Publications by Sara Sarto

The implementation of data protection regulations such as the GDPR and the California Consumer Privacy Act has sparked a growing interest in removing sensitive information from pre-trained models without requiring retraining from scratch, all while maintaining predictive performance on remaining data. Recent studies on machine unlearning for deep neural networks have resulted in different attempts that put constraints on the training procedure and which are limited to small-scale architectures and with poor adaptability to real-world requirements. In this paper, we develop an approach to delete information on a class from a pre-trained model, by injecting a trainable low-rank decomposition into the network parameters, and without requiring access to the original training set. Our approach greatly reduces the number of parameters to train as well as time and memory requirements. This allows a painless application to real-life settings where the entire training set is unavailable, and compliance with the requirement of time-bound deletion. We conduct experiments on various Vision Transformer architectures for class forgetting. Extensive empirical analyses demonstrate that our proposed method is efficient, safe to apply, and effective in removing learned information while maintaining accuracy.

Video Surveillance started decades ago to remotely monitor specific areas and allow control from human inspectors. Later, Computer Vision gradually replaced human monitoring, firstly through motion alerts and now with Deep Learning techniques. From the beginning of this journey, people have worried about the risk of privacy violations. This article surveys the main steps of Computer Vision in Video Surveillance, from early approaches for people detection and tracking to action analysis and language description, outlining the most relevant directions on the topic to deal with privacy concerns. We show how the relationship between Video Surveillance and privacy is a biased paradox since surveillance provides increased safety but does not necessarily require the people identification. Through experiments on action recognition and natural language description, we showcase that the paradox of surveillance and privacy can be solved by Artificial Intelligence and that the respect of human rights is not an impossible chimera.

Multimodal LLMs are the natural evolution of LLMs and enlarge their capabilities so as to work beyond the pure textual modality. As research is being carried out to design novel architectures and vision-and-language adapters in this paper we concentrate on endowing such models with the capability of answering questions that require external knowledge. Our approach termed Wiki-LLaVA aims at integrating an external knowledge source of multimodal documents which is accessed through a hierarchical retrieval pipeline. Relevant passages using this approach are retrieved from the external knowledge source and employed as additional context for the LLM augmenting the effectiveness and precision of generated dialogues. We conduct extensive experiments on datasets tailored for visual question answering with external data and demonstrate the appropriateness of our approach.

The CLIP model has been recently proven to be very effective for a variety of cross-modal tasks, including the evaluation of captions generated from vision-and-language models. In this paper, we propose a new recipe for a contrastive-based evaluation metric for image captioning, namely Positive-Augmented Contrastive learning Score (PAC-S), that in a novel way unifies the learning of a contrastive visual-semantic space with the addition of generated images and text on curated data. Experiments spanning several datasets demonstrate that our new metric achieves the highest correlation with human judgments on both images and videos, outperforming existing reference-based metrics like CIDEr and SPICE and reference-free metrics like CLIP-Score. Finally, we test the system-level correlation of the proposed metric when considering popular image captioning approaches, and assess the impact of employing different cross-modal features. We publicly release our source code and trained models.

Image captioning, like many tasks involving vision and language, currently relies on Transformer-based architectures for extracting the semantics in an image and translating it into linguistically coherent descriptions. Although successful, the attention operator only considers a weighted summation of projections of the current input sample, therefore ignoring the relevant semantic information which can come from the joint observation of other samples. In this paper, we devise a network which can perform attention over activations obtained while processing other training samples, through a prototypical memory model. Our memory models the distribution of past keys and values through the definition of prototype vectors which are both discriminative and compact. Experimentally, we assess the performance of the proposed model on the COCO dataset, in comparison with carefully designed baselines and state-of-the-art approaches, and by investigating the role of each of the proposed components. We demonstrate that our proposal can increase the performance of an encoder-decoder Transformer by 3.7 CIDEr points both when training in cross-entropy only and when fine-tuning with self-critical sequence training. Source code and trained models are available at: https://github.com/aimagelab/PMA-Net.

Image captioning models aim at connecting Vision and Language by providing natural language descriptions of input images. In the past few years, the task has been tackled by learning parametric models and proposing visual feature extraction advancements or by modeling better multi-modal connections. In this paper, we investigate the development of an image captioning approach with a kNN memory, with which knowledge can be retrieved from an external corpus to aid the generation process. Our architecture combines a knowledge retriever based on visual similarities, a differentiable encoder, and a kNN-augmented attention layer to predict tokens based on the past context and on text retrieved from the external memory. Experimental results, conducted on the COCO dataset, demonstrate that employing an explicit external memory can aid the generation process and increase caption quality. Our work opens up new avenues for improving image captioning models at larger scale.