Towards Visually Explaining Similarity Models
- URL: http://arxiv.org/abs/2008.06035v2
- Date: Tue, 13 Oct 2020 17:00:38 GMT
- Title: Towards Visually Explaining Similarity Models
- Authors: Meng Zheng and Srikrishna Karanam and Terrence Chen and Richard J.
Radke and Ziyan Wu
- Abstract summary: We present a method to generate gradient-based visual attention for image similarity predictors.
By relying solely on the learned feature embedding, we show that our approach can be applied to any kind of CNN-based similarity architecture.
We show that our resulting attention maps serve more than just interpretability; they can be infused into the model learning process itself with new trainable constraints.
- Score: 29.704524987493766
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: We consider the problem of visually explaining similarity models, i.e.,
explaining why a model predicts two images to be similar in addition to
producing a scalar score. While much recent work in visual model
interpretability has focused on gradient-based attention, these methods rely on
a classification module to generate visual explanations. Consequently, they
cannot readily explain other kinds of models that do not use or need
classification-like loss functions (e.g., similarity models trained with a
metric learning loss). In this work, we bridge this crucial gap, presenting a
method to generate gradient-based visual attention for image similarity
predictors. By relying solely on the learned feature embedding, we show that
our approach can be applied to any kind of CNN-based similarity architecture,
an important step towards generic visual explainability. We show that our
resulting attention maps serve more than just interpretability; they can be
infused into the model learning process itself with new trainable constraints.
We show that the resulting similarity models perform, and can be visually
explained, better than the corresponding baseline models trained without these
constraints. We demonstrate our approach using extensive experiments on three
different kinds of tasks: generic image retrieval, person re-identification,
and low-shot semantic segmentation.
Related papers
- Reinforcing Pre-trained Models Using Counterfactual Images [54.26310919385808]
This paper proposes a novel framework to reinforce classification models using language-guided generated counterfactual images.
We identify model weaknesses by testing the model using the counterfactual image dataset.
We employ the counterfactual images as an augmented dataset to fine-tune and reinforce the classification model.
arXiv Detail & Related papers (2024-06-19T08:07:14Z) - CNN-based explanation ensembling for dataset, representation and explanations evaluation [1.1060425537315088]
We explore the potential of ensembling explanations generated by deep classification models using convolutional model.
Through experimentation and analysis, we aim to investigate the implications of combining explanations to uncover a more coherent and reliable patterns of the model's behavior.
arXiv Detail & Related papers (2024-04-16T08:39:29Z) - CAM-Based Methods Can See through Walls [6.356330972370584]
We show that most CAM-based interpretability methods can incorrectly attribute an important score to parts of the image that the model cannot see.
We train a VGG-like model constrained to not use the lower part of the image and observe positive scores in the unseen part of the image.
This behavior is evaluated quantitatively on two new datasets.
arXiv Detail & Related papers (2024-04-02T13:57:30Z) - COSE: A Consistency-Sensitivity Metric for Saliency on Image
Classification [21.3855970055692]
We present a set of metrics that utilize vision priors to assess the performance of saliency methods on image classification tasks.
We show that although saliency methods are thought to be architecture-independent, most methods could better explain transformer-based models over convolutional-based models.
arXiv Detail & Related papers (2023-09-20T01:06:44Z) - Learning with Explanation Constraints [91.23736536228485]
We provide a learning theoretic framework to analyze how explanations can improve the learning of our models.
We demonstrate the benefits of our approach over a large array of synthetic and real-world experiments.
arXiv Detail & Related papers (2023-03-25T15:06:47Z) - Identifying Spurious Correlations and Correcting them with an
Explanation-based Learning [4.039245878626345]
We present a simple method to identify spurious correlations that have been learned by a model trained for image classification problems.
We apply image-level perturbations and monitor changes in certainties of predictions made using the trained model.
arXiv Detail & Related papers (2022-11-15T16:34:53Z) - From Canonical Correlation Analysis to Self-supervised Graph Neural
Networks [99.44881722969046]
We introduce a conceptually simple yet effective model for self-supervised representation learning with graph data.
We optimize an innovative feature-level objective inspired by classical Canonical Correlation Analysis.
Our method performs competitively on seven public graph datasets.
arXiv Detail & Related papers (2021-06-23T15:55:47Z) - Counterfactual Generative Networks [59.080843365828756]
We propose to decompose the image generation process into independent causal mechanisms that we train without direct supervision.
By exploiting appropriate inductive biases, these mechanisms disentangle object shape, object texture, and background.
We show that the counterfactual images can improve out-of-distribution with a marginal drop in performance on the original classification task.
arXiv Detail & Related papers (2021-01-15T10:23:12Z) - Few-shot Visual Reasoning with Meta-analogical Contrastive Learning [141.2562447971]
We propose to solve a few-shot (or low-shot) visual reasoning problem, by resorting to analogical reasoning.
We extract structural relationships between elements in both domains, and enforce them to be as similar as possible with analogical learning.
We validate our method on RAVEN dataset, on which it outperforms state-of-the-art method, with larger gains when the training data is scarce.
arXiv Detail & Related papers (2020-07-23T14:00:34Z) - Learning What Makes a Difference from Counterfactual Examples and
Gradient Supervision [57.14468881854616]
We propose an auxiliary training objective that improves the generalization capabilities of neural networks.
We use pairs of minimally-different examples with different labels, a.k.a counterfactual or contrasting examples, which provide a signal indicative of the underlying causal structure of the task.
Models trained with this technique demonstrate improved performance on out-of-distribution test sets.
arXiv Detail & Related papers (2020-04-20T02:47:49Z)
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.