Search Results for author:
Found 23 papers, 18 papers with code
EOL: Transductive Few-Shot Open-Set Recognition by Enhancing Outlier Logits
In Few-Shot Learning (FSL), models are trained to recognise unseen objects from a query set, given a few labelled examples from a support set.
SaulLM-54B & SaulLM-141B: Scaling Up Domain Adaptation for the Legal Domain
In this paper, we introduce SaulLM-54B and SaulLM-141B, two large language models (LLMs) tailored for the legal sector.
LP++: A Surprisingly Strong Linear Probe for Few-Shot CLIP
In this work, we propose and examine from convex-optimization perspectives a generalization of the standard LP baseline, in which the linear classifier weights are learnable functions of the text embedding, with class-wise multipliers blending image and text knowledge.
SaulLM-7B: A pioneering Large Language Model for Law
In this paper, we introduce SaulLM-7B, a large language model (LLM) tailored for the legal domain.
Transductive Learning for Textual Few-Shot Classification in API-based Embedding Models
First, we introduce a scenario where the embedding of a pre-trained model is served through a gated API with compute-cost and data-privacy constraints.
Bag of Tricks for Fully Test-Time Adaptation
Fully Test-Time Adaptation (TTA), which aims at adapting models to data drifts, has recently attracted wide interest.
In Search for a Generalizable Method for Source Free Domain Adaptation
Source-free domain adaptation (SFDA) is compelling because it allows adapting an off-the-shelf model to a new domain using only unlabelled data.
Open-Set Likelihood Maximization for Few-Shot Learning
We tackle the Few-Shot Open-Set Recognition (FSOSR) problem, i. e. classifying instances among a set of classes for which we only have a few labeled samples, while simultaneously detecting instances that do not belong to any known class.
A Strong Baseline for Generalized Few-Shot Semantic Segmentation
In addition, the terms derived from our MI-based formulation are coupled with a knowledge distillation term to retain the knowledge on base classes.
Towards Practical Few-Shot Query Sets: Transductive Minimum Description Length Inference
We relax these assumptions and extend current benchmarks, so that the query-set classes of a given task are unknown, but just belong to a much larger set of possible classes.
Simplex Clustering via sBeta with Applications to Online Adjustment of Black-Box Predictions
We explore clustering the softmax predictions of deep neural networks and introduce a novel probabilistic clustering method, referred to as k-sBetas.
Model-Agnostic Few-Shot Open-Set Recognition
Through extensive experiments spanning 5 datasets, we show that OSTIM surpasses both inductive and existing transductive methods in detecting open-set instances while competing with the strongest transductive methods in classifying closed-set instances.
FHIST: A Benchmark for Few-shot Classification of Histological Images
We build few-shot tasks and base-training data with various tissue types, different levels of domain shifts stemming from various cancer sites, and different class-granularity levels, thereby reflecting realistic scenarios.
Realistic Evaluation of Transductive Few-Shot Learning
Transductive inference is widely used in few-shot learning, as it leverages the statistics of the unlabeled query set of a few-shot task, typically yielding substantially better performances than its inductive counterpart.
A Differential Entropy Estimator for Training Neural Networks
Mutual Information (MI) has been widely used as a loss regularizer for training neural networks.
Parameter-free Online Test-time Adaptation
An interesting and practical paradigm is online test-time adaptation, according to which training data is inaccessible, no labelled data from the test distribution is available, and adaptation can only happen at test time and on a handful of samples.
Mutual-Information Based Few-Shot Classification
We motivate our transductive loss by deriving a formal relation between the classification accuracy and mutual-information maximization.
Transductive Few-Shot Learning: Clustering is All You Need?
Surprisingly, we found that even standard clustering procedures (e. g., K-means), which correspond to particular, non-regularized cases of our general model, already achieve competitive performances in comparison to the state-of-the-art in few-shot learning.
Adversarial Robustness via Fisher-Rao Regularization
Adversarial robustness has become a topic of growing interest in machine learning since it was observed that neural networks tend to be brittle.
Few-Shot Segmentation Without Meta-Learning: A Good Transductive Inference Is All You Need?
We show that the way inference is performed in few-shot segmentation tasks has a substantial effect on performances -- an aspect often overlooked in the literature in favor of the meta-learning paradigm.
Ranked #3 on
Few-Shot Semantic Segmentation
on COCO-20i (10-shot)
Information Maximization for Few-Shot Learning
We introduce Transductive Infomation Maximization (TIM) for few-shot learning.
Transductive Information Maximization For Few-Shot Learning
We introduce Transductive Infomation Maximization (TIM) for few-shot learning.
A unifying mutual information view of metric learning: cross-entropy vs. pairwise losses
Second, we show that, more generally, minimizing the cross-entropy is actually equivalent to maximizing the mutual information, to which we connect several well-known pairwise losses.
Ranked #12 on
Metric Learning
on CARS196
(using extra training data)
