Sparse autoencoders (SAEs) have emerged as a powerful technique for extracting human-interpretable features from neural networks activations. Previous works compared different models based on SAE-derived features but those comparisons have been restricted to models within the same modality. We propose a novel indicator allowing quantitative comparison of models across SAE features, and use it to conduct a comparative study of visual, textual and multimodal encoders. We also propose to quantify the Comparative Sharedness of individual features between different classes of models. With these two new tools, we conduct several studies on 21 encoders of the three types, with two significantly different sizes, and considering generalist and domain specific datasets. The results allow to revisit previous studies at the light of encoders trained in a multimodal context and to quantify to which extent all these models share some representations or features. They also suggest that visual features that are specific to VLMs among vision encoders are shared with text encoders, highlighting the impact of text pretraining. The code is available at https://github.com/CEA-LIST/SAEshareConcepts
Despite the high accuracy offered by state-of-the-art deep natural-language models (e.g. LSTM, BERT), their application in real-life settings is still widely limited, as they behave like a black-box to the end-user. Hence, explainability is rapidly becoming a fundamental requirement of future-generation data-driven systems based on deep-learning approaches. Several attempts to fulfill the existing gap between accuracy and interpretability have been done. However, robust and specialized xAI (Explainable Artificial Intelligence) solutions tailored to deep natural-language models are still missin…
Allen Institute for AI（艾伦人工智能研究所）；University of Arizona（亚利桑那大学）
Our goal, in the context of open-domain textual question-answering (QA), is to explain answers by showing the line of reasoning from what is known to the answer, rather than simply showing a fragment of textual evidence (a "rationale'"). If this could be done, new opportunities for understanding and debugging the system's reasoning become possible. Our approach is to generate explanations in the form of entailment trees, namely a tree of multipremise entailment steps from facts that are known, through intermediate conclusions, to the hypothesis of interest (namely the question + answer). To tr…
University of Science and Technology of China（中国科学技术大学）；Nanyang Technological University（南洋理工大学）；NVIDIA AI Technology Center（英伟达人工智能技术中心）；University of Rochester（罗切斯特大学）
Most existing works in visual question answering (VQA) are dedicated to improving the accuracy of predicted answers, while disregarding the explanations. We argue that the explanation for an answer is of the same or even more importance compared with the answer itself, since it makes the question and answering process more understandable and traceable. To this end, we propose a new task of VQA-E (VQA with Explanation), where the computational models are required to generate an explanation with the predicted answer. We first construct a new dataset, and then frame the VQA-E problem in a multi-t…
Can LLM-Generated Textual Explanations Enhance Model Classification Performance? An Empirical Study
Technical University of Munich, School of Computation, Information and Technology, Department of Computer Science, Munich, Germany（慕尼黑技术大学，计算、信息与技术学院，计算机科学系，德国慕尼黑）
Tel-Aviv University（特拉维夫大学）；Allen Institute for AI（艾伦人工智能研究所）
Large pre-trained language models (LMs) have been shown to perform surprisingly well when fine-tuned on tasks that require commonsense and world knowledge. However, in end-to-end architectures, it is difficult to explain what is the knowledge in the LM that allows it to make a correct prediction. In this work, we propose a model for multi-choice question answering, where a LM-based generator generates a textual hypothesis that is later used by a classifier to answer the question. The hypothesis provides a window into the information used by the fine-tuned LM that can be inspected by humans. A …
Effectiveness and interpretability are two essential properties for trustworthy AI systems. Most recent studies in visual reasoning are dedicated to improving the accuracy of predicted answers, and less attention is paid to explaining the rationales behind the decisions. As a result, they commonly take advantage of spurious biases instead of actually reasoning on the visual-textual data, and have yet developed the capability to explain their decision making by considering key information from both modalities. This paper aims to close the gap from three distinct perspectives: first, we define a…
In this paper, we propose a method to obtain robust explanations for visual question answering(VQA) that correlate well with the answers. Our model explains the answers obtained through a VQA model by providing visual and textual explanations. The main challenges that we address are i) Answers and textual explanations obtained by current methods are not well correlated and ii) Current methods for visual explanation do not focus on the right location for explaining the answer. We address both these challenges by using a collaborative correlated module which ensures that even if we do not train …
TCP:Textual-based Class-aware Prompt tuning for Visual-Language Model
Institute of Automation, CAS（中国科学院自动化研究所）；State Key Laboratory of Multimodal Artificial Intelligence Systems（多模态人工智能系统国家重点实验室）；State Key Lab of Processors（处理器国家重点实验室）；Institute of Computing Technology, CAS（中国科学院计算技术研究所）；University of Chinese Academy of Sciences（中国科学院大学）
Charles University（查理大学）；Nara Institute of Science and Technology（奈良先端科学技术大学院大学）；RIKEN AIP（理化学研究所先进智能项目中心）
We present our work in progress exploring the possibilities of a shared embedding space between textual and visual modality. Leveraging the textual nature of object detection labels and the hypothetical expressiveness of extracted visual object representations, we propose an approach opposite to the current trend, grounding of the representations in the word embedding space of the captioning system instead of grounding words or sentences in their associated images. Based on the previous work, we apply additional grounding losses to the image captioning training objective aiming to force visual…
Explaining, Verifying, and Aligning Semantic Hierarchies in Vision-Language Model Embeddings
University of Lübeck（吕贝克大学）；Technical University of Munich（慕尼黑工业大学）；AUMOVIO SE；Osnabrück University（奥斯纳布吕克大学）；Leibniz Institute for Agricultural Engineering and Bioeconomy（莱布尼茨农业工程与生物经济研究所）；University of Hamburg（汉堡大学）
A Similarity Paradigm Through Textual Regularization Without Forgetting
Shanghai Jiao Tong University（上海交通大学）；Hong Kong Baptist University（香港浸会大学）；Northeastern University（东北大学）；University of Science and Technology of China（中国科学技术大学）；Harbin Institute of Technology (Shenzhen)（哈尔滨工业大学（深圳））
This paper explores the bottleneck of feature representations of deep neural networks (DNNs), from the perspective of the complexity of interactions between input variables encoded in DNNs. To this end, we focus on the multi-order interaction between input variables, where the order represents the complexity of interactions. We discover that a DNN is more likely to encode both too simple interactions and too complex interactions, but usually fails to learn interactions of intermediate complexity. Such a phenomenon is widely shared by different DNNs for different tasks. This phenomenon indicate…
School of Computing Sciences, University of East Anglia（东英吉利大学计算科学学院）；Malong Technologies Co., Ltd.（码隆科技有限公司）；Future Media Center, University of Electronic Science and Technology of China（电子科技大学未来媒体中心）
Cross-modal hashing is usually regarded as an effective technique for large-scale textual-visual cross retrieval, where data from different modalities are mapped into a shared Hamming space for matching. Most of the traditional textual-visual binary encoding methods only consider holistic image representations and fail to model descriptive sentences. This renders existing methods inappropriate to handle the rich semantics of informative cross-modal data for quality textual-visual search tasks. To address the problem of hashing cross-modal data with semantic-rich cues, in this paper, a novel in…
Dynamic Textual Prompt For Rehearsal-free Lifelong Person Re-identification
National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology（空天地海一体化大数据应用技术国家工程实验室）；School of Computer Science, Northwestern Polytechnical University（西北工业大学计算机学院）
University of Glasgow（格拉斯哥大学）；TAL Education Group（好未来教育集团）；National University of Singapore（新加坡国立大学）
The current state-of-the-art image-sentence retrieval methods implicitly align the visual-textual fragments, like regions in images and words in sentences, and adopt attention modules to highlight the relevance of cross-modal semantic correspondences. However, the retrieval performance remains unsatisfactory due to a lack of consistent representation in both semantics and structural spaces. In this work, we propose to address the above issue from two aspects: (i) constructing intrinsic structure (along with relations) among the fragments of respective modalities, e.g., "dog $\to$ play $\to$ ba…
Qatar Computing Research Institute（卡塔尔计算研究所）；University of Trento（特伦托大学）；Hamad Bin Khalifa University（哈马德·本·哈利法大学）；Shaheed Benazir Bhutto Women University（沙希德·贝·布托女子大学）；SimulaMet
The paper presents our proposed solutions for the MediaEval 2020 Flood-Related Multimedia Task, which aims to analyze and detect flooding events in multimedia content shared over Twitter. In total, we proposed four different solutions including a multi-modal solution combining textual and visual information for the mandatory run, and three single modal image and text-based solutions as optional runs. In the multimodal method, we rely on a supervised multimodal bitransformer model that combines textual and visual features in an early fusion, achieving a micro F1-score of .859 on the development…
We introduce a multimodal visual-textual search refinement method for fashion garments. Existing search engines do not enable intuitive, interactive, refinement of retrieved results based on the properties of a particular product. We propose a method to retrieve similar items, based on a query item image and textual refinement properties. We believe this method can be leveraged to solve many real-life customer scenarios, in which a similar item in a different color, pattern, length or style is desired. We employ a joint embedding training scheme in which product images and their catalog textua…
Chittagong University of Engineering and Technology（吉大港工程技术大学）
In the past few years, the meme has become a new way of communication on the Internet. As memes are the images with embedded text, it can quickly spread hate, offence and violence. Classifying memes are very challenging because of their multimodal nature and region-specific interpretation. A shared task is organized to develop models that can identify trolls from multimodal social media memes. This work presents a computational model that we have developed as part of our participation in the task. Training data comes in two forms: an image with embedded Tamil code-mixed text and an associated …
Text-guided Feature Disentanglement for Cross-modal Gait Recognition
Fujian Key Laboratory of Urban Intelligent Sensing and Computing, Xiamen University（福建城市智能感知与计算重点实验室，厦门大学）；Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University（多媒体可信感知与高效计算重点实验室，中华人民共和国教育部，厦门大学）
South China University of Technology（华南理工大学）；Baidu VIS（百度视觉技术部）；University of Liverpool（利物浦大学）
Text-to-image person re-identification (ReID) aims to search for pedestrian images of an interested identity via textual descriptions. It is challenging due to both rich intra-modal variations and significant inter-modal gaps. Existing works usually ignore the difference in feature granularity between the two modalities, i.e., the visual features are usually fine-grained while textual features are coarse, which is mainly responsible for the large inter-modal gaps. In this paper, we propose an end-to-end framework based on transformers to learn granularity-unified representations for both modal…
Nanjing University（南京大学）；SenseTime Research（商汤科技研究院）；Shanghai AI Laboratory（上海人工智能实验室）
Video recognition in an open and dynamic world is quite challenging, as we need to handle different settings such as close-set, long-tail, few-shot and open-set. By leveraging semantic knowledge from noisy text descriptions crawled from the Internet, we focus on the general video recognition (GVR) problem of solving different recognition tasks within a unified framework. The core contribution of this paper is twofold. First, we build a comprehensive video recognition benchmark of Kinetics-GVR, including four sub-task datasets to cover the mentioned settings. To facilitate the research of GVR, …
