Multi-turn compositional image generation (M-CIG) is a challenging task that aims to iteratively manipulate a reference image given a modification text. While most of the existing methods for M-CIG are based on generative adversarial networks (GANs), recent advances in image generation have demonstrated the superiority of diffusion models over GANs. In this paper, we propose a diffusion-based method for M-CIG named conditional denoising diffusion with image compositional matching (CDD-ICM). We leverage CLIP as the backbone of image and text encoders, and incorporate a gated fusion mechanism, originally proposed for question answering, to compositionally fuse the reference image and the modification text at each turn of M-CIG. We introduce a conditioning scheme to generate the target image based on the fusion results. To prioritize the semantic quality of the generated target image, we learn an auxiliary image compositional match (ICM) objective, along with the conditional denoising diffusion (CDD) objective in a multi-task learning framework. Additionally, we also perform ICM guidance and classifier-free guidance to improve performance. Experimental results show that CDD-ICM achieves state-of-the-art results on two benchmark datasets for M-CIG, i.e., CoDraw and i-CLEVR.
Lung nodule malignancy prediction has been enhanced by advanced deep-learning techniques and effective tricks. Nevertheless, current methods are mainly trained with cross-entropy loss using one-hot categorical labels, which results in difficulty in distinguishing those nodules with closer progression labels. Interestingly, we observe that clinical text information annotated by radiologists provides us with discriminative knowledge to identify challenging samples. Drawing on the capability of the contrastive language-image pre-training (CLIP) model to learn generalized visual representations from text annotations, in this paper, we propose CLIP-Lung, a textual knowledge-guided framework for lung nodule malignancy prediction. First, CLIP-Lung introduces both class and attribute annotations into the training of the lung nodule classifier without any additional overheads in inference. Second, we designed a channel-wise conditional prompt (CCP) module to establish consistent relationships between learnable context prompts and specific feature maps. Third, we align image features with both class and attribute features via contrastive learning, rectifying false positives and false negatives in latent space. The experimental results on the benchmark LIDC-IDRI dataset have demonstrated the superiority of CLIP-Lung, both in classification performance and interpretability of attention maps.
This is a speculative essay on interface design and artificial intelligence. Recently there has been a surge of attention to chatbots based on large language models, including widely reported unsavory interactions. We contend that part of the problem is that text is not all you need: sophisticated AI systems should have dashboards, just like all other complicated devices. Assuming the hypothesis that AI systems based on neural networks will contain interpretable models of aspects of the world around them, we discuss what data such dashboards might display. We conjecture that, for many systems, the two most important models will be of the user and of the system itself. We call these the System Model and User Model. We argue that, for usability and safety, interfaces to dialogue-based AI systems should have a parallel display based on the state of the System Model and the User Model. Finding ways to identify, interpret, and display these two models should be a core part of interface research for AI.
The recent introduction of ChatGPT has drawn significant attention from both industry and academia due to its impressive capabilities in solving a diverse range of tasks, including language translation, text summarization, and computer programming. Its capability for writing, modifying, and even correcting code together with its ease of use and access is already dramatically impacting computer science education. This paper aims to explore how well ChatGPT can perform in an introductory-level functional language programming course. In our systematic evaluation, we treated ChatGPT as one of our students and demonstrated that it can achieve a grade B- and its rank in the class is 155 out of 314 students overall. Our comprehensive evaluation provides valuable insights into ChatGPT's impact from both student and instructor perspectives. Additionally, we identify several potential benefits that ChatGPT can offer to both groups. Overall, we believe that this study significantly clarifies and advances our understanding of ChatGPT's capabilities and potential impact on computer science education.
In-context learning (ICL) unfolds as large language models become capable of inferring test labels conditioned on a few labeled samples without any gradient update. ICL-enabled large language models provide a promising step forward toward bypassing recurrent annotation costs in a low-resource setting. Yet, only a handful of past studies have explored ICL in a cross-lingual setting, in which the need for transferring label-knowledge from a high-resource language to a low-resource one is immensely crucial. To bridge the gap, we provide the first in-depth analysis of ICL for cross-lingual text classification. We find that the prevalent mode of selecting random input-label pairs to construct the prompt-context is severely limited in the case of cross-lingual ICL, primarily due to the lack of alignment in the input as well as the output spaces. To mitigate this, we propose a novel prompt construction strategy -- Cross-lingual In-context Source-Target Alignment (X-InSTA). With an injected coherence in the semantics of the input examples and a task-based alignment across the source and target languages, X-InSTA is able to outperform random prompt selection by a large margin across three different tasks using 44 different cross-lingual pairs.
Outside-knowledge visual question answering is a challenging task that requires both the acquisition and the use of open-ended real-world knowledge. Some existing solutions draw external knowledge into the cross-modality space which overlooks the much vaster textual knowledge in natural-language space, while others transform the image into a text that further fuses with the textual knowledge into the natural-language space and completely abandons the use of visual features. In this paper, we are inspired to constrain the cross-modality space into the same space of natural-language space which makes the visual features preserved directly, and the model still benefits from the vast knowledge in natural-language space. To this end, we propose a novel framework consisting of a multimodal encoder, a textual encoder and an answer decoder. Such structure allows us to introduce more types of knowledge including explicit and implicit multimodal and textual knowledge. Extensive experiments validate the superiority of the proposed method which outperforms the state-of-the-art by 6.17% accuracy. We also conduct comprehensive ablations of each component, and systematically study the roles of varying types of knowledge. Codes and knowledge data can be found at https://github.com/PhoebusSi/Thinking-while-Observing.
Inference-time adaptation methods for semantic parsing are useful for leveraging examples from newly-observed domains without repeated fine-tuning. Existing approaches typically bias the decoder by simply concatenating input-output example pairs (cases) from the new domain at the encoder's input in a Seq-to-Seq model. Such methods cannot adequately leverage the structure of logical forms in the case examples. We propose StructCBR, a structured case-based reasoning approach, which leverages subtree-level similarity between logical forms of cases and candidate outputs, resulting in better decoder decisions. For the task of adapting Text-to-SQL models to unseen schemas, we show that exploiting case examples in a structured manner via StructCBR offers consistent performance improvements over prior inference-time adaptation methods across five different databases. To the best of our knowledge, we are the first to attempt inference-time adaptation of Text-to-SQL models, and harness trainable structured similarity between subqueries.
Long-tailed multi-label visual recognition (LTML) task is a highly challenging task due to the label co-occurrence and imbalanced data distribution. In this work, we propose a unified framework for LTML, namely prompt tuning with class-specific embedding loss (LMPT), capturing the semantic feature interactions between categories by combining text and image modality data and improving the performance synchronously on both head and tail classes. Specifically, LMPT introduces the embedding loss function with class-aware soft margin and re-weighting to learn class-specific contexts with the benefit of textual descriptions (captions), which could help establish semantic relationships between classes, especially between the head and tail classes. Furthermore, taking into account the class imbalance, the distribution-balanced loss is adopted as the classification loss function to further improve the performance on the tail classes without compromising head classes. Extensive experiments are conducted on VOC-LT and COCO-LT datasets, which demonstrates that the proposed method significantly surpasses the previous state-of-the-art methods and zero-shot CLIP in LTML. Our codes are fully available at \url{https://github.com/richard-peng-xia/LMPT}.
Pre-trained transformers are popular in state-of-the-art dialogue generation (DG) systems. Such language models are, however, vulnerable to various adversarial samples as studied in traditional tasks such as text classification, which inspires our curiosity about their robustness in DG systems. One main challenge of attacking DG models is that perturbations on the current sentence can hardly degrade the response accuracy because the unchanged chat histories are also considered for decision-making. Instead of merely pursuing pitfalls of performance metrics such as BLEU, ROUGE, we observe that crafting adversarial samples to force longer generation outputs benefits attack effectiveness -- the generated responses are typically irrelevant, lengthy, and repetitive. To this end, we propose a white-box multi-objective attack method called DGSlow. Specifically, DGSlow balances two objectives -- generation accuracy and length, via a gradient-based multi-objective optimizer and applies an adaptive searching mechanism to iteratively craft adversarial samples with only a few modifications. Comprehensive experiments on four benchmark datasets demonstrate that DGSlow could significantly degrade state-of-the-art DG models with a higher success rate than traditional accuracy-based methods. Besides, our crafted sentences also exhibit strong transferability in attacking other models.
Controllable image captioning is an emerging multimodal topic that aims to describe the image with natural language following human purpose, $\textit{e.g.}$, looking at the specified regions or telling in a particular text style. State-of-the-art methods are trained on annotated pairs of input controls and output captions. However, the scarcity of such well-annotated multimodal data largely limits their usability and scalability for interactive AI systems. Leveraging unimodal instruction-following foundation models is a promising alternative that benefits from broader sources of data. In this paper, we present Caption AnyThing (CAT), a foundation model augmented image captioning framework supporting a wide range of multimodel controls: 1) visual controls, including points, boxes, and trajectories; 2) language controls, such as sentiment, length, language, and factuality. Powered by Segment Anything Model (SAM) and ChatGPT, we unify the visual and language prompts into a modularized framework, enabling the flexible combination between different controls. Extensive case studies demonstrate the user intention alignment capabilities of our framework, shedding light on effective user interaction modeling in vision-language applications. Our code is publicly available at https://github.com/ttengwang/Caption-Anything.