentioned in a sentence is an aggregation of the sentiments of the words indicating the aspect category in the sentence, which leads to suboptimal performance. In this paper, we propose a Multi-Instance Multi-Label Learning Network for Aspect-Category sentiment analysis (AC-MIMLLN), which treats sentences as bags, words as instances, and the words indicating an aspect category as the key instances of the aspect category. Given a sentence and the aspect categories mentioned in the sentence, AC-MIMLLN first predicts the sentiments of the instances, then finds the key instances for the aspect categories, finally obtains the sentiments of the sentence toward the aspect categories by aggregating the key instance sentiments. Experimental results on three public datasets demonstrate the effectiveness of AC-MIMLLN.