What Does a Language-And-Vision Transformer See: The Impact of Semantic Information on Visual Representations

Neural networks have proven to be very successful in automatically capturing the composition of language and different structures across a range of multi-modal tasks. Thus, an important question to investigate is how neural networks learn and organise such structures. Numerous studies have examined the knowledge captured by language models (LSTMs, transformers) and vision architectures (CNNs, vision transformers) for respective uni-modal tasks. However, very few have explored what structures are acquired by multi-modal transformers where linguistic and visual features are combined. It is critical to understand the representations learned by each modality, their respective interplay, and the task’s effect on these representations in large-scale architectures. In this paper, we take a multi-modal transformer trained for image captioning and examine the structure of the self-attention patterns extracted from the visual stream. Our results indicate that the information about different relations between objects in the visual stream is hierarchical and varies from local to a global object-level understanding of the image. In particular, while visual representations in the first layers encode the knowledge of relations between semantically similar object detections, often constituting neighbouring objects, deeper layers expand their attention across more distant objects and learn global relations between them. We also show that globally attended objects in deeper layers can be linked with entities described in image descriptions, indicating a critical finding - the indirect effect of language on visual representations. In addition, we highlight how object-based input representations affect the structure of learned visual knowledge and guide the model towards more accurate image descriptions. A parallel question that we investigate is whether the insights from cognitive science echo the structure of representations that the current neural architecture learns. The proposed analysis of the inner workings of multi-modal transformers can be used to better understand and improve on such problems as pre-training of large-scale multi-modal architectures, multi-modal information fusion and probing of attention weights. In general, we contribute to the explainable multi-modal natural language processing and currently shallow understanding of how the input representations and the structure of the multi-modal transformer affect visual representations.

Cross-Modal Hybrid Feature Fusion for Image-Sentence Matching

Image-sentence matching is a challenging task in the field of language and vision, which aims at measuring the similarities between images and sentence descriptions. Most existing methods independently map the global features of images and sentences into a common space to calculate the image-sentence similarity. However, the image-sentence similarity obtained by these methods may be coarse as (1) an intermediate common space is introduced to implicitly match the heterogeneous features of images and sentences in a global level, and (2) only the inter-modality relations of images and sentences are captured while the intra-modality relations are ignored. To overcome the limitations, we propose a novel Cross-Modal Hybrid Feature Fusion (CMHF) framework for directly learning the image-sentence similarity by fusing multimodal features with inter- and intra-modality relations incorporated. It can robustly capture the high-level interactions between visual regions in images and words in sentences, where flexible attention mechanisms are utilized to generate effective attention flows within and across the modalities of images and sentences. A structured objective with ranking loss constraint is formed in CMHF to learn the image-sentence similarity based on the fused fine-grained features of different modalities bypassing the usage of intermediate common space. Extensive experiments and comprehensive analysis performed on two widely used datasets—Microsoft COCO and Flickr30K—show the effectiveness of the hybrid feature fusion framework in CMHF, in which the state-of-the-art matching performance is achieved by our proposed CMHF method.

Trends in Integration of Vision and Language Research: A Survey of Tasks, Datasets, and Methods

Interest in Artificial Intelligence (AI) and its applications has seen unprecedented growth in the last few years. This success can be partly attributed to the advancements made in the sub-fields of AI such as machine learning, computer vision, and natural language processing. Much of the growth in these fields has been made possible with deep learning, a sub-area of machine learning that uses artificial neural networks. This has created significant interest in the integration of vision and language. In this survey, we focus on ten prominent tasks that integrate language and vision by discussing their problem formulation, methods, existing datasets, evaluation measures, and compare the results obtained with corresponding state-of-the-art methods. Our efforts go beyond earlier surveys which are either task-specific or concentrate only on one type of visual content, i.e., image or video. Furthermore, we also provide some potential future directions in this field of research with an anticipation that this survey stimulates innovative thoughts and ideas to address the existing challenges and build new applications.

TCIC: Theme Concepts Learning Cross Language and Vision for Image Captioning

Existing research for image captioning usually represents an image using a scene graph with low-level facts (objects and relations) and fails to capture the high-level semantics. In this paper, we propose a Theme Concepts extended Image Captioning (TCIC) framework that incorporates theme concepts to represent high-level cross-modality semantics. In practice, we model theme concepts as memory vectors and propose Transformer with Theme Nodes (TTN) to incorporate those vectors for image captioning. Considering that theme concepts can be learned from both images and captions, we propose two settings for their representations learning based on TTN. On the vision side, TTN is configured to take both scene graph based features and theme concepts as input for visual representation learning. On the language side, TTN is configured to take both captions and theme concepts as input for text representation re-construction. Both settings aim to generate target captions with the same transformer-based decoder. During the training, we further align representations of theme concepts learned from images and corresponding captions to enforce the cross-modality learning. Experimental results on MS COCO show the effectiveness of our approach compared to some state-of-the-art models.

Explaining Self-Supervised Image Representations with Visual Probing

Recently introduced self-supervised methods for image representation learning provide on par or superior results to their fully supervised competitors, yet the corresponding efforts to explain the self-supervised approaches lag behind. Motivated by this observation, we introduce a novel visual probing framework for explaining the self-supervised models by leveraging probing tasks employed previously in natural language processing. The probing tasks require knowledge about semantic relationships between image parts. Hence, we propose a systematic approach to obtain analogs of natural language in vision, such as visual words, context, and taxonomy. We show the effectiveness and applicability of those analogs in the context of explaining self-supervised representations. Our key findings emphasize that relations between language and vision can serve as an effective yet intuitive tool for discovering how machine learning models work, independently of data modality. Our work opens a plethora of research pathways towards more explainable and transparent AI.

Deep Visual Semantic Embedding with Text Data Augmentation and Word Embedding Initialization

Language and vision are the two most essential parts of human intelligence for interpreting the real world around us. How to make connections between language and vision is the key point in current research. Multimodality methods like visual semantic embedding have been widely studied recently, which unify images and corresponding texts into the same feature space. Inspired by the recent development of text data augmentation and a simple but powerful technique proposed called EDA (easy data augmentation), we can expand the information with given data using EDA to improve the performance of models. In this paper, we take advantage of the text data augmentation technique and word embedding initialization for multimodality retrieval. We utilize EDA for text data augmentation, word embedding initialization for text encoder based on recurrent neural networks, and minimizing the gap between the two spaces by triplet ranking loss with hard negative mining. On two Flickr-based datasets, we achieve the same recall with only 60% of the training dataset as the normal training with full available data. Experiment results show the improvement of our proposed model; and, on all datasets in this paper (Flickr8k, Flickr30k, and MS-COCO), our model performs better on image annotation and image retrieval tasks; the experiments also demonstrate that text data augmentation is more suitable for smaller datasets, while word embedding initialization is suitable for larger ones.

Aspect-Aware Response Generation for Multimodal Dialogue System

Multimodality in dialogue systems has opened up new frontiers for the creation of robust conversational agents. Any multimodal system aims at bridging the gap between language and vision by leveraging diverse and often complementary information from image, audio, and video, as well as text. For every task-oriented dialog system, different aspects of the product or service are crucial for satisfying the user’s demands. Based upon the aspect, the user decides upon selecting the product or service. The ability to generate responses with the specified aspects in a goal-oriented dialogue setup facilitates user satisfaction by fulfilling the user’s goals. Therefore, in our current work, we propose the task of aspect controlled response generation in a multimodal task-oriented dialog system. We employ a multimodal hierarchical memory network for generating responses that utilize information from both text and images. As there was no readily available data for building such multimodal systems, we create a Multi-Domain Multi-Modal Dialog (MDMMD++) dataset. The dataset comprises the conversations having both text and images belonging to the four different domains, such as hotels, restaurants, electronics, and furniture. Quantitative and qualitative analysis on the newly created MDMMD++ dataset shows that the proposed methodology outperforms the baseline models for the proposed task of aspect controlled response generation.