510 citations · 972 across the 24 of their papers we have counts for
35 papers
Semi-supervised learning made simple with self-supervised clustering
Enrico Fini, Pietro Astolfi, Karteek Alahari +4
Self-supervised learning models have been shown to learn rich visual representations without requiring human annotations. However, in many real-world scenarios, labels are partiall…
A soft nearest-neighbor framework for continual semi-supervised learning
Zhiqi Kang, Enrico Fini, Moin Nabi +2
Despite significant advances, the performance of state-of-the-art continual learning approaches hinges on the unrealistic scenario of fully labeled data. In this paper, we tackle t…
miCSE: Mutual Information Contrastive Learning for Low-shot Sentence Embeddings
Tassilo Klein, Moin Nabi
This paper presents miCSE, a mutual information-based contrastive learning framework that significantly advances the state-of-the-art in few-shot sentence embedding. The proposed a…
Mixture-of-experts VAEs can disregard variation in surjective multimodal data
Jannik Wolff, Tassilo Klein, Moin Nabi +2
Machine learning systems are often deployed in domains that entail data from multiple modalities, for example, phenotypic and genotypic characteristics describe patients in healthc…
SCD: Self-Contrastive Decorrelation for Sentence Embeddings
Tassilo Klein, Moin Nabi
In this paper, we propose Self-Contrastive Decorrelation (SCD), a self-supervised approach. Given an input sentence, it optimizes a joint self-contrastive and decorrelation objecti…
Uncertainty-aware Contrastive Distillation for Incremental Semantic Segmentation
Guanglei Yang, Enrico Fini, Dan Xu +5
A fundamental and challenging problem in deep learning is catastrophic forgetting, i.e. the tendency of neural networks to fail to preserve the knowledge acquired from old tasks wh…
A Unified Objective for Novel Class Discovery
Enrico Fini, Enver Sangineto, Stéphane Lathuilière +3
In this paper, we study the problem of Novel Class Discovery (NCD). NCD aims at inferring novel object categories in an unlabeled set by leveraging from prior knowledge of a labele…
Attention-based Contrastive Learning for Winograd Schemas
Tassilo Klein, Moin Nabi
Self-supervised learning has recently attracted considerable attention in the NLP community for its ability to learn discriminative features using a contrastive objective. This pap…
Towards Zero-shot Commonsense Reasoning with Self-supervised Refinement of Language Models
Tassilo Klein, Moin Nabi
Can we get existing language models and refine them for zero-shot commonsense reasoning? This paper presents an initial study exploring the feasibility of zero-shot commonsense rea…
Solo-learn: A Library of Self-supervised Methods for Visual Representation Learning
Victor G. Turrisi da Costa, Enrico Fini, Moin Nabi +2
This paper presents solo-learn, a library of self-supervised methods for visual representation learning. Implemented in Python, using Pytorch and Pytorch lightning, the library fit…
Multimodal Prototypical Networks for Few-shot Learning
Frederik Pahde, Mihai Puscas, Tassilo Klein +1
Although providing exceptional results for many computer vision tasks, state-of-the-art deep learning algorithms catastrophically struggle in low data scenarios. However, if data i…
Learning Graph-Based Priors for Generalized Zero-Shot Learning
Colin Samplawski, Jannik Wolff, Tassilo Klein +1
The task of zero-shot learning (ZSL) requires correctly predicting the label of samples from classes which were unseen at training time. This is achieved by leveraging side informa…
Online Continual Learning under Extreme Memory Constraints
Enrico Fini, Stéphane Lathuilière, Enver Sangineto +2
Continual Learning (CL) aims to develop agents emulating the human ability to sequentially learn new tasks while being able to retain knowledge obtained from past experiences. In t…
Contrastive Self-Supervised Learning for Commonsense Reasoning
Tassilo Klein, Moin Nabi
We propose a self-supervised method to solve Pronoun Disambiguation and Winograd Schema Challenge problems. Our approach exploits the characteristic structure of training corpora r…
Pruning at a Glance: Global Neural Pruning for Model Compression
Abdullah Salama, Oleksiy Ostapenko, Tassilo Klein +1
Deep Learning models have become the dominant approach in several areas due to their high performance. Unfortunately, the size and hence computational requirements of operating suc…
Multimodal Self-Supervised Learning for Medical Image Analysis
Aiham Taleb, Christoph Lippert, Tassilo Klein +1
Self-supervised learning approaches leverage unlabeled samples to acquire generic knowledge about different concepts, hence allowing for annotation-efficient downstream task learni…
Learning to Answer by Learning to Ask: Getting the Best of GPT-2 and BERT Worlds
Tassilo Klein, Moin Nabi
Automatic question generation aims at the generation of questions from a context, with the corresponding answers being sub-spans of the given passage. Whereas, most of the methods…
Uncertainty-Driven Semantic Segmentation through Human-Machine Collaborative Learning
Mahdyar Ravanbakhsh, Tassilo Klein, Kayhan Batmanghelich +1
Deep learning-based approaches achieve state-of-the-art performance in the majority of image segmentation benchmarks. However, training of such models requires a sizable amount of…
Attention Is (not) All You Need for Commonsense Reasoning
Tassilo Klein, Moin Nabi
The recently introduced BERT model exhibits strong performance on several language understanding benchmarks. In this paper, we describe a simple re-implementation of BERT for commo…
Budget-Aware Adapters for Multi-Domain Learning
Rodrigo Berriel, Stéphane Lathuilière, Moin Nabi +4
Multi-Domain Learning (MDL) refers to the problem of learning a set of models derived from a common deep architecture, each one specialized to perform a task in a certain domain (e…
Learning to Remember: A Synaptic Plasticity Driven Framework for Continual Learning
Oleksiy Ostapenko, Mihai Puscas, Tassilo Klein +2
Models trained in the context of continual learning (CL) should be able to learn from a stream of data over an undefined period of time. The main challenges herein are: 1) maintain…
Low-Shot Learning from Imaginary 3D Model
Frederik Pahde, Mihai Puscas, Jannik Wolff +3
Since the advent of deep learning, neural networks have demonstrated remarkable results in many visual recognition tasks, constantly pushing the limits. However, the state-of-the-a…
Self Paced Adversarial Training for Multimodal Few-shot Learning
Frederik Pahde, Oleksiy Ostapenko, Patrick Jähnichen +2
State-of-the-art deep learning algorithms yield remarkable results in many visual recognition tasks. However, they still fail to provide satisfactory results in scarce data regimes…
The Wisdom of MaSSeS: Majority, Subjectivity, and Semantic Similarity in the Evaluation of VQA
Shailza Jolly, Sandro Pezzelle, Tassilo Klein +2
We introduce MASSES, a simple evaluation metric for the task of Visual Question Answering (VQA). In its standard form, the VQA task is operationalized as follows: Given an image an…