ViTree: Single-path Neural Tree for Step-wise Interpretable Fine-grained
Visual Categorization
- URL: http://arxiv.org/abs/2401.17050v1
- Date: Tue, 30 Jan 2024 14:32:25 GMT
- Title: ViTree: Single-path Neural Tree for Step-wise Interpretable Fine-grained
Visual Categorization
- Authors: Danning Lao, Qi Liu, Jiazi Bu, Junchi Yan, Wei Shen
- Abstract summary: We introduce ViTree, a novel approach for fine-grained visual categorization.
By traversing the tree paths, ViTree effectively selects patches from transformer-processed features to highlight informative local regions.
This patch and path selectivity enhances model interpretability of ViTree, enabling better insights into the model's inner workings.
- Score: 56.37520969273242
- License: http://creativecommons.org/licenses/by-nc-sa/4.0/
- Abstract: As computer vision continues to advance and finds widespread applications
across various domains, the need for interpretability in deep learning models
becomes paramount. Existing methods often resort to post-hoc techniques or
prototypes to explain the decision-making process, which can be indirect and
lack intrinsic illustration. In this research, we introduce ViTree, a novel
approach for fine-grained visual categorization that combines the popular
vision transformer as a feature extraction backbone with neural decision trees.
By traversing the tree paths, ViTree effectively selects patches from
transformer-processed features to highlight informative local regions, thereby
refining representations in a step-wise manner. Unlike previous tree-based
models that rely on soft distributions or ensembles of paths, ViTree selects a
single tree path, offering a clearer and simpler decision-making process. This
patch and path selectivity enhances model interpretability of ViTree, enabling
better insights into the model's inner workings. Remarkably, extensive
experimentation validates that this streamlined approach surpasses various
strong competitors and achieves state-of-the-art performance while maintaining
exceptional interpretability which is proved by multi-perspective methods. Code
can be found at https://github.com/SJTU-DeepVisionLab/ViTree.
Related papers
- Training-Free Guidance Beyond Differentiability: Scalable Path Steering with Tree Search in Diffusion and Flow Models [39.13996838237359]
This work focuses on training-free guidance addressing challenges from non-differentiable objectives and discrete data distributions.
We propose an algorithmic framework TreeG: Tree Search-Based Path Steering Guidance.
Our experiments show that TreeG consistently outperforms the top guidance baselines in symbolic music generation, small molecule generation, and enhancer DNA design.
arXiv Detail & Related papers (2025-02-17T04:20:39Z) - ReTreever: Tree-based Coarse-to-Fine Representations for Retrieval [64.44265315244579]
We propose a tree-based method for organizing and representing reference documents at various granular levels.
Our method, called ReTreever, jointly learns a routing function per internal node of a binary tree such that query and reference documents are assigned to similar tree branches.
Our evaluations show that ReTreever generally preserves full representation accuracy.
arXiv Detail & Related papers (2025-02-11T21:35:13Z) - Learning a Decision Tree Algorithm with Transformers [75.96920867382859]
We introduce MetaTree, a transformer-based model trained via meta-learning to directly produce strong decision trees.
We fit both greedy decision trees and globally optimized decision trees on a large number of datasets, and train MetaTree to produce only the trees that achieve strong generalization performance.
arXiv Detail & Related papers (2024-02-06T07:40:53Z) - Unboxing Tree Ensembles for interpretability: a hierarchical
visualization tool and a multivariate optimal re-built tree [0.34530027457862006]
We develop an interpretable representation of a tree-ensemble model that can provide valuable insights into its behavior.
The proposed model is effective in yielding a shallow interpretable tree approxing the tree-ensemble decision function.
arXiv Detail & Related papers (2023-02-15T10:43:31Z) - Social Interpretable Tree for Pedestrian Trajectory Prediction [75.81745697967608]
We propose a tree-based method, termed as Social Interpretable Tree (SIT), to address this multi-modal prediction task.
A path in the tree from the root to leaf represents an individual possible future trajectory.
Despite the hand-crafted tree, the experimental results on ETH-UCY and Stanford Drone datasets demonstrate that our method is capable of matching or exceeding the performance of state-of-the-art methods.
arXiv Detail & Related papers (2022-05-26T12:18:44Z) - Dive into Decision Trees and Forests: A Theoretical Demonstration [0.0]
Decision trees use the strategy of "divide-and-conquer" to divide a complex problem on the dependency between input features and labels into smaller ones.
Recent advances have greatly improved their performance in computational advertising, recommender system, information retrieval, etc.
arXiv Detail & Related papers (2021-01-20T16:47:59Z) - Growing Deep Forests Efficiently with Soft Routing and Learned
Connectivity [79.83903179393164]
This paper further extends the deep forest idea in several important aspects.
We employ a probabilistic tree whose nodes make probabilistic routing decisions, a.k.a., soft routing, rather than hard binary decisions.
Experiments on the MNIST dataset demonstrate that our empowered deep forests can achieve better or comparable performance than [1],[3].
arXiv Detail & Related papers (2020-12-29T18:05:05Z) - MurTree: Optimal Classification Trees via Dynamic Programming and Search [61.817059565926336]
We present a novel algorithm for learning optimal classification trees based on dynamic programming and search.
Our approach uses only a fraction of the time required by the state-of-the-art and can handle datasets with tens of thousands of instances.
arXiv Detail & Related papers (2020-07-24T17:06:55Z)
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.