EmbSpatial-Bench: Benchmarking Spatial Understanding for Embodied Tasks with Large Vision-Language Models

The recent rapid development of Large Vision-Language Models (LVLMs) has indicated their potential for embodied tasks.However, the critical skill of spatial understanding in embodied environments has not been thoroughly evaluated, leaving the gap between current LVLMs and qualified embodied intelligence unknown. Therefore, we construct EmbSpatial-Bench, a benchmark for evaluating embodied spatial understanding of LVLMs.The benchmark is automatically derived from embodied scenes and covers 6 spatial relationships from an egocentric perspective.Experiments expose the insufficient capacity of current LVLMs (even GPT-4V). We further present EmbSpatial-SFT, an instruction-tuning dataset designed to improve LVLMs' embodied spatial understanding.

VoCoT: Unleashing Visually Grounded Multi-Step Reasoning in Large Multi-Modal Models

While large multi-modal models (LMMs) have exhibited impressive capabilities across diverse tasks, their effectiveness in handling complex tasks has been limited by the prevailing single-step reasoning paradigm. To this end, this paper proposes VoCoT, a multi-step Visually grounded object-centric Chain-of-Thought reasoning framework tailored for inference with LMMs. VoCoT is characterized by two key features: (1) object-centric reasoning paths that revolve around cross-modal shared object-level information, and (2) visually grounded representation of object concepts in a multi-modal interleaved and aligned manner, which effectively bridges the modality gap within LMMs during long-term generation. Additionally, we construct an instruction dataset to facilitate LMMs in adapting to reasoning with VoCoT. By introducing VoCoT into the prevalent open-source LMM architecture, we introduce VolCano. With only 7B parameters and limited input resolution, VolCano demonstrates excellent performance across various scenarios, surpassing SOTA models, including GPT-4V, in tasks requiring complex reasoning. Our code, data and model will be available at https://github.com/RupertLuo/VoCoT.

DELAN: Dual-Level Alignment for Vision-and-Language Navigation by Cross-Modal Contrastive Learning

Vision-and-Language navigation (VLN) requires an agent to navigate in unseen environment by following natural language instruction. For task completion, the agent needs to align and integrate various navigation modalities, including instruction, observation and navigation history. Existing works primarily concentrate on cross-modal attention at the fusion stage to achieve this objective. Nevertheless, modality features generated by disparate uni-encoders reside in their own spaces, leading to a decline in the quality of cross-modal fusion and decision. To address this problem, we propose a Dual-levEL AligNment (DELAN) framework by cross-modal contrastive learning. This framework is designed to align various navigation-related modalities before fusion, thereby enhancing cross-modal interaction and action decision-making. Specifically, we divide the pre-fusion alignment into dual levels: instruction-history level and landmark-observation level according to their semantic correlations. We also reconstruct a dual-level instruction for adaptation to the dual-level alignment. As the training signals for pre-fusion alignment are extremely limited, self-supervised contrastive learning strategies are employed to enforce the matching between different modalities. Our approach seamlessly integrates with the majority of existing models, resulting in improved navigation performance on various VLN benchmarks, including R2R, R4R, RxR and CVDN.

ReForm-Eval: Evaluating Large Vision Language Models via Unified Re-Formulation of Task-Oriented Benchmarks

Recent years have witnessed remarkable progress in the development of large vision-language models (LVLMs). Benefiting from the strong language backbones and efficient cross-modal alignment strategies, LVLMs exhibit surprising capabilities to perceive visual signals and perform visually grounded reasoning. However, the capabilities of LVLMs have not been comprehensively and quantitatively evaluate. Most existing multi-modal benchmarks require task-oriented input-output formats, posing great challenges to automatically assess the free-form text output of LVLMs. To effectively leverage the annotations available in existing benchmarks and reduce the manual effort required for constructing new benchmarks, we propose to re-formulate existing benchmarks into unified LVLM-compatible formats. Through systematic data collection and reformulation, we present the ReForm-Eval benchmark, offering substantial data for evaluating various capabilities of LVLMs. Based on ReForm-Eval, we conduct extensive experiments, thoroughly analyze the strengths and weaknesses of existing LVLMs, and identify the underlying factors. Our benchmark and evaluation framework will be open-sourced as a cornerstone for advancing the development of LVLMs.

A Unified Continuous Learning Framework for Multi-modal Knowledge Discovery and Pre-training

Multi-modal pre-training and knowledge discovery are two important research topics in multi-modal machine learning. Nevertheless, none of existing works make attempts to link knowledge discovery with knowledge guided multi-modal pre-training. In this paper, we propose to unify them into a continuous learning framework for mutual improvement. Taking the open-domain uni-modal datasets of images and texts as input, we maintain a knowledge graph as the foundation to support these two tasks. For knowledge discovery, a pre-trained model is used to identify cross-modal links on the graph. For model pre-training, the knowledge graph is used as the external knowledge to guide the model updating. These two steps are iteratively performed in our framework for continuous learning. The experimental results on MS-COCO and Flickr30K with respect to both knowledge discovery and the pre-trained model validate the effectiveness of our framework.

MVP: Multi-Stage Vision-Language Pre-Training via Multi-Level Semantic Alignment

In this paper, we propose a Multi-stage Vision-language Pre-training (MVP) framework to learn cross-modality representation via multi-level semantic alignment. We introduce concepts in both modalities to construct two-level semantic representations for language and vision. Based on the multi-level input, we train the cross-modality model in two stages, namely, uni-modal learning and cross-modal learning. The former stage enforces within-modality interactions to learn multi-level semantics for each single modality. The latter stage enforces interactions across modalities via both coarse-grain and fine-grain semantic alignment tasks. Image-text matching and masked language modeling are then used to further optimize the pre-training model. Our model generates the-state-of-the-art results on several vision and language tasks.

Negative Sample is Negative in Its Own Way: Tailoring Negative Sentences for Image-Text Retrieval

Matching model is essential for Image-Text Retrieval framework. Existing research usually train the model with a triplet loss and explore various strategy to retrieve hard negative sentences in the dataset. We argue that current retrieval-based negative sample construction approach is limited in the scale of the dataset thus fail to identify negative sample of high difficulty for every image. We propose our TAiloring neGative Sentences with Discrimination and Correction (TAGS-DC) to generate synthetic sentences automatically as negative samples. TAGS-DC is composed of masking and refilling to generate synthetic negative sentences with higher difficulty. To keep the difficulty during training, we mutually improve the retrieval and generation through parameter sharing. To further utilize fine-grained semantic of mismatch in the negative sentence, we propose two auxiliary tasks, namely word discrimination and word correction to improve the training. In experiments, we verify the effectiveness of our model on MS-COCO and Flickr30K compared with current state-of-the-art models and demonstrates its robustness and faithfulness in the further analysis. Our code is available in https://github.com/LibertFan/TAGS.

Constructing Phrase-level Semantic Labels to Form Multi-Grained Supervision for Image-Text Retrieval

Existing research for image text retrieval mainly relies on sentence-level supervision to distinguish matched and mismatched sentences for a query image. However, semantic mismatch between an image and sentences usually happens in finer grain, i.e., phrase level. In this paper, we explore to introduce additional phrase-level supervision for the better identification of mismatched units in the text. In practice, multi-grained semantic labels are automatically constructed for a query image in both sentence-level and phrase-level. We construct text scene graphs for the matched sentences and extract entities and triples as the phrase-level labels. In order to integrate both supervision of sentence-level and phrase-level, we propose Semantic Structure Aware Multimodal Transformer (SSAMT) for multi-modal representation learning. Inside the SSAMT, we utilize different kinds of attention mechanisms to enforce interactions of multi-grain semantic units in both sides of vision and language. For the training, we propose multi-scale matching losses from both global and local perspectives, and penalize mismatched phrases. Experimental results on MS-COCO and Flickr30K show the effectiveness of our approach compared to some state-of-the-art models.

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.

An Unsupervised Sampling Approach for Image-Sentence Matching Using Document-Level Structural Information

In this paper, we focus on the problem of unsupervised image-sentence matching. Existing research explores to utilize document-level structural information to sample positive and negative instances for model training. Although the approach achieves positive results, it introduces a sampling bias and fails to distinguish instances with high semantic similarity. To alleviate the bias, we propose a new sampling strategy to select additional intra-document image-sentence pairs as positive or negative samples. Furthermore, to recognize the complex pattern in intra-document samples, we propose a Transformer based model to capture fine-grained features and implicitly construct a graph for each document, where concepts in a document are introduced to bridge the representation learning of images and sentences in the context of a document. Experimental results show the effectiveness of our approach to alleviate the bias and learn well-aligned multimodal representations.