End-to-end Feature Alignment: A Simple CNN with Intrinsic Class Attribution

• URL: http://arxiv.org/abs/2603.25798v1
• Date: Thu, 26 Mar 2026 18:06:44 GMT
• Title: End-to-end Feature Alignment: A Simple CNN with Intrinsic Class Attribution
• Abstract summary: We present a prototype CNN architecture with intrinsic class attribution through end-to-end feature alignment.<n>We prove theoretically that FA-CNN penultimate feature maps are identical to Grad-CAM saliency maps.<n>FA-CNN performs well on benchmark image classification datasets.
• Score: 3.411873646414169
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We present Feature-Align CNN (FA-CNN), a prototype CNN architecture with intrinsic class attribution through end-to-end feature alignment. Our intuition is that the use of unordered operations such as Linear and Conv2D layers cause unnecessary shuffling and mixing of semantic concepts, thereby making raw feature maps difficult to understand. We introduce two new order preserving layers, the dampened skip connection, and the global average pooling classifier head. These layers force the model to maintain an end-to-end feature alignment from the raw input pixels all the way to final class logits. This end-to-end alignment enhances the interpretability of the model by allowing the raw feature maps to intrinsically exhibit class attribution. We prove theoretically that FA-CNN penultimate feature maps are identical to Grad-CAM saliency maps. Moreover, we prove that these feature maps slowly morph layer-by-layer over network depth, showing the evolution of features through network depth toward penultimate class activations. FA-CNN performs well on benchmark image classification datasets. Moreover, we compare the averaged FA-CNN raw feature maps against Grad-CAM and permutation methods in a percent pixels removed interpretability task. We conclude this work with a discussion and future, including limitations and extensions toward hybrid models.

Related papers

• Disentangling Rich Dynamics from Feature Learning: A Framework for Independent Measurements [5.369150515904139]
  We introduce (1) a measure that quantifies the rich regime independently of performance, and (2) interpretable feature metrics for visualization.<n>We reveal how batch normalization and training set size influence lazy/rich dynamics for VGG16 and ResNet18 on CIFAR-10/100.
  arXiv  Detail & Related papers  (2024-10-05T18:53:48Z)
• A Gradient Boosting Approach for Training Convolutional and Deep Neural Networks [0.0]
  We introduce two procedures for training Convolutional Neural Networks (CNNs) and Deep Neural Network based on Gradient Boosting (GB) The presented models show superior performance in terms of classification accuracy with respect to standard CNN and Deep-NN with the same architectures.
  arXiv  Detail & Related papers  (2023-02-22T12:17:32Z)
• Do We Really Need a Learnable Classifier at the End of Deep Neural Network? [118.18554882199676]
  We study the potential of learning a neural network for classification with the classifier randomly as an ETF and fixed during training. Our experimental results show that our method is able to achieve similar performances on image classification for balanced datasets.
  arXiv  Detail & Related papers  (2022-03-17T04:34:28Z)
• Interflow: Aggregating Multi-layer Feature Mappings with Attention Mechanism [0.7614628596146599]
  This paper proposes the Interflow algorithm specially for traditional CNN models. Interflow divides CNNs into several stages according to the depth and makes predictions by the feature mappings in each stage. It can alleviate gradient vanishing problem, lower the difficulty of network depth selection, and lighten possible over-fitting problem.
  arXiv  Detail & Related papers  (2021-06-26T18:22:01Z)
• Making CNNs Interpretable by Building Dynamic Sequential Decision Forests with Top-down Hierarchy Learning [62.82046926149371]
  We propose a generic model transfer scheme to make Convlutional Neural Networks (CNNs) interpretable. We achieve this by building a differentiable decision forest on top of CNNs. We name the transferred model deep Dynamic Sequential Decision Forest (dDSDF)
  arXiv  Detail & Related papers  (2021-06-05T07:41:18Z)
• An evidential classifier based on Dempster-Shafer theory and deep learning [6.230751621285322]
  We propose a new classification system based on Dempster-Shafer (DS) theory and a convolutional neural network (CNN) architecture for set-valued classification. Experiments on image recognition, signal processing, and semantic-relationship classification tasks demonstrate that the proposed combination of deep CNN, DS layer, and expected utility layer makes it possible to improve classification accuracy.
  arXiv  Detail & Related papers  (2021-03-25T01:29:05Z)
• The Mind's Eye: Visualizing Class-Agnostic Features of CNNs [92.39082696657874]
  We propose an approach to visually interpret CNN features given a set of images by creating corresponding images that depict the most informative features of a specific layer. Our method uses a dual-objective activation and distance loss, without requiring a generator network nor modifications to the original model.
  arXiv  Detail & Related papers  (2021-01-29T07:46:39Z)
• Convolutional Neural Networks from Image Markers [62.997667081978825]
  Feature Learning from Image Markers (FLIM) was recently proposed to estimate convolutional filters, with no backpropagation, from strokes drawn by a user on very few images. This paper extends FLIM for fully connected layers and demonstrates it on different image classification problems. The results show that FLIM-based convolutional neural networks can outperform the same architecture trained from scratch by backpropagation.
  arXiv  Detail & Related papers  (2020-12-15T22:58:23Z)
• Interpreting Graph Neural Networks for NLP With Differentiable Edge Masking [63.49779304362376]
  Graph neural networks (GNNs) have become a popular approach to integrating structural inductive biases into NLP models. We introduce a post-hoc method for interpreting the predictions of GNNs which identifies unnecessary edges. We show that we can drop a large proportion of edges without deteriorating the performance of the model.
  arXiv  Detail & Related papers  (2020-10-01T17:51:19Z)
• Learning CNN filters from user-drawn image markers for coconut-tree image classification [78.42152902652215]
  We present a method that needs a minimal set of user-selected images to train the CNN's feature extractor. The method learns the filters of each convolutional layer from user-drawn markers in image regions that discriminate classes. It does not rely on optimization based on backpropagation, and we demonstrate its advantages on the binary classification of coconut-tree aerial images.
  arXiv  Detail & Related papers  (2020-08-08T15:50:23Z)
• Eigen-CAM: Class Activation Map using Principal Components [1.2691047660244335]
  This paper builds on previous ideas to cope with the increasing demand for interpretable, robust, and transparent models. The proposed Eigen-CAM computes and visualizes the principle components of the learned features/representations from the convolutional layers.
  arXiv  Detail & Related papers  (2020-08-01T17:14:13Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.