49 citations · 217 across the 32 of their papers we have counts for
36 papers · 1 filter
Transitivity Recovering Decompositions: Interpretable and Robust Fine-Grained Relationships
Abhra Chaudhuri, Massimiliano Mancini, Zeynep Akata +1
Recent advances in fine-grained representation learning leverage local-to-global (emergent) relationships for achieving state-of-the-art results. The relational representations rel…
Vision-by-Language for Training-Free Compositional Image Retrieval
Shyamgopal Karthik, Karsten Roth, Massimiliano Mancini +1
Given an image and a target modification (e.g an image of the Eiffel tower and the text "without people and at night-time"), Compositional Image Retrieval (CIR) aims to retrieve th…
PDiscoNet: Semantically consistent part discovery for fine-grained recognition
Robert van der Klis, Stephan Alaniz, Massimiliano Mancini +4
Fine-grained classification often requires recognizing specific object parts, such as beak shape and wing patterns for birds. Encouraging a fine-grained classification model to fir…
Iterative Superquadric Recomposition of 3D Objects from Multiple Views
Stephan Alaniz, Massimiliano Mancini, Zeynep Akata
Humans are good at recomposing novel objects, i.e. they can identify commonalities between unknown objects from general structure to finer detail, an ability difficult to replicate…
Image-free Classifier Injection for Zero-Shot Classification
Anders Christensen, Massimiliano Mancini, A. Sophia Koepke +2
Zero-shot learning models achieve remarkable results on image classification for samples from classes that were not seen during training. However, such models must be trained from…
On the Effectiveness of LayerNorm Tuning for Continual Learning in Vision Transformers
Thomas De Min, Massimiliano Mancini, Karteek Alahari +2
State-of-the-art rehearsal-free continual learning methods exploit the peculiarities of Vision Transformers to learn task-specific prompts, drastically reducing catastrophic forget…
ProbVLM: Probabilistic Adapter for Frozen Vision-Language Models
Uddeshya Upadhyay, Shyamgopal Karthik, Massimiliano Mancini +1
Large-scale vision-language models (VLMs) like CLIP successfully find correspondences between images and text. Through the standard deterministic mapping process, an image or a tex…
Vocabulary-free Image Classification
Alessandro Conti, Enrico Fini, Massimiliano Mancini +3
Recent advances in large vision-language models have revolutionized the image classification paradigm. Despite showing impressive zero-shot capabilities, a pre-defined set of categ…
If at First You Don't Succeed, Try, Try Again: Faithful Diffusion-based Text-to-Image Generation by Selection
Shyamgopal Karthik, Karsten Roth, Massimiliano Mancini +1
Despite their impressive capabilities, diffusion-based text-to-image (T2I) models can lack faithfulness to the text prompt, where generated images may not contain all the mentioned…
Cross-Modal Fusion Distillation for Fine-Grained Sketch-Based Image Retrieval
Abhra Chaudhuri, Massimiliano Mancini, Yanbei Chen +2
Representation learning for sketch-based image retrieval has mostly been tackled by learning embeddings that discard modality-specific information. As instances from different moda…
Relational Proxies: Emergent Relationships as Fine-Grained Discriminators
Abhra Chaudhuri, Massimiliano Mancini, Zeynep Akata +1
Fine-grained categories that largely share the same set of parts cannot be discriminated based on part information alone, as they mostly differ in the way the local parts relate to…
Semi-Supervised and Unsupervised Deep Visual Learning: A Survey
Yanbei Chen, Massimiliano Mancini, Xiatian Zhu +1
State-of-the-art deep learning models are often trained with a large amount of costly labeled training data. However, requiring exhaustive manual annotations may degrade the model'…
Abstracting Sketches through Simple Primitives
Stephan Alaniz, Massimiliano Mancini, Anjan Dutta +2
Humans show high-level of abstraction capabilities in games that require quickly communicating object information. They decompose the message content into multiple parts and commun…
BayesCap: Bayesian Identity Cap for Calibrated Uncertainty in Frozen Neural Networks
Uddeshya Upadhyay, Shyamgopal Karthik, Yanbei Chen +2
High-quality calibrated uncertainty estimates are crucial for numerous real-world applications, especially for deep learning-based deployed ML systems. While Bayesian deep learning…
KG-SP: Knowledge Guided Simple Primitives for Open World Compositional Zero-Shot Learning
Shyamgopal Karthik, Massimiliano Mancini, Zeynep Akata
The goal of open-world compositional zero-shot learning (OW-CZSL) is to recognize compositions of state and objects in images, given only a subset of them during training and no pr…
Attention Consistency on Visual Corruptions for Single-Source Domain Generalization
Ilke Cugu, Massimiliano Mancini, Yanbei Chen +1
Generalizing visual recognition models trained on a single distribution to unseen input distributions (i.e. domains) requires making them robust to superfluous correlations in the…
Modeling the Background for Incremental and Weakly-Supervised Semantic Segmentation
Fabio Cermelli, Massimiliano Mancini, Samuel Rota Buló +2
Deep neural networks have enabled major progresses in semantic segmentation. However, even the most advanced neural architectures suffer from important limitations. First, they are…
Concurrent Discrimination and Alignment for Self-Supervised Feature Learning
Anjan Dutta, Massimiliano Mancini, Zeynep Akata
Existing self-supervised learning methods learn representation by means of pretext tasks which are either (1) discriminating that explicitly specify which features should be separa…
On the Challenges of Open World Recognitionunder Shifting Visual Domains
Dario Fontanel, Fabio Cermelli, Massimiliano Mancini +1
Robotic visual systems operating in the wild must act in unconstrained scenarios, under different environmental conditions while facing a variety of semantic concepts, including un…
Detecting Anomalies in Semantic Segmentation with Prototypes
Dario Fontanel, Fabio Cermelli, Massimiliano Mancini +1
Traditional semantic segmentation methods can recognize at test time only the classes that are present in the training set. This is a significant limitation, especially for semanti…
Learning Graph Embeddings for Open World Compositional Zero-Shot Learning
Massimiliano Mancini, Muhammad Ferjad Naeem, Yongqin Xian +1
Compositional Zero-Shot learning (CZSL) aims to recognize unseen compositions of state and object visual primitives seen during training. A problem with standard CZSL is the assump…
A Closer Look at Self-training for Zero-Label Semantic Segmentation
Giuseppe Pastore, Fabio Cermelli, Yongqin Xian +3
Being able to segment unseen classes not observed during training is an important technical challenge in deep learning, because of its potential to reduce the expensive annotation…
Boosting Binary Masks for Multi-Domain Learning through Affine Transformations
Massimiliano Mancini, Elisa Ricci, Barbara Caputo +1
In this work, we present a new, algorithm for multi-domain learning. Given a pretrained architecture and a set of visual domains received sequentially, the goal of multi-domain lea…
Inferring Latent Domains for Unsupervised Deep Domain Adaptation
Massimiliano Mancini, Lorenzo Porzi, Samuel Rota Bulò +2
Unsupervised Domain Adaptation (UDA) refers to the problem of learning a model in a target domain where labeled data are not available by leveraging information from annotated data…