English
Related papers

Related papers: Analyzing Hierarchical Structure in Vision Models …

200 papers

One of the roadblocks to a better understanding of neural networks' internals is \textit{polysemanticity}, where neurons appear to activate in multiple, semantically distinct contexts. Polysemanticity prevents us from identifying concise,…

Machine Learning · Computer Science 2023-10-05 Hoagy Cunningham , Aidan Ewart , Logan Riggs , Robert Huben , Lee Sharkey

The recent emergence of Self-Supervised Learning (SSL) as a fundamental paradigm for learning image representations has, and continues to, demonstrate high empirical success in a variety of tasks. However, most SSL approaches fail to learn…

Computer Vision and Pattern Recognition · Computer Science 2024-11-06 Alžběta Manová , Aiden Durrant , Georgios Leontidis

While recent vision-and-language models (VLMs) like CLIP are a powerful tool for analyzing text and images in a shared semantic space, they do not explicitly model the hierarchical nature of the set of texts which may describe an image.…

Computer Vision and Pattern Recognition · Computer Science 2024-07-17 Morris Alper , Hadar Averbuch-Elor

With the popularity of deep neural networks (DNNs), model interpretability is becoming a critical concern. Many approaches have been developed to tackle the problem through post-hoc analysis, such as explaining how predictions are made or…

Computer Vision and Pattern Recognition · Computer Science 2023-07-11 Haixing Dai , Lu Zhang , Lin Zhao , Zihao Wu , Zhengliang Liu , David Liu , Xiaowei Yu , Yanjun Lyu , Changying Li , Ninghao Liu , Tianming Liu , Dajiang Zhu

Protein language models have revolutionized structure prediction, but their nonlinear nature obscures how sequence representations inform structure prediction. While sparse autoencoders (SAEs) offer a path to interpretability here by…

Biomolecules · Quantitative Biology 2025-03-13 Nithin Parsan , David J. Yang , John J. Yang

Sparse Autoencoders (SAEs) have emerged as a promising solution for decomposing large language model representations into interpretable features. However, Paulo and Belrose (2025) have highlighted instability across different initialization…

Machine Learning · Computer Science 2025-06-24 Seonglae Cho , Harryn Oh , Donghyun Lee , Luis Eduardo Rodrigues Vieira , Andrew Bermingham , Ziad El Sayed

Deep dictionary learning seeks multiple dictionaries at different image scales to capture complementary coherent characteristics. We propose a method for learning a hierarchy of synthesis dictionaries with an image classification goal. The…

Computer Vision and Pattern Recognition · Computer Science 2019-09-04 Shahin Mahdizadehaghdam , Ashkan Panahi , Hamid Krim , Liyi Dai

Sparse autoencoders (SAEs) have become a standard tool for mechanistic interpretability in autoregressive large language models (LLMs), enabling researchers to extract sparse, human-interpretable features and intervene on model behavior.…

Machine Learning · Computer Science 2026-02-06 Xu Wang , Bingqing Jiang , Yu Wan , Baosong Yang , Lingpeng Kong , Difan Zou

Masked Autoencoders (MAEs) achieve impressive performance in image classification tasks, yet the internal representations they learn remain less understood. This work started as an attempt to understand the strong downstream classification…

Machine Learning · Computer Science 2026-02-04 Anika Shrivastava , Renu Rameshan , Samar Agnihotri

Sparse coding, which is the decomposition of a vector using only a few basis elements, is widely used in machine learning and image processing. The basis set, also called dictionary, is learned to adapt to specific data. This approach has…

Machine Learning · Computer Science 2011-12-13 Louise Benoît , Julien Mairal , Francis Bach , Jean Ponce

Determining company similarity is a vital task in finance, underpinning risk management, hedging, and portfolio diversification. Practitioners often rely on sector and industry classifications such as SIC and GICS codes to gauge similarity,…

Image set-based visual classification methods have achieved remarkable performance, via characterising the image set in terms of a non-singular covariance matrix on a symmetric positive definite (SPD) manifold. To adapt to complicated…

Computer Vision and Pattern Recognition · Computer Science 2022-06-17 Rui Wang , Xiao-Jun Wu , Ziheng Chen , Tianyang Xu , Josef Kittler

We study the challenge of achieving theoretically grounded feature recovery using Sparse Autoencoders (SAEs) for the interpretation of Large Language Models. Existing SAE training algorithms often lack rigorous mathematical guarantees and…

Machine Learning · Computer Science 2025-06-18 Siyu Chen , Heejune Sheen , Xuyuan Xiong , Tianhao Wang , Zhuoran Yang

Interpretability can improve the safety, transparency and trust of AI models, which is especially important in healthcare applications where decisions often carry significant consequences. Mechanistic interpretability, particularly through…

Variational Autoencoders (VAEs) are powerful generative models for learning latent representations. Standard VAEs generate dispersed and unstructured latent spaces by utilizing all dimensions, which limits their interpretability, especially…

Computer Vision and Pattern Recognition · Computer Science 2025-05-21 Farshad Sangari Abiz , Reshad Hosseini , Babak N. Araabi

Sparse autoencoders (SAEs) are a promising technique for decomposing language model activations into interpretable linear features. However, current SAEs fall short of completely explaining model performance, resulting in "dark matter":…

Machine Learning · Computer Science 2025-03-26 Joshua Engels , Logan Riggs , Max Tegmark

Sparse autoencoders (SAEs) are a technique for sparse decomposition of neural network activations into human-interpretable features. However, current SAEs suffer from feature absorption, where specialized features capture instances of…

Machine Learning · Computer Science 2025-09-29 Anton Korznikov , Andrey Galichin , Alexey Dontsov , Oleg Rogov , Elena Tutubalina , Ivan Oseledets

Vision models are interpretable when they classify objects on the basis of features that a person can directly understand. Recently, methods relying on visual feature prototypes have been developed for this purpose. However, in contrast to…

Computer Vision and Pattern Recognition · Computer Science 2019-08-27 Peter Hase , Chaofan Chen , Oscar Li , Cynthia Rudin

Visual Semantic Embedding (VSE) models, which map images into a rich semantic embedding space, have been a milestone in object recognition and zero-shot learning. Current approaches to VSE heavily rely on static word em-bedding techniques.…

Computer Vision and Pattern Recognition · Computer Science 2021-07-27 Yue Jiao , Jonathon Hare , Adam Prügel-Bennett

Accurate understanding of anatomical structures is essential for reliably staging certain dental diseases. A way of introducing this within semantic segmentation models is by utilising hierarchy-aware methodologies. However, existing…

Computer Vision and Pattern Recognition · Computer Science 2026-02-20 Ryan Banks , Camila Lindoni Azevedo , Hongying Tang , Yunpeng Li
‹ Prev 1 8 9 10 Next ›