N. Sebe

Semantic Connectivity-Driven Pseudo-labeling for Cross-domain Segmentation

Dong Zhao, Ruizhi Yang, Shuang Wang +5

Presently, self-training stands as a prevailing approach in cross-domain semantic segmentation, enhancing model efficacy by training with pixels assigned with reliable pseudo-label…

Diversified in-domain synthesis with efficient fine-tuning for few-shot classification

Victor G. Turrisi da Costa, Nicola Dall'Asen, Yiming Wang +2

Few-shot image classification aims to learn an image classifier using only a small set of labeled examples per class. A recent research direction for improving few-shot classifiers…

ZeroReg: Zero-Shot Point Cloud Registration with Foundation Models

Weijie Wang, Wenqi Ren, Guofeng Mei +5

State-of-the-art 3D point cloud registration methods rely on labeled 3D datasets for training, which limits their practical applications in real-world scenarios and often hinders g…

Improving Fairness using Vision-Language Driven Image Augmentation

Moreno D'Incà, Christos Tzelepis, Ioannis Patras +1

Fairness is crucial when training a deep-learning discriminative model, especially in the facial domain. Models tend to correlate specific characteristics (such as age and skin col…

cs.LG2023

RankFeat&RankWeight: Rank-1 Feature/Weight Removal for Out-of-distribution Detection

Yue Song, Wei Wang, Nicu Sebe

The task of out-of-distribution (OOD) detection is crucial for deploying machine learning models in real-world settings. In this paper, we observe that the singular value distribut…

Hourglass Tokenizer for Efficient Transformer-Based 3D Human Pose Estimation

Wenhao Li, Mengyuan Liu, Hong Liu +3

Transformers have been successfully applied in the field of video-based 3D human pose estimation. However, the high computational costs of these video pose transformers (VPTs) make…

CNNs for JPEGs: A Study in Computational Cost

Samuel Felipe dos Santos, Nicu Sebe, Jurandy Almeida

Convolutional neural networks (CNNs) have achieved astonishing advances over the past decade, defining state-of-the-art in several computer vision tasks. CNNs are capable of learni…

Tightening Classification Boundaries in Open Set Domain Adaptation through Unknown Exploitation

Lucas Fernando Alvarenga e Silva, Nicu Sebe, Jurandy Almeida

Convolutional Neural Networks (CNNs) have brought revolutionary advances to many research areas due to their capacity of learning from raw data. However, when those methods are app…

Turn Fake into Real: Adversarial Head Turn Attacks Against Deepfake Detection

Weijie Wang, Zhengyu Zhao, Nicu Sebe +1

Malicious use of deepfakes leads to serious public concerns and reduces people's trust in digital media. Although effective deepfake detectors have been proposed, they are substant…

Budget-Aware Pruning: Handling Multiple Domains with Less Parameters

Samuel Felipe dos Santos, Rodrigo Berriel, Thiago Oliveira-Santos +2

Deep learning has achieved state-of-the-art performance on several computer vision tasks and domains. Nevertheless, it still has a high computational cost and demands a significant…

Compositional Semantic Mix for Domain Adaptation in Point Cloud Segmentation

Cristiano Saltori, Fabio Galasso, Giuseppe Fiameni +3

Deep-learning models for 3D point cloud semantic segmentation exhibit limited generalization capabilities when trained and tested on data captured with different sensors or in vary…

cs.CV2023★ 8 cited

Interactive Neural Painting

Elia Peruzzo, Willi Menapace, Vidit Goel +9

In the last few years, Neural Painting (NP) techniques became capable of producing extremely realistic artworks. This paper advances the state of the art in this emerging research…

Edge Guided GANs with Multi-Scale Contrastive Learning for Semantic Image Synthesis

Hao Tang, Guolei Sun, Nicu Sebe +1

We propose a novel ECGAN for the challenging semantic image synthesis task. Although considerable improvements have been achieved by the community in the recent period, the quality…

Let's ViCE! Mimicking Human Cognitive Behavior in Image Generation Evaluation

Federico Betti, Jacopo Staiano, Lorenzo Baraldi +2

Research in Image Generation has recently made significant progress, particularly boosted by the introduction of Vision-Language models which are able to produce high-quality visua…

Householder Projector for Unsupervised Latent Semantics Discovery

Yue Song, Jichao Zhang, Nicu Sebe +1

Generative Adversarial Networks (GANs), especially the recent style-based generators (StyleGANs), have versatile semantics in the structured latent space. Latent semantics discover…

T2TD: Text-3D Generation Model based on Prior Knowledge Guidance

Weizhi Nie, Ruidong Chen, Weijie Wang +2

In recent years, 3D models have been utilized in many applications, such as auto-driver, 3D reconstruction, VR, and AR. However, the scarcity of 3D model data does not meet its pra…

Federated Generalized Category Discovery

Nan Pu, Zhun Zhong, Xinyuan Ji +1

Generalized category discovery (GCD) aims at grouping unlabeled samples from known and unknown classes, given labeled data of known classes. To meet the recent decentralization tre…

cs.LG2023

Riemannian Multinomial Logistics Regression for SPD Neural Networks

Ziheng Chen, Yue Song, Gaowen Liu +3

Deep neural networks for learning Symmetric Positive Definite (SPD) matrices are gaining increasing attention in machine learning. Despite the significant progress, most existing S…

cs.LG2023★ 5 cited

Latent Traversals in Generative Models as Potential Flows

Yue Song, T. Anderson Keller, Nicu Sebe +1

Despite the significant recent progress in deep generative models, the underlying structure of their latent spaces is still poorly understood, thereby making the task of performing…

cs.CV2023★ 3 cited

Dynamic Conceptional Contrastive Learning for Generalized Category Discovery

Nan Pu, Zhun Zhong, Nicu Sebe

Generalized category discovery (GCD) is a recently proposed open-world problem, which aims to automatically cluster partially labeled data. The main challenge is that the unlabeled…

Attribute-preserving Face Dataset Anonymization via Latent Code Optimization

Simone Barattin, Christos Tzelepis, Ioannis Patras +1

This work addresses the problem of anonymizing the identity of faces in a dataset of images, such that the privacy of those depicted is not violated, while at the same time the dat…

Graph Transformer GANs for Graph-Constrained House Generation

Hao Tang, Zhenyu Zhang, Humphrey Shi +5

We present a novel graph Transformer generative adversarial network (GTGAN) to learn effective graph node relations in an end-to-end fashion for the challenging graph-constrained h…