Self-attention techniques, and specifically Transformers, are dominating the field of text processing and are becoming increasingly popular in computer vision classification tasks. In order to visualize the parts of the image that led to a certain classification, existing methods either rely on the obtained attention maps or employ heuristic propagation along the attention graph. In this work, we propose a novel way to compute relevancy for Transformer networks. The method assigns local relevance based on the Deep Taylor Decomposition principle and then propagates these relevancy scores through the layers. This propagation involves attention layers and skip connections, which challenge existing methods. Our solution is based on a specific formulation that is shown to maintain the total relevancy across layers. We benchmark our method on very recent visual Transformer networks, as well as on a text classification problem, and demonstrate a clear advantage over the existing explainability methods.
Story Visualization is an advanced task of computed vision that targets sequential image synthesis, where the generated samples need to be realistic, faithful to their conditioning and sequentially consistent. Our work proposes a novel architectural and training approach: the Impartial Transformer achieves both text-relevant plausible scenes and sequential consistency utilizing as few trainable parameters as possible. This enhancement is even able to handle synthesis of 'hard' samples with occluded objects, achieving improved evaluation metrics comparing to past approaches.
Understanding how cities visually differ from each others is interesting for planners, residents, and historians. We investigate the interpretation of deep features learned by convolutional neural networks (CNNs) for city recognition. Given a trained city recognition network, we first generate weighted masks using the known Grad-CAM technique and to select the most discriminate regions in the image. Since the image classification label is the city name, it contains no information of objects that are class-discriminate, we investigate the interpretability of deep representations with two method…
MIT CSAIL（麻省理工学院计算机科学与人工智能实验室）；MIT-IBM Watson AI Lab（麻省理工学院-IBM沃森人工智能实验室）；UT Austin（德克萨斯大学奥斯汀分校）
The self-attention-based model, transformer, is recently becoming the leading backbone in the field of computer vision. In spite of the impressive success made by transformers in a variety of vision tasks, it still suffers from heavy computation and intensive memory costs. To address this limitation, this paper presents an Interpretability-Aware REDundancy REDuction framework (IA-RED$^2$). We start by observing a large amount of redundant computation, mainly spent on uncorrelated input patches, and then introduce an interpretable module to dynamically and gracefully drop these redundant patche…
Recently vision transformers (ViT) have been applied successfully for various tasks in computer vision. However, important questions such as why they work or how they behave still remain largely unknown. In this paper, we propose an effective visualization technique, to assist us in exposing the information carried in neurons and feature embeddings across the ViT's layers. Our approach departs from the computational process of ViTs with a focus on visualizing the local and global information in input images and the latent feature embeddings at multiple levels. Visualizations at the input and e…
Breakthroughs in transformer-based models have revolutionized not only the NLP field, but also vision and multimodal systems. However, although visualization and interpretability tools have become available for NLP models, internal mechanisms of vision and multimodal transformers remain largely opaque. With the success of these transformers, it is increasingly critical to understand their inner workings, as unraveling these black-boxes will lead to more capable and trustworthy models. To contribute to this quest, we propose VL-InterpreT, which provides novel interactive visualizations for inte…
Evaluating Graphical Perception Capabilities of Vision Transformers
Viscom Group, Institute of Media Informatics, Ulm University（Viscom集团，媒体信息学研究所，乌尔姆大学）；ViRVIG Group, Universitat Politècnica de Catalunya - BarcelonaTech（ViRVIG集团，巴塞罗那技术大学-加泰罗尼亚理工大学）；Ulm University（乌尔姆大学）
Interpretability has attracted increasing attention in earth observation problems. We apply interactive visualization and representation analysis to guide interpretation of glacier segmentation models. We visualize the activations from a U-Net to understand and evaluate the model performance. We build an online interface using the Shiny R package to provide comprehensive error analysis of the predictions. Users can interact with the panels and discover model failure modes. Further, we discuss how visualization can provide sanity checks during data preprocessing and model training.
Systematic Evaluation of Vision Transformers for Automated Cervical Cancer Classification: Optimization, Statistical Validation, and Clinical Interpretability
School of Systems Science and Industrial Engineering, Binghamton University（宾夕法尼亚大学系统科学与工业工程学院）
MoPFormer: Motion-Primitive Transformer for Wearable-Sensor Activity Recognition
Southern University of Science and Technology（南方科技大学）；City University of Hong Kong（香港城市大学）；Zhejiang University（浙江大学）；Institute of Computing Technology, Chinese Academy of Sciences（中国科学院计算技术研究所）
Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；University of Chinese Academy of Sciences（中国科学院大学）
In this paper, we consider the image captioning task from a new sequence-to-sequence prediction perspective and propose CaPtion TransformeR (CPTR) which takes the sequentialized raw images as the input to Transformer. Compared to the "CNN+Transformer" design paradigm, our model can model global context at every encoder layer from the beginning and is totally convolution-free. Extensive experiments demonstrate the effectiveness of the proposed model and we surpass the conventional "CNN+Transformer" methods on the MSCOCO dataset. Besides, we provide detailed visualizations of the self-attention …
Deep learning is increasingly used in decision-making tasks. However, understanding how neural networks produce final predictions remains a fundamental challenge. Existing work on interpreting neural network predictions for images often focuses on explaining predictions for single images or neurons. As predictions are often computed from millions of weights that are optimized over millions of images, such explanations can easily miss a bigger picture. We present Summit, an interactive system that scalably and systematically summarizes and visualizes what features a deep learning model has lear…
Nantes University（南特大学）；Centrale Nantes（南特中央理工学院）；CNRS（法国国家科学研究中心）；University of Nantes（南特大学）；Nantes University Hospital（南特大学医院）；Inserm（法国国家健康与医学研究院）
The prevalence of employing attention mechanisms has brought along concerns on the interpretability of attention distributions. Although it provides insights about how a model is operating, utilizing attention as the explanation of model predictions is still highly dubious. The community is still seeking more interpretable strategies for better identifying local active regions that contribute the most to the final decision. To improve the interpretability of existing attention models, we propose a novel Bilinear Representative Non-Parametric Attention (BR-NPA) strategy that captures the task-r…
University of Science and Technology of China（中国科学技术大学）
Decoding brain cognitive states from neuroimaging signals is an important topic in neuroscience. In recent years, deep neural networks (DNNs) have been recruited for multiple brain state decoding and achieved good performance. However, the open question of how to interpret the DNN black box remains unanswered. Capitalizing on advances in machine learning, we integrated attention modules into brain decoders to facilitate an in-depth interpretation of DNN channels. A 4D convolution operation was also included to extract temporo-spatial interaction within the fMRI signal. The experiments showed t…
Gnothi Seauton: Empowering Faithful Self-Interpretability in Black-Box Transformers
School of Artificial Intelligence, Shanghai Jiao Tong University（上海交通大学人工智能学院）；Shanghai Jiao Tong University（上海交通大学）；Sichuan University（四川大学）；Big Data and AI Lab, ICBC（中国工商银行大数据与人工智能实验室）；Hong Kong University of Science and Technology, Guangzhou（香港科技大学广州校区）
Keen Eye（基恩眼公司）；LTCI, Télécom Paris, Institut Polytechnique de Paris（巴黎理工学院巴黎电信学院LTCI实验室）
Deep learning methods are widely used for medical applications to assist medical doctors in their daily routines. While performances reach expert's level, interpretability (highlight how and what a trained model learned and why it makes a specific decision) is the next important challenge that deep learning methods need to answer to be fully integrated in the medical field. In this paper, we address the question of interpretability in the context of whole slide images (WSI) classification. We formalize the design of WSI classification architectures and propose a piece-wise interpretability app…
GastroViT: A Vision Transformer Based Ensemble Learning Approach for Gastrointestinal Disease Classification with Grad CAM & SHAP Visualization
Rajshahi University of Engineering & Technology（拉杰沙希工程技术大学）；Manchester Metropolitan University（曼彻斯特城市大学）；Qatar University（卡塔尔大学）；Universiti Kebangsaan Malaysia（马来西亚国立大学）
Recent advances in text-to-image synthesis have led to large pretrained transformers with excellent capabilities to generate visualizations from a given text. However, these models are ill-suited for specialized tasks like story visualization, which requires an agent to produce a sequence of images given a corresponding sequence of captions, forming a narrative. Moreover, we find that the story visualization task fails to accommodate generalization to unseen plots and characters in new narratives. Hence, we first propose the task of story continuation, where the generated visual story is condi…
Harvard University（哈佛大学）；Imperial College London（帝国理工学院）；University of Oxford（牛津大学）
In this paper we introduce a new problem within the growing literature of interpretability for convolution neural networks (CNNs). While previous work has focused on the question of how to visually interpret CNNs, we ask what it is that we care to interpret, that is, which layers and neurons are worth our attention? Due to the vast size of modern deep learning network architectures, automated, quantitative methods are needed to rank the relative importance of neurons so as to provide an answer to this question. We present a new statistical method for ranking the hidden neurons in any convoluti…
