MoPE: Parameter-Efficient and Scalable Multimodal Fusion via Mixture of Prompt Experts

Prompt-tuning has demonstrated parameter-efficiency in fusing unimodal foundation models for multimodal tasks. However, its limited adaptivity and expressiveness lead to suboptimal performance when compared with other tuning methods. In this paper, we address this issue by disentangling the vanilla prompts to adaptively capture dataset-level and instance-level features. Building upon this disentanglement, we introduce the mixture of prompt experts (MoPE) technique to enhance expressiveness. MoPE leverages multimodal pairing priors to route the most effective prompt on a per-instance basis. Compared to vanilla prompting, our MoPE-based conditional prompting exhibits greater expressiveness for multimodal fusion, scaling better with the training data and the overall number of trainable parameters. We also study a regularization term for expert routing, leading to emergent expert specialization, where different experts focus on different concepts, enabling interpretable soft prompting. Extensive experiments across three multimodal datasets demonstrate that our method achieves state-of-the-art results, matching or even surpassing the performance of fine-tuning, while requiring only 0.8% of the trainable parameters. Code will be released: https://github.com/songrise/MoPE.

GPT4SGG: Synthesizing Scene Graphs from Holistic and Region-specific Narratives

Learning scene graphs from natural language descriptions has proven to be a cheap and promising scheme for Scene Graph Generation (SGG). However, such unstructured caption data and its processing are troubling the learning an acurrate and complete scene graph. This dilema can be summarized as three points. First, traditional language parsers often fail to extract meaningful relationship triplets from caption data. Second, grounding unlocalized objects in parsed triplets will meet ambiguity in visual-language alignment. Last, caption data typically are sparse and exhibit bias to partial observations of image content. These three issues make it hard for the model to generate comprehensive and accurate scene graphs. To fill this gap, we propose a simple yet effective framework, GPT4SGG, to synthesize scene graphs from holistic and region-specific narratives. The framework discards traditional language parser, and localize objects before obtaining relationship triplets. To obtain relationship triplets, holistic and dense region-specific narratives are generated from the image. With such textual representation of image data and a task-specific prompt, an LLM, particularly GPT-4, directly synthesizes a scene graph as "pseudo labels". Experimental results showcase GPT4SGG significantly improves the performance of SGG models trained on image-caption data. We believe this pioneering work can motivate further research into mining the visual reasoning capabilities of LLMs.

Conditional Prompt Tuning for Multimodal Fusion

We show that the representation of one modality can effectively guide the prompting of another modality for parameter-efficient multimodal fusion. Specifically, we first encode one modality and use its representation as a prior to conditionally prompt all frozen layers of the other modality. This is achieved by disentangling the vanilla prompt vectors into three types of specialized prompts that adaptively capture global-level and instance-level features. To better produce the instance-wise prompt, we introduce the mixture of prompt experts (MoPE) to dynamically route each instance to the most suitable prompt experts for encoding. We further study a regularization term to avoid degenerated prompt expert routing. Thanks to our design, our method can effectively transfer the pretrained knowledge in unimodal encoders for downstream multimodal tasks. Compared with vanilla prompting, we show that our MoPE-based conditional prompting is more expressive, thereby scales better with training data and the total number of prompts. We also demonstrate that our prompt tuning is architecture-agnostic, thereby offering high modularity. Extensive experiments over three multimodal datasets demonstrate state-of-the-art results, matching or surpassing the performance achieved through fine-tuning, while only necessitating 0.7% of the trainable parameters. Code will be released: https://github.com/songrise/ConditionalPrompt.

Expanding Scene Graph Boundaries: Fully Open-vocabulary Scene Graph Generation via Visual-Concept Alignment and Retention

Scene Graph Generation (SGG) offers a structured representation critical in many computer vision applications. Traditional SGG approaches, however, are limited by a closed-set assumption, restricting their ability to recognize only predefined object and relation categories. To overcome this, we categorize SGG scenarios into four distinct settings based on the node and edge: Closed-set SGG, Open Vocabulary (object) Detection-based SGG (OvD-SGG), Open Vocabulary Relation-based SGG (OvR-SGG), and Open Vocabulary Detection + Relation-based SGG (OvD+R-SGG). While object-centric open vocabulary SGG has been studied recently, the more challenging problem of relation-involved open-vocabulary SGG remains relatively unexplored. To fill this gap, we propose a unified framework named OvSGTR towards fully open vocabulary SGG from a holistic view. The proposed framework is an end-toend transformer architecture, which learns a visual-concept alignment for both nodes and edges, enabling the model to recognize unseen categories. For the more challenging settings of relation-involved open vocabulary SGG, the proposed approach integrates relation-aware pre-training utilizing image-caption data and retains visual-concept alignment through knowledge distillation. Comprehensive experimental results on the Visual Genome benchmark demonstrate the effectiveness and superiority of the proposed framework.

CLIP-Count: Towards Text-Guided Zero-Shot Object Counting

Recent advances in visual-language models have shown remarkable zero-shot text-image matching ability that is transferable to down-stream tasks such as object detection and segmentation. However, adapting these models for object counting, which involves estimating the number of objects in an image, remains a formidable challenge. In this study, we conduct the first exploration of transferring visual-language models for class-agnostic object counting. Specifically, we propose CLIP-Count, a novel pipeline that estimates density maps for open-vocabulary objects with text guidance in a zero-shot manner, without requiring any finetuning on specific object classes. To align the text embedding with dense image features, we introduce a patch-text contrastive loss that guides the model to learn informative patch-level image representations for dense prediction. Moreover, we design a hierarchical patch-text interaction module that propagates semantic information across different resolution levels of image features. Benefiting from the full exploitation of the rich image-text alignment knowledge of pretrained visual-language models, our method effectively generates high-quality density maps for objects-of-interest. Extensive experiments on FSC-147, CARPK, and ShanghaiTech crowd counting datasets demonstrate that our proposed method achieves state-of-the-art accuracy and generalizability for zero-shot object counting. Project page at https://github.com/songrise/CLIP-Count

Fast-ParC: Position Aware Global Kernel for ConvNets and ViTs

Transformer models have made tremendous progress in various fields in recent years. In the field of computer vision, vision transformers (ViTs) also become strong alternatives to convolutional neural networks (ConvNets), yet they have not been able to replace ConvNets since both have their own merits. For instance, ViTs are good at extracting global features with attention mechanisms while ConvNets are more efficient in modeling local relationships due to their strong inductive bias. A natural idea that arises is to combine the strengths of both ConvNets and ViTs to design new structures. In this paper, we propose a new basic neural network operator named position-aware circular convolution (ParC) and its accelerated version Fast-ParC. The ParC operator can capture global features by using a global kernel and circular convolution while keeping location sensitiveness by employing position embeddings. Our Fast-ParC further reduces the O(n2) time complexity of ParC to O(n log n) using Fast Fourier Transform. This acceleration makes it possible to use global convolution in the early stages of models with large feature maps, yet still maintains the overall computational cost comparable with using 3x3 or 7x7 kernels. The proposed operation can be used in a plug-and-play manner to 1) convert ViTs to pure-ConvNet architecture to enjoy wider hardware support and achieve higher inference speed; 2) replacing traditional convolutions in the deep stage of ConvNets to improve accuracy by enlarging the effective receptive field. Experiment results show that our ParC op can effectively enlarge the receptive field of traditional ConvNets, and adopting the proposed op benefits both ViTs and ConvNet models on all three popular vision tasks, image classification, object

Prompt-based Learning for Unpaired Image Captioning

Unpaired Image Captioning (UIC) has been developed to learn image descriptions from unaligned vision-language sample pairs. Existing schemes usually adopt the visual concept reward of reinforcement learning to obtain the alignment between visual concepts and images. However, the cross-domain alignment is usually weak that severely constrains the overall performance of these existing schemes. Recent successes of Vision-Language Pre-Trained Models (VL-PTMs) have triggered the development of prompt-based learning from VL-PTMs. We present in this paper a novel scheme based on prompt to train the UIC model, making best use of the powerful generalization ability and abundant vision-language prior knowledge learned under VL-PTMs. We adopt the CLIP model for this research in unpaired image captioning. Specifically, the visual images are taken as input to the prompt generation module, which contains the pre-trained model as well as one feed-forward layer for prompt extraction. Then, the input images and generated prompts are aggregated for unpaired adversarial captioning learning. To further enhance the potential performance of the captioning, we designed a high-quality pseudo caption filter guided by the CLIP logits to measure correlations between predicted captions and the corresponding images. This allows us to improve the captioning model in a supervised learning manner. Extensive experiments on the COCO and Flickr30K datasets have been carried out to validate the superiority of the proposed model. We have achieved the state-of-the-art performance on the COCO dataset, which outperforms the best UIC model by 1.9% on the BLEU-4 metric. We expect that the proposed prompt-based UIC model will inspire a new line of research for the VL-PTMs based captioning.

Unpaired Image Captioning by Image-level Weakly-Supervised Visual Concept Recognition

The goal of unpaired image captioning (UIC) is to describe images without using image-caption pairs in the training phase. Although challenging, we except the task can be accomplished by leveraging a training set of images aligned with visual concepts. Most existing studies use off-the-shelf algorithms to obtain the visual concepts because the Bounding Box (BBox) labels or relationship-triplet labels used for the training are expensive to acquire. In order to resolve the problem in expensive annotations, we propose a novel approach to achieve cost-effective UIC. Specifically, we adopt image-level labels for the optimization of the UIC model in a weakly-supervised manner. For each image, we assume that only the image-level labels are available without specific locations and numbers. The image-level labels are utilized to train a weakly-supervised object recognition model to extract object information (e.g., instance) in an image, and the extracted instances are adopted to infer the relationships among different objects based on an enhanced graph neural network (GNN). The proposed approach achieves comparable or even better performance compared with previous methods without the expensive cost of annotations. Furthermore, we design an unrecognized object (UnO) loss combined with a visual concept reward to improve the alignment of the inferred object and relationship information with the images. It can effectively alleviate the issue encountered by existing UIC models about generating sentences with nonexistent objects. To the best of our knowledge, this is the first attempt to solve the problem of Weakly-Supervised visual concept recognition for UIC (WS-UIC) based only on image-level labels. Extensive experiments have been carried out to demonstrate that the proposed WS-UIC model achieves inspiring results on the COCO dataset while significantly reducing the cost of labeling.