In an effort to create a more efficient AI system, we introduce a new multi-modality learning framework that leverages a modality-agnostic concept space possessing abstract knowledge and a set of modality-specific projection models tailored to process distinct modality inputs and map them onto the concept space. Decoupled from specific modalities and their associated projection models, the concept space focuses on learning abstract knowledge that is universally applicable across modalities. Subsequently, the knowledge embedded into the concept space streamlines the learning processes of modality-specific projection models. We evaluate our framework on two popular tasks: Image-Text Matching and Visual Question Answering. Our framework achieves performance on par with benchmark models while demonstrating more efficient learning curves.
Deep generative models have achieved promising results in image generation, and various generative model hubs, e.g., Hugging Face and Civitai, have been developed that enable model developers to upload models and users to download models. However, these model hubs lack advanced model management and identification mechanisms, resulting in users only searching for models through text matching, download sorting, etc., making it difficult to efficiently find the model that best meets user requirements. In this paper, we propose a novel setting called Generative Model Identification (GMI), which aims to enable the user to identify the most appropriate generative model(s) for the user's requirements from a large number of candidate models efficiently. To our best knowledge, it has not been studied yet. In this paper, we introduce a comprehensive solution consisting of three pivotal modules: a weighted Reduced Kernel Mean Embedding (RKME) framework for capturing the generated image distribution and the relationship between images and prompts, a pre-trained vision-language model aimed at addressing dimensionality challenges, and an image interrogator designed to tackle cross-modality issues. Extensive empirical results demonstrate the proposal is both efficient and effective. For example, users only need to submit a single example image to describe their requirements, and the model platform can achieve an average top-4 identification accuracy of more than 80%.
Programming based approaches to reasoning tasks have substantially expanded the types of questions models can answer about visual scenes. Yet on benchmark visual reasoning data, when models answer correctly, they produce incorrect programs 33% of the time. These models are often right for the wrong reasons and risk unexpected failures on new data. Unit tests play a foundational role in ensuring code correctness and could be used to repair such failures. We propose Visual Unit Testing (ViUniT), a framework to improve the reliability of visual programs by automatically generating unit tests. In our framework, a unit test is represented as a novel image and answer pair meant to verify the logical correctness of a program produced for a given query. Our method leverages a language model to create unit tests in the form of image descriptions and expected answers and image synthesis to produce corresponding images. We conduct a comprehensive analysis of what constitutes an effective visual unit test suite, exploring unit test generation, sampling strategies, image generation methods, and varying the number of programs and unit tests. Additionally, we introduce four applications of visual unit tests: best program selection, answer refusal, re-prompting, and unsupervised reward formulations for reinforcement learning. Experiments with two models across three datasets in visual question answering and image-text matching demonstrate that ViUniT improves model performance by 11.4%. Notably, it enables 7B open-source models to outperform gpt-4o-mini by an average of 7.7% and reduces the occurrence of programs that are correct for the wrong reasons by 40%.
In the peer review process of top-tier machine learning (ML) and artificial intelligence (AI) conferences, reviewers are assigned to papers through automated methods. These assignment algorithms consider two main factors: (1) reviewers' expressed interests indicated by their bids for papers, and (2) reviewers' domain expertise inferred from the similarity between the text of their previously published papers and the submitted manuscripts. A significant challenge these conferences face is the existence of collusion rings, where groups of researchers manipulate the assignment process to review each other's papers, providing positive evaluations regardless of their actual quality. Most efforts to combat collusion rings have focused on preventing bid manipulation, under the assumption that the text similarity component is secure. In this paper, we demonstrate that even in the absence of bidding, colluding reviewers and authors can exploit the machine learning based text-matching component of reviewer assignment used at top ML/AI venues to get assigned their target paper. We also highlight specific vulnerabilities within this system and offer suggestions to enhance its robustness.
Identifying defects and anomalies in industrial products is a critical quality control task. Traditional manual inspection methods are slow, subjective, and error-prone. In this work, we propose a novel zero-shot training-free approach for automated industrial image anomaly detection using a multimodal machine learning pipeline, consisting of three foundation models. Our method first uses a large language model, i.e., GPT-3. generate text prompts describing the expected appearances of normal and abnormal products. We then use a grounding object detection model, called Grounding DINO, to locate the product in the image. Finally, we compare the cropped product image patches to the generated prompts using a zero-shot image-text matching model, called CLIP, to identify any anomalies. Our experiments on two datasets of industrial product images, namely MVTec-AD and VisA, demonstrate the effectiveness of this method, achieving high accuracy in detecting various types of defects and anomalies without the need for model training. Our proposed model enables efficient, scalable, and objective quality control in industrial manufacturing settings.
The Large Vision Language Model (VLM) has recently addressed remarkable progress in bridging two fundamental modalities. VLM, trained by a sufficiently large dataset, exhibits a comprehensive understanding of both visual and linguistic to perform diverse tasks. To distill this knowledge accurately, in this paper, we introduce a novel approach that explicitly utilizes VLM as an objective function form for the Human-Object Interaction (HOI) detection task (\textbf{VLM-HOI}). Specifically, we propose a method that quantifies the similarity of the predicted HOI triplet using the Image-Text matching technique. We represent HOI triplets linguistically to fully utilize the language comprehension of VLMs, which are more suitable than CLIP models due to their localization and object-centric nature. This matching score is used as an objective for contrastive optimization. To our knowledge, this is the first utilization of VLM language abilities for HOI detection. Experiments demonstrate the effectiveness of our method, achieving state-of-the-art HOI detection accuracy on benchmarks. We believe integrating VLMs into HOI detection represents important progress towards more advanced and interpretable analysis of human-object interactions.
We firstly present a diffusion-based action recognition with zero-shot learning for skeleton inputs. In zero-shot skeleton-based action recognition, aligning skeleton features with the text features of action labels is essential for accurately predicting unseen actions. Previous methods focus on direct alignment between skeleton and text latent spaces, but the modality gaps between these spaces hinder robust generalization learning. Motivated from the remarkable performance of text-to-image diffusion models, we leverage their alignment capabilities between different modalities mostly by focusing on the training process during reverse diffusion rather than using their generative power. Based on this, our framework is designed as a Triplet Diffusion for Skeleton-Text Matching (TDSM) method which aligns skeleton features with text prompts through reverse diffusion, embedding the prompts into the unified skeleton-text latent space to achieve robust matching. To enhance discriminative power, we introduce a novel triplet diffusion (TD) loss that encourages our TDSM to correct skeleton-text matches while pushing apart incorrect ones. Our TDSM significantly outperforms the very recent state-of-the-art methods with large margins of 2.36%-point to 13.05%-point, demonstrating superior accuracy and scalability in zero-shot settings through effective skeleton-text matching.
Recent advancements in image-text matching have been notable, yet prevailing models predominantly cater to broad queries and struggle with accommodating fine-grained query intention. In this paper, we work towards the \textbf{E}ntity-centric \textbf{I}mage-\textbf{T}ext \textbf{M}atching (EITM), a task that the text and image involve specific entity-related information. The challenge of this task mainly lies in the larger semantic gap in entity association modeling, comparing with the general image-text matching problem.To narrow the huge semantic gap between the entity-centric text and the images, we take the fundamental CLIP as the backbone and devise a multimodal attentive contrastive learning framework to tam CLIP to adapt EITM problem, developing a model named EntityCLIP. The key of our multimodal attentive contrastive learning is to generate interpretive explanation text using Large Language Models (LLMs) as the bridge clues. In specific, we proceed by extracting explanatory text from off-the-shelf LLMs. This explanation text, coupled with the image and text, is then input into our specially crafted Multimodal Attentive Experts (MMAE) module, which effectively integrates explanation texts to narrow the gap of the entity-related text and image in a shared semantic space. Building on the enriched features derived from MMAE, we further design an effective Gated Integrative Image-text Matching (GI-ITM) strategy. The GI-ITM employs an adaptive gating mechanism to aggregate MMAE's features, subsequently applying image-text matching constraints to steer the alignment between the text and the image. Extensive experiments are conducted on three social media news benchmarks including N24News, VisualNews, and GoodNews, the results shows that our method surpasses the competition methods with a clear margin.
Many contrastive learning based models have achieved advanced performance in image-text matching tasks. The key of these models lies in analyzing the correlation between image-text pairs, which involves cross-modal interaction of embeddings in corresponding dimensions. However, the embeddings of different modalities are from different models or modules, and there is a significant modality gap. Directly interacting such embeddings lacks rationality and may capture inaccurate correlation. Therefore, we propose a novel method called DIAS to bridge the modality gap from two aspects: (1) We align the information representation of embeddings from different modalities in corresponding dimension to ensure the correlation calculation is based on interactions of similar information. (2) The spatial constraints of inter- and intra-modalities unmatched pairs are introduced to ensure the effectiveness of semantic alignment of the model. Besides, a sparse correlation algorithm is proposed to select strong correlated spatial relationships, enabling the model to learn more significant features and avoid being misled by weak correlation. Extensive experiments demonstrate the superiority of DIAS, achieving 4.3\%-10.2\% rSum improvements on Flickr30k and MSCOCO benchmarks.
Fine-grained video action recognition can be conceptualized as a video-text matching problem. Previous approaches often rely on global video semantics to consolidate video embeddings, which can lead to misalignment in video-text pairs due to a lack of understanding of action semantics at an atomic granularity level. To tackle this challenge, we propose a multi-granularity framework based on two observations: (i) videos with different global semantics may share similar atomic actions or appearances, and (ii) atomic actions within a video can be momentary, slow, or even non-directly related to the global video semantics. Inspired by the concept of storyboarding, which disassembles a script into individual shots, we enhance global video semantics by generating fine-grained descriptions using a pre-trained large language model. These detailed descriptions capture common atomic actions depicted in videos. A filtering metric is proposed to select the descriptions that correspond to the atomic actions present in both the videos and the descriptions. By employing global semantics and fine-grained descriptions, we can identify key frames in videos and utilize them to aggregate embeddings, thereby making the embedding more accurate. Extensive experiments on various video action recognition datasets demonstrate superior performance of our proposed method in supervised, few-shot, and zero-shot settings.
Graph-structured data is prevalent in the real world. Recently, due to the powerful emergent capabilities, Large Language Models (LLMs) have shown promising performance in modeling graphs. The key to effectively applying LLMs on graphs is converting graph data into a format LLMs can comprehend. Graph-to-token approaches are popular in enabling LLMs to process graph information. They transform graphs into sequences of tokens and align them with text tokens through instruction tuning, where self-supervised instruction tuning helps LLMs acquire general knowledge about graphs, and supervised fine-tuning specializes LLMs for the downstream tasks on graphs. Despite their initial success, we find that existing methods have a misalignment between self-supervised tasks and supervised downstream tasks, resulting in negative transfer from self-supervised fine-tuning to downstream tasks. To address these issues, we propose Graph Alignment Large Language Models (GALLM) to benefit from aligned task templates. In the self-supervised tuning stage, we introduce a novel text matching task using templates aligned with downstream tasks. In the task-specific tuning stage, we propose two category prompt methods that learn supervision information from additional explanation with further aligned templates. Experimental evaluations on four datasets demonstrate substantial improvements in supervised learning, multi-dataset generalizability, and particularly in zero-shot capability, highlighting the model's potential as a graph foundation model.
The rapid development of online recruitment platforms has created unprecedented opportunities for job seekers while concurrently posing the significant challenge of quickly and accurately pinpointing positions that align with their skills and preferences. Job recommendation systems have significantly alleviated the extensive search burden for job seekers by optimizing user engagement metrics, such as clicks and applications, thus achieving notable success. In recent years, a substantial amount of research has been devoted to developing effective job recommendation models, primarily focusing on text-matching based and behavior modeling based methods. While these approaches have realized impressive outcomes, it is imperative to note that research on the explainability of recruitment recommendations remains profoundly unexplored. To this end, in this paper, we propose DISCO, a hierarchical Disentanglement based Cognitive diagnosis framework, aimed at flexibly accommodating the underlying representation learning model for effective and interpretable job recommendations. Specifically, we first design a hierarchical representation disentangling module to explicitly mine the hierarchical skill-related factors implied in hidden representations of job seekers and jobs. Subsequently, we propose level-aware association modeling to enhance information communication and robust representation learning both inter- and intra-level, which consists of the interlevel knowledge influence module and the level-wise contrastive learning. Finally, we devise an interaction diagnosis module incorporating a neural diagnosis function for effectively modeling the multi-level recruitment interaction process between job seekers and jobs, which introduces the cognitive measurement theory.
Vision Language Models (VLMs) extend remarkable capabilities of text-only large language models and vision-only models, and are able to learn from and process multi-modal vision-text input. While modern VLMs perform well on a number of standard image classification and image-text matching tasks, they still struggle with a number of crucial vision-language (VL) reasoning abilities such as counting and spatial reasoning. Moreover, while they might be very brittle to small variations in instructions and/or evaluation protocols, existing benchmarks fail to evaluate their robustness (or rather the lack of it). In order to couple challenging VL scenarios with comprehensive robustness evaluation, we introduce DARE, Diverse Visual Question Answering with Robustness Evaluation, a carefully created and curated multiple-choice VQA benchmark. DARE evaluates VLM performance on five diverse categories and includes four robustness-oriented evaluations based on the variations of: prompts, the subsets of answer options, the output format and the number of correct answers. Among a spectrum of other findings, we report that state-of-the-art VLMs still struggle with questions in most categories and are unable to consistently deliver their peak performance across the tested robustness evaluations. The worst case performance across the subsets of options is up to 34% below the performance in the standard case. The robustness of the open-source VLMs such as LLaVA 1.6 and Idefics2 cannot match the closed-source models such as GPT-4 and Gemini, but even the latter remain very brittle to different variations.
Research in music understanding has extensively explored composition-level attributes such as key, genre, and instrumentation through advanced representations, leading to cross-modal applications using large language models. However, aspects of musical performance such as stylistic expression and technique remain underexplored, along with the potential of using large language models to enhance educational outcomes with customized feedback. To bridge this gap, we introduce LLaQo, a Large Language Query-based music coach that leverages audio language modeling to provide detailed and formative assessments of music performances. We also introduce instruction-tuned query-response datasets that cover a variety of performance dimensions from pitch accuracy to articulation, as well as contextual performance understanding (such as difficulty and performance techniques). Utilizing AudioMAE encoder and Vicuna-7b LLM backend, our model achieved state-of-the-art (SOTA) results in predicting teachers' performance ratings, as well as in identifying piece difficulty and playing techniques. Textual responses from LLaQo was moreover rated significantly higher compared to other baseline models in a user study using audio-text matching. Our proposed model can thus provide informative answers to open-ended questions related to musical performance from audio data.
The success of Vision Language Models (VLMs) on various vision-language tasks heavily relies on pre-training with large scale web-crawled datasets. However, the noisy and incomplete nature of web data makes dataset scale crucial for performance, rendering end-to-end training increasingly prohibitive. In this paper, we propose NEVLP, a noise-robust framework for efficient vision-language pre-training that requires less pre-training data. Specifically, we bridge the modality gap between a frozen image encoder and a large language model with a transformer and introduce two innovative learning strategies: noise-adaptive learning and concept-enhanced learning to mitigate the impact of noise. In noise-adaptive learning, we estimate the noise probability of each image-text pair based on the transformer's memorization effect and employ noise-adaptive regularization on image-text contrastive learning to condition cross-modal alignment. In concept-enhanced learning, we enrich incomplete text by incorporating visual concepts (objects in the image) to provide prior information about existing objects for image-text matching and image-grounded text generation, thereby mitigating text incompletion. Our framework effectively utilizes noisy web data and achieves state-of-the-art performance with less pre-training data across a wide range of vision-language tasks, including image-text retrieval, image captioning, and visual question answering.
We introduce jina-embeddings-v3, a novel text embedding model with 570 million parameters, achieves state-of-the-art performance on multilingual data and long-context retrieval tasks, supporting context lengths of up to 8192 tokens. The model includes a set of task-specific Low-Rank Adaptation (LoRA) adapters to generate high-quality embeddings for query-document retrieval, clustering, classification, and text matching. Evaluation on the MTEB benchmark shows that jina-embeddings-v3 outperforms the latest proprietary embeddings from OpenAI and Cohere on English tasks, while achieving superior performance compared to multilingual-e5-large-instruct across all multilingual tasks. With a default output dimension of 1024, users can flexibly reduce the embedding dimensions to as low as 32 without compromising performance, enabled by Matryoshka Representation Learning.
We introduce VidLPRO, a novel video-language (VL) pre-training framework designed specifically for robotic and laparoscopic surgery. While existing surgical VL models primarily rely on contrastive learning, we propose a more comprehensive approach to capture the intricate temporal dynamics and align video with language. VidLPRO integrates video-text contrastive learning, video-text matching, and masked language modeling objectives to learn rich VL representations. To support this framework, we present GenSurg+, a carefully curated dataset derived from GenSurgery, comprising 17k surgical video clips paired with captions generated by GPT-4 using transcripts extracted by the Whisper model. This dataset addresses the need for large-scale, high-quality VL data in the surgical domain. Extensive experiments on benchmark datasets, including Cholec80 and AutoLaparo, demonstrate the efficacy of our approach. VidLPRO achieves state-of-the-art performance in zero-shot surgical phase recognition, significantly outperforming existing surgical VL models such as SurgVLP and HecVL. Our model demonstrates improvements of up to 21.5\% in accuracy and 15.7% in F1 score, setting a new benchmark in the field. Notably, VidLPRO exhibits robust performance even with single-frame inference, while effectively scaling with increased temporal context. Ablation studies reveal the impact of frame sampling strategies on model performance and computational efficiency. These results underscore VidLPRO's potential as a foundation model for surgical video understanding.
Text-attributed graph (TAG) is an important type of graph structured data with text descriptions for each node. Few- and zero-shot node classification on TAGs have many applications in fields such as academia and social networks. However, the two tasks are challenging due to the lack of supervision signals, and existing methods only use the contrastive loss to align graph-based node embedding and language-based text embedding. In this paper, we propose Hound to improve accuracy by introducing more supervision signals, and the core idea is to go beyond the node-text pairs that come with data. Specifically, we design three augmentation techniques, i.e., node perturbation, text matching, and semantics negation to provide more reference nodes for each text and vice versa. Node perturbation adds/drops edges to produce diversified node embeddings that can be matched with a text. Text matching retrieves texts with similar embeddings to match with a node. Semantics negation uses a negative prompt to construct a negative text with the opposite semantics, which is contrasted with the original node and text. We evaluate Hound on 5 datasets and compare with 13 state-of-the-art baselines. The results show that Hound consistently outperforms all baselines, and its accuracy improvements over the best-performing baseline are usually over 5%.
Currently, large vision-language models have gained promising progress on many downstream tasks. However, they still suffer many challenges in fine-grained visual understanding tasks, such as object attribute comprehension. Besides, there have been growing efforts on the evaluations of large vision-language models, but lack of in-depth study of attribute comprehension and the visual language fine-tuning process. In this paper, we propose to evaluate the attribute comprehension ability of large vision-language models from two perspectives: attribute recognition and attribute hierarchy understanding. We evaluate three vision-language interactions, including visual question answering, image-text matching, and image-text cosine similarity. Furthermore, we explore the factors affecting attribute comprehension during fine-tuning. Through a series of quantitative and qualitative experiments, we introduce three main findings: (1) Large vision-language models possess good attribute recognition ability, but their hierarchical understanding ability is relatively limited. (2) Compared to ITC, ITM exhibits superior capability in capturing finer details, making it more suitable for attribute understanding tasks. (3) The attribute information in the captions used for fine-tuning plays a crucial role in attribute understanding. We hope this work can help guide future progress in fine-grained visual understanding of large vision-language models.
Prior image-text matching methods have shown remarkable performance on many benchmark datasets, but most of them overlook the bias in the dataset, which exists in intra-modal and inter-modal, and tend to learn the spurious correlations that extremely degrade the generalization ability of the model. Furthermore, these methods often incorporate biased external knowledge from large-scale datasets as prior knowledge into image-text matching model, which is inevitable to force model further learn biased associations. To address above limitations, this paper firstly utilizes Structural Causal Models (SCMs) to illustrate how intra- and inter-modal confounders damage the image-text matching. Then, we employ backdoor adjustment to propose an innovative Deconfounded Causal Inference Network (DCIN) for image-text matching task. DCIN (1) decomposes the intra- and inter-modal confounders and incorporates them into the encoding stage of visual and textual features, effectively eliminating the spurious correlations during image-text matching, and (2) uses causal inference to mitigate biases of external knowledge. Consequently, the model can learn causality instead of spurious correlations caused by dataset bias. Extensive experiments on two well-known benchmark datasets, i.e., Flickr30K and MSCOCO, demonstrate the superiority of our proposed method.