Causal Graphical Models for Vision-Language Compositional Understanding

Recent work has empirically shown that Vision-Language Models (VLMs) struggle to fully understand the compositional properties of the human language, usually modeling an image caption as a "bag of words". As a result, they perform poorly on compositional tasks, which require a deeper understanding of the different entities of a sentence (subject, verb, etc.) jointly with their mutual relationships in order to be solved. In this paper, we model the dependency relations among textual and visual tokens using a Causal Graphical Model (CGM), built using a dependency parser, and we train a decoder conditioned by the VLM visual encoder. Differently from standard autoregressive or parallel predictions, our decoder's generative process is partially-ordered following the CGM structure. This structure encourages the decoder to learn only the main causal dependencies in a sentence discarding spurious correlations. Using extensive experiments on five compositional benchmarks, we show that our method significantly outperforms all the state-of-the-art compositional approaches by a large margin, and it also improves over methods trained using much larger datasets.

Personalizing Multimodal Large Language Models for Image Captioning: An Experimental Analysis

The task of image captioning demands an algorithm to generate natural language descriptions of visual inputs. Recent advancements have seen a convergence between image captioning research and the development of Large Language Models (LLMs) and Multimodal LLMs -- like GPT-4V and Gemini -- which extend the capabilities of text-only LLMs to multiple modalities. This paper investigates whether Multimodal LLMs can supplant traditional image captioning networks by evaluating their performance on various image description benchmarks. We explore both the zero-shot capabilities of these models and their adaptability to different semantic domains through fine-tuning methods, including prompt learning, prefix tuning, and low-rank adaptation. Our results demonstrate that while Multimodal LLMs achieve impressive zero-shot performance, fine-tuning for specific domains while maintaining their generalization capabilities intact remains challenging. We discuss the implications of these findings for future research in image captioning and the development of more adaptable Multimodal LLMs.

Talking to DINO: Bridging Self-Supervised Vision Backbones with Language for Open-Vocabulary Segmentation

Open-Vocabulary Segmentation (OVS) aims at segmenting images from free-form textual concepts without predefined training classes. While existing vision-language models such as CLIP can generate segmentation masks by leveraging coarse spatial information from Vision Transformers, they face challenges in spatial localization due to their global alignment of image and text features. Conversely, self-supervised visual models like DINO excel in fine-grained visual encoding but lack integration with language. To bridge this gap, we present Talk2DINO, a novel hybrid approach that combines the spatial accuracy of DINOv2 with the language understanding of CLIP. Our approach aligns the textual embeddings of CLIP to the patch-level features of DINOv2 through a learned mapping function without the need to fine-tune the underlying backbones. At training time, we exploit the attention maps of DINOv2 to selectively align local visual patches with textual embeddings. We show that the powerful semantic and localization abilities of Talk2DINO can enhance the segmentation process, resulting in more natural and less noisy segmentations, and that our approach can also effectively distinguish foreground objects from the background. Experimental results demonstrate that Talk2DINO achieves state-of-the-art performance across several unsupervised OVS benchmarks. Source code and models are publicly available at: https://lorebianchi98.github.io/Talk2DINO/.

Augmenting Multimodal LLMs with Self-Reflective Tokens for Knowledge-based Visual Question Answering

Multimodal LLMs (MLLMs) are the natural extension of large language models to handle multimodal inputs, combining text and image data. They have recently garnered attention due to their capability to address complex tasks involving both modalities. However, their effectiveness is limited to the knowledge acquired during training, which restricts their practical utility. In this work, we introduce a novel method to enhance the adaptability of MLLMs by integrating external knowledge sources. Our proposed model, Reflective LLaVA (ReflectiVA), utilizes reflective tokens to dynamically determine the need for external knowledge and predict the relevance of information retrieved from an external database. Tokens are trained following a two-stage two-model training recipe. This ultimately enables the MLLM to manage external knowledge while preserving fluency and performance on tasks where external knowledge is not needed. Through our experiments, we demonstrate the efficacy of ReflectiVA for knowledge-based visual question answering, highlighting its superior performance compared to existing methods. Source code and trained models are publicly available at https://github.com/aimagelab/ReflectiVA.

Personalized Instance-based Navigation Toward User-Specific Objects in Realistic Environments

In the last years, the research interest in visual navigation towards objects in indoor environments has grown significantly. This growth can be attributed to the recent availability of large navigation datasets in photo-realistic simulated environments, like Gibson and Matterport3D. However, the navigation tasks supported by these datasets are often restricted to the objects present in the environment at acquisition time. Also, they fail to account for the realistic scenario in which the target object is a user-specific instance that can be easily confused with similar objects and may be found in multiple locations within the environment. To address these limitations, we propose a new task denominated Personalized Instance-based Navigation (PIN), in which an embodied agent is tasked with locating and reaching a specific personal object by distinguishing it among multiple instances of the same category. The task is accompanied by PInNED, a dedicated new dataset composed of photo-realistic scenes augmented with additional 3D objects. In each episode, the target object is presented to the agent using two modalities: a set of visual reference images on a neutral background and manually annotated textual descriptions. Through comprehensive evaluations and analyses, we showcase the challenges of the PIN task as well as the performance and shortcomings of currently available methods designed for object-driven navigation, considering modular and end-to-end agents.

Positive-Augmented Contrastive Learning for Vision-and-Language Evaluation and Training

Despite significant advancements in caption generation, existing evaluation metrics often fail to capture the full quality or fine-grained details of captions. This is mainly due to their reliance on non-specific human-written references or noisy pre-training data. Still, finding an effective metric is crucial not only for captions evaluation but also for the generation phase. Metrics can indeed play a key role in the fine-tuning stage of captioning models, ultimately enhancing the quality of the generated captions. In this paper, we propose PAC-S++, a learnable metric that leverages the CLIP model, pre-trained on both web-collected and cleaned data and regularized through additional pairs of generated visual and textual positive samples. Exploiting this stronger and curated pre-training, we also apply PAC-S++ as a reward in the Self-Critical Sequence Training (SCST) stage typically employed to fine-tune captioning models. Extensive experiments on different image and video datasets highlight the effectiveness of PAC-S++ compared to popular metrics for the task, including its sensitivity to object hallucinations. Furthermore, we show that integrating PAC-S++ into the fine-tuning stage of a captioning model results in semantically richer captions with fewer repetitions and grammatical errors. Evaluations on out-of-domain benchmarks further demonstrate the efficacy of our fine-tuning approach in enhancing model capabilities. Source code and trained models are publicly available at: https://github.com/aimagelab/pacscore.

Optimizing Resource Consumption in Diffusion Models through Hallucination Early Detection

Diffusion models have significantly advanced generative AI, but they encounter difficulties when generating complex combinations of multiple objects. As the final result heavily depends on the initial seed, accurately ensuring the desired output can require multiple iterations of the generation process. This repetition not only leads to a waste of time but also increases energy consumption, echoing the challenges of efficiency and accuracy in complex generative tasks. To tackle this issue, we introduce HEaD (Hallucination Early Detection), a new paradigm designed to swiftly detect incorrect generations at the beginning of the diffusion process. The HEaD pipeline combines cross-attention maps with a new indicator, the Predicted Final Image, to forecast the final outcome by leveraging the information available at early stages of the generation process. We demonstrate that using HEaD saves computational resources and accelerates the generation process to get a complete image, i.e. an image where all requested objects are accurately depicted. Our findings reveal that HEaD can save up to 12% of the generation time on a two objects scenario and underscore the importance of early detection mechanisms in generative models.

Fluent and Accurate Image Captioning with a Self-Trained Reward Model

Fine-tuning image captioning models with hand-crafted rewards like the CIDEr metric has been a classical strategy for promoting caption quality at the sequence level. This approach, however, is known to limit descriptiveness and semantic richness and tends to drive the model towards the style of ground-truth sentences, thus losing detail and specificity. On the contrary, recent attempts to employ image-text models like CLIP as reward have led to grammatically incorrect and repetitive captions. In this paper, we propose Self-Cap, a captioning approach that relies on a learnable reward model based on self-generated negatives that can discriminate captions based on their consistency with the image. Specifically, our discriminator is a fine-tuned contrastive image-text model trained to promote caption correctness while avoiding the aberrations that typically happen when training with a CLIP-based reward. To this end, our discriminator directly incorporates negative samples from a frozen captioner, which significantly improves the quality and richness of the generated captions but also reduces the fine-tuning time in comparison to using the CIDEr score as the sole metric for optimization. Experimental results demonstrate the effectiveness of our training strategy on both standard and zero-shot image captioning datasets.

Revisiting Image Captioning Training Paradigm via Direct CLIP-based Optimization

The conventional training approach for image captioning involves pre-training a network using teacher forcing and subsequent fine-tuning with Self-Critical Sequence Training to maximize hand-crafted captioning metrics. However, when attempting to optimize modern and higher-quality metrics like CLIP-Score and PAC-Score, this training method often encounters instability and fails to acquire the genuine descriptive capabilities needed to produce fluent and informative captions. In this paper, we propose a new training paradigm termed Direct CLIP-Based Optimization (DiCO). Our approach jointly learns and optimizes a reward model that is distilled from a learnable captioning evaluator with high human correlation. This is done by solving a weighted classification problem directly inside the captioner. At the same time, DiCO prevents divergence from the original model, ensuring that fluency is maintained. DiCO not only exhibits improved stability and enhanced quality in the generated captions but also aligns more closely with human preferences compared to existing methods, especially in modern metrics. Additionally, it maintains competitive performance in traditional metrics. Our source code and trained models are publicly available at https://github.com/aimagelab/DiCO.

UNMuTe: Unifying Navigation and Multimodal Dialogue-like Text Generation

Smart autonomous agents are becoming increasingly important in various real-life applications, including robotics and autonomous vehicles. One crucial skill that these agents must possess is the ability to interact with their surrounding entities, such as other agents or humans. In this work, we aim at building an intelligent agent that can efficiently navigate in an environment while being able to interact with an oracle (or human) in natural language and ask for directions when it is unsure about its navigation performance. The interaction is started by the agent that produces a question, which is then answered by the oracle on the basis of the shortest trajectory to the goal. The process can be performed multiple times during navigation, thus enabling the agent to hold a dialogue with the oracle. To this end, we propose a novel computational model, named UNMuTe, that consists of two main components: a dialogue model and a navigator. Specifically, the dialogue model is based on a GPT-2 decoder that handles multimodal data consisting of both text and images. First, the dialogue model is trained to generate question-answer pairs: the question is generated using the current image, while the answer is produced leveraging future images on the path toward the goal. Subsequently, a VLN model is trained to follow the dialogue predicting navigation actions or triggering the dialogue model if it needs help. In our experimental analysis, we show that UNMuTe achieves state-of-the-art performance on the main navigation tasks implying dialogue, i.e. Cooperative Vision and Dialogue Navigation (CVDN) and Navigation from Dialogue History (NDH), proving that our approach is effective in generating useful questions and answers to guide navigation.