Multimodal learning aims to imitate human beings to acquire complementary information from multiple modalities for various downstream tasks. However, traditional aggregation-based multimodal fusion methods ignore the inter-modality relationship, treat each modality equally, suffer sensor noise, and thus reduce multimodal learning performance. In this work, we propose a novel multimodal contrastive method to explore more reliable multimodal representations under the weak supervision of unimodal predicting. Specifically, we first capture task-related unimodal representations and the unimodal predictions from the introduced unimodal predicting task. Then the unimodal representations are aligned with the more effective one by the designed multimodal contrastive method under the supervision of the unimodal predictions. Experimental results with fused features on two image-text classification benchmarks UPMC-Food-101 and N24News show that our proposed Unimodality-Supervised MultiModal Contrastive UniS-MMC learning method outperforms current state-of-the-art multimodal methods. The detailed ablation study and analysis further demonstrate the advantage of our proposed method.
Recent object detection approaches rely on pretrained vision-language models for image-text alignment. However, they fail to detect the Mobile User Interface (MUI) element since it contains additional OCR information, which describes its content and function but is often ignored. In this paper, we develop a new MUI element detection dataset named MUI-zh and propose an Adaptively Prompt Tuning (APT) module to take advantage of discriminating OCR information. APT is a lightweight and effective module to jointly optimize category prompts across different modalities. For every element, APT uniformly encodes its visual features and OCR descriptions to dynamically adjust the representation of frozen category prompts. We evaluate the effectiveness of our plug-and-play APT upon several existing CLIP-based detectors for both standard and open-vocabulary MUI element detection. Extensive experiments show that our method achieves considerable improvements on two datasets. The datasets is available at \url{github.com/antmachineintelligence/MUI-zh}.
Diffusion models, either with or without text condition, have demonstrated impressive capability in synthesizing photorealistic images given a few or even no words. These models may not fully satisfy user need, as normal users or artists intend to control the synthesized images with specific guidance, like overall layout, color, structure, object shape, and so on. To adapt diffusion models for controllable image synthesis, several methods have been proposed to incorporate the required conditions as regularization upon the intermediate features of the diffusion denoising network. These methods, known as early-constraint ones in this paper, have difficulties in handling multiple conditions with a single solution. They intend to train separate models for each specific condition, which require much training cost and result in non-generalizable solutions. To address these difficulties, we propose a new approach namely late-constraint: we leave the diffusion networks unchanged, but constrain its output to be aligned with the required conditions. Specifically, we train a lightweight condition adapter to establish the correlation between external conditions and internal representations of diffusion models. During the iterative denoising process, the conditional guidance is sent into corresponding condition adapter to manipulate the sampling process with the established correlation. We further equip the introduced late-constraint strategy with a timestep resampling method and an early stopping technique, which boost the quality of synthesized image meanwhile complying with the guidance. Our method outperforms the existing early-constraint methods and generalizes better to unseen condition.
We introduce the logical grammar emdebbing (LGE), a model inspired by pregroup grammars and categorial grammars to enable unsupervised inference of lexical categories and syntactic rules from a corpus of text. LGE produces comprehensible output summarizing its inferences, has a completely transparent process for producing novel sentences, and can learn from as few as a hundred sentences.
To help the visually impaired enjoy movies, automatic movie narrating systems are expected to narrate accurate, coherent, and role-aware plots when there are no speaking lines of actors. Existing works benchmark this challenge as a normal video captioning task via some simplifications, such as removing role names and evaluating narrations with ngram-based metrics, which makes it difficult for automatic systems to meet the needs of real application scenarios. To narrow this gap, we construct a large-scale Chinese movie benchmark, named Movie101. Closer to real scenarios, the Movie Clip Narrating (MCN) task in our benchmark asks models to generate role-aware narration paragraphs for complete movie clips where no actors are speaking. External knowledge, such as role information and movie genres, is also provided for better movie understanding. Besides, we propose a new metric called Movie Narration Score (MNScore) for movie narrating evaluation, which achieves the best correlation with human evaluation. Our benchmark also supports the Temporal Narration Grounding (TNG) task to investigate clip localization given text descriptions. For both two tasks, our proposed methods well leverage external knowledge and outperform carefully designed baselines. The dataset and codes are released at https://github.com/yuezih/Movie101.
Multimodal Named Entity Recognition (MNER) on social media aims to enhance textual entity prediction by incorporating image-based clues. Existing research in this domain has primarily focused on maximizing the utilization of potentially relevant information in images or incorporating external knowledge from explicit knowledge bases (KBs). However, these methods either neglect the necessity of providing the model with relevant external knowledge, or the retrieved external knowledge suffers from high redundancy. To address these problems, we propose a conceptually simple two-stage framework called Prompt ChatGPT In MNER (PGIM) in this paper. We leverage ChatGPT as an implicit knowledge engine to acquire auxiliary refined knowledge, thereby bolstering the model's performance in MNER tasks. Specifically, we first utilize a Multimodal Similar Example Awareness module to select suitable examples from a small number of manually annotated samples. These examples are then integrated into a formatted prompt template tailored to the MNER task, guiding ChatGPT to generate auxiliary refined knowledge. Finally, the acquired knowledge is integrated with the raw text and inputted into the downstream model for further processing. Extensive experiments show that our PGIM significantly outperforms all existing state-of-the-art methods on two classic MNER datasets.
Our goal is to synthesize 3D human motions given textual inputs describing simultaneous actions, for example 'waving hand' while 'walking' at the same time. We refer to generating such simultaneous movements as performing 'spatial compositions'. In contrast to temporal compositions that seek to transition from one action to another, spatial compositing requires understanding which body parts are involved in which action, to be able to move them simultaneously. Motivated by the observation that the correspondence between actions and body parts is encoded in powerful language models, we extract this knowledge by prompting GPT-3 with text such as "what are the body parts involved in the action <action name>?", while also providing the parts list and few-shot examples. Given this action-part mapping, we combine body parts from two motions together and establish the first automated method to spatially compose two actions. However, training data with compositional actions is always limited by the combinatorics. Hence, we further create synthetic data with this approach, and use it to train a new state-of-the-art text-to-motion generation model, called SINC ("SImultaneous actioN Compositions for 3D human motions"). In our experiments, we find training on additional synthetic GPT-guided compositional motions improves text-to-motion generation.
Contrastive learning-based methods, such as unsup-SimCSE, have achieved state-of-the-art (SOTA) performances in learning unsupervised sentence embeddings. However, in previous studies, each embedding used for contrastive learning only derived from one sentence instance, and we call these embeddings instance-level embeddings. In other words, each embedding is regarded as a unique class of its own, whichmay hurt the generalization performance. In this study, we propose IS-CSE (instance smoothing contrastive sentence embedding) to smooth the boundaries of embeddings in the feature space. Specifically, we retrieve embeddings from a dynamic memory buffer according to the semantic similarity to get a positive embedding group. Then embeddings in the group are aggregated by a self-attention operation to produce a smoothed instance embedding for further analysis. We evaluate our method on standard semantic text similarity (STS) tasks and achieve an average of 78.30%, 79.47%, 77.73%, and 79.42% Spearman's correlation on the base of BERT-base, BERT-large, RoBERTa-base, and RoBERTa-large respectively, a 2.05%, 1.06%, 1.16% and 0.52% improvement compared to unsup-SimCSE.
Recently, model-based retrieval has emerged as a new paradigm in text retrieval that discards the index in the traditional retrieval model and instead memorizes the candidate corpora using model parameters. This design employs a sequence-to-sequence paradigm to generate document identifiers, which enables the complete capture of the relevance between queries and documents and simplifies the classic indexretrieval-rerank pipeline. Despite its attractive qualities, there remain several major challenges in model-based retrieval, including the discrepancy between pre-training and fine-tuning, and the discrepancy between training and inference. To deal with the above challenges, we propose a novel two-stage model-based retrieval approach called TOME, which makes two major technical contributions, including the utilization of tokenized URLs as identifiers and the design of a two-stage generation architecture. We also propose a number of training strategies to deal with the training difficulty as the corpus size increases. Extensive experiments and analysis on MS MARCO and Natural Questions demonstrate the effectiveness of our proposed approach, and we investigate the scaling laws of TOME by examining various influencing factors.
The in-context learning capabilities of LLMs like GPT-3 allow annotators to customize an LLM to their specific tasks with a small number of examples. However, users tend to include only the most obvious patterns when crafting examples, resulting in underspecified in-context functions that fall short on unseen cases. Further, it is hard to know when "enough" examples have been included even for known patterns. In this work, we present ScatterShot, an interactive system for building high-quality demonstration sets for in-context learning. ScatterShot iteratively slices unlabeled data into task-specific patterns, samples informative inputs from underexplored or not-yet-saturated slices in an active learning manner, and helps users label more efficiently with the help of an LLM and the current example set. In simulation studies on two text perturbation scenarios, ScatterShot sampling improves the resulting few-shot functions by 4-5 percentage points over random sampling, with less variance as more examples are added. In a user study, ScatterShot greatly helps users in covering different patterns in the input space and labeling in-context examples more efficiently, resulting in better in-context learning and less user effort.