Modern image-to-text systems typically adopt the encoder-decoder framework, which comprises two main components: an image encoder, responsible for extracting image features, and a transformer-based decoder, used for generating captions. Taking inspiration from the analysis of neural networks' robustness against adversarial perturbations, we propose a novel gray-box algorithm for creating adversarial examples in image-to-text models. Unlike image classification tasks that have a finite set of class labels, finding visually similar adversarial examples in an image-to-text task poses greater challenges because the captioning system allows for a virtually infinite space of possible captions. In this paper, we present a gray-box adversarial attack on image-to-text, both untargeted and targeted. We formulate the process of discovering adversarial perturbations as an optimization problem that uses only the image-encoder component, meaning the proposed attack is language-model agnostic. Through experiments conducted on the ViT-GPT2 model, which is the most-used image-to-text model in Hugging Face, and the Flickr30k dataset, we demonstrate that our proposed attack successfully generates visually similar adversarial examples, both with untargeted and targeted captions. Notably, our attack operates in a gray-box manner, requiring no knowledge about the decoder module. We also show that our attacks fool the popular open-source platform Hugging Face.
One impressive emergent capability of large language models (LLMs) is generation of code, including Structured Query Language (SQL) for databases. For the task of converting natural language text to SQL queries, Text-to-SQL, adaptation of LLMs is of paramount importance, both in in-context learning and fine-tuning settings, depending on the amount of adaptation data used. In this paper, we propose an LLM-based Text-to-SQL model SQL-PaLM, leveraging on PaLM-2, that pushes the state-of-the-art in both settings. Few-shot SQL-PaLM is based on an execution-based self-consistency prompting approach designed for Text-to-SQL, and achieves 77.3% in test-suite accuracy on Spider, which to our best knowledge is the first to outperform previous state-of-the-art with fine-tuning by a significant margin, 4%. Furthermore, we demonstrate that the fine-tuned SQL-PALM outperforms it further by another 1%. Towards applying SQL-PaLM to real-world scenarios we further evaluate its robustness on other challenging variants of Spider and demonstrate the superior generalization capability of SQL-PaLM. In addition, via extensive case studies, we demonstrate the impressive intelligent capabilities and various success enablers of LLM-based Text-to-SQL.
We present our work on developing a multilingual, efficient text-to-text transformer that is suitable for handling long inputs. This model, called mLongT5, builds upon the architecture of LongT5, while leveraging the multilingual datasets used for pretraining mT5 and the pretraining tasks of UL2. We evaluate this model on a variety of multilingual summarization and question-answering tasks, and the results show stronger performance for mLongT5 when compared to existing multilingual models such as mBART or M-BERT.
Large-scale foundation models, such as CLIP, have demonstrated remarkable success in visual recognition tasks by embedding images in a semantically rich space. Self-supervised learning (SSL) has also shown promise in improving visual recognition by learning invariant features. However, the combination of CLIP with SSL is found to face challenges due to the multi-task framework that blends CLIP's contrastive loss and SSL's loss, including difficulties with loss weighting and inconsistency among different views of images in CLIP's output space. To overcome these challenges, we propose a prompt learning-based model called GOPro, which is a unified framework that ensures similarity between various augmented views of input images in a shared image-text embedding space, using a pair of learnable image and text projectors atop CLIP, to promote invariance and generalizability. To automatically learn such prompts, we leverage the visual content and style primitives extracted from pre-trained CLIP and adapt them to the target task. In addition to CLIP's cross-domain contrastive loss, we introduce a visual contrastive loss and a novel prompt consistency loss, considering the different views of the images. GOPro is trained end-to-end on all three loss objectives, combining the strengths of CLIP and SSL in a principled manner. Empirical evaluations demonstrate that GOPro outperforms the state-of-the-art prompting techniques on three challenging domain generalization tasks across multiple benchmarks by a significant margin. Our code is available at https://github.com/mainaksingha01/GOPro.
This paper presents a novel method that leverages a visual-language model, CLIP, as a data source for zero-shot anomaly detection. Tremendous efforts have been put towards developing anomaly detectors due to their potential industrial applications. Considering the difficulty in acquiring various anomalous samples for training, most existing methods train models with only normal samples and measure discrepancies from the distribution of normal samples during inference, which requires training a model for each object category. The problem of this inefficient training requirement has been tackled by designing a CLIP-based anomaly detector that applies prompt-guided classification to each part of an image in a sliding window manner. However, the method still suffers from the labor of careful prompt ensembling with known object categories. To overcome the issues above, we propose leveraging CLIP as a data source for training. Our method generates text embeddings with the text encoder in CLIP with typical prompts that include words of normal and anomaly. In addition to these words, we insert several randomly generated words into prompts, which enables the encoder to generate a diverse set of normal and anomalous samples. Using the generated embeddings as training data, a feed-forward neural network learns to extract features of normal and anomaly from CLIP's embeddings, and as a result, a category-agnostic anomaly detector can be obtained without any training images. Experimental results demonstrate that our method achieves state-of-the-art performance without laborious prompt ensembling in zero-shot setups.
We introduce the Qwen-VL series, a set of large-scale vision-language models designed to perceive and understand both text and images. Comprising Qwen-VL and Qwen-VL-Chat, these models exhibit remarkable performance in tasks like image captioning, question answering, visual localization, and flexible interaction. The evaluation covers a wide range of tasks including zero-shot captioning, visual or document visual question answering, and grounding. We demonstrate the Qwen-VL outperforms existing Large Vision Language Models (LVLMs). We present their architecture, training, capabilities, and performance, highlighting their contributions to advancing multimodal artificial intelligence. Code, demo and models are available at https://github.com/QwenLM/Qwen-VL.
Large Language Models (LLMs) such as ChatGPT have received enormous attention over the past year and are now used by hundreds of millions of people every day. The rapid adoption of this technology naturally raises questions about the possible biases such models might exhibit. In this work, we tested one of these models (GPT-3) on a range of cognitive effects, which are systematic patterns that are usually found in human cognitive tasks. We found that LLMs are indeed prone to several human cognitive effects. Specifically, we show that the priming, distance, SNARC, and size congruity effects were presented with GPT-3, while the anchoring effect is absent. We describe our methodology, and specifically the way we converted real-world experiments to text-based experiments. Finally, we speculate on the possible reasons why GPT-3 exhibits these effects and discuss whether they are imitated or reinvented.
Although remote working is increasingly adopted during the pandemic, many are concerned by the low-efficiency in the remote working. Missing in text-based communication are non-verbal cues such as facial expressions and body language, which hinders the effective communication and negatively impacts the work outcomes. Prevalent on social media platforms, emojis, as alternative non-verbal cues, are gaining popularity in the virtual workspaces well. In this paper, we study how emoji usage influences developer participation and issue resolution in virtual workspaces. To this end, we collect GitHub issues for a one-year period and apply causal inference techniques to measure the causal effect of emojis on the outcome of issues, controlling for confounders such as issue content, repository, and author information. We find that emojis can significantly reduce the resolution time of issues and attract more user participation. We also compare the heterogeneous effect on different types of issues. These findings deepen our understanding of the developer communities, and they provide design implications on how to facilitate interactions and broaden developer participation.
This paper tackles text-guided control of StyleGAN for editing garments in full-body human images. Existing StyleGAN-based methods suffer from handling the rich diversity of garments and body shapes and poses. We propose a framework for text-guided full-body human image synthesis via an attention-based latent code mapper, which enables more disentangled control of StyleGAN than existing mappers. Our latent code mapper adopts an attention mechanism that adaptively manipulates individual latent codes on different StyleGAN layers under text guidance. In addition, we introduce feature-space masking at inference time to avoid unwanted changes caused by text inputs. Our quantitative and qualitative evaluations reveal that our method can control generated images more faithfully to given texts than existing methods.
Objective: To evaluate the efficiency of large language models (LLMs) such as ChatGPT to assist in diagnosing neuro-ophthalmic diseases based on detailed case descriptions. Methods: We selected 22 different case reports of neuro-ophthalmic diseases from a publicly available online database. These cases included a wide range of chronic and acute diseases that are commonly seen by neuro-ophthalmic sub-specialists. We inserted the text from each case as a new prompt into both ChatGPT v3.5 and ChatGPT Plus v4.0 and asked for the most probable diagnosis. We then presented the exact information to two neuro-ophthalmologists and recorded their diagnoses followed by comparison to responses from both versions of ChatGPT. Results: ChatGPT v3.5, ChatGPT Plus v4.0, and the two neuro-ophthalmologists were correct in 13 (59%), 18 (82%), 19 (86%), and 19 (86%) out of 22 cases, respectively. The agreement between the various diagnostic sources were as follows: ChatGPT v3.5 and ChatGPT Plus v4.0, 13 (59%); ChatGPT v3.5 and the first neuro-ophthalmologist, 12 (55%); ChatGPT v3.5 and the second neuro-ophthalmologist, 12 (55%); ChatGPT Plus v4.0 and the first neuro-ophthalmologist, 17 (77%); ChatGPT Plus v4.0 and the second neuro-ophthalmologist, 16 (73%); and first and second neuro-ophthalmologists 17 (17%). Conclusions: The accuracy of ChatGPT v3.5 and ChatGPT Plus v4.0 in diagnosing patients with neuro-ophthalmic diseases was 59% and 82%, respectively. With further development, ChatGPT Plus v4.0 may have potential to be used in clinical care settings to assist clinicians in providing quick, accurate diagnoses of patients in neuro-ophthalmology. The applicability of using LLMs like ChatGPT in clinical settings that lack access to subspeciality trained neuro-ophthalmologists deserves further research.