A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
A new method improves few-shot image classification by updating top layers.
Generative Adversarial Networks (GAN) boast impressive capacity to generate realistic images. However, like much of the field of deep learning, they require an inordinate amount of data to produce results, thereby limiting their usefulness in generating novelty. In the same vein, recent advances in meta-learning have o…
DeepBDC improves few-shot classification by measuring joint distributions of image features.
Unsupervised image-to-image translation methods learn to map images in a given class to an analogous image in a different class, drawing on unstructured (non-registered) datasets of images. While remarkably successful, current methods require access to many images in both source and destination classes at training time…
Paper introduces privacy-preserving few-shot learning for images.
AdarGCN tackles noisy web images in few-shot learning.
BayPrAnoMeta tackles few-shot industrial image anomaly detection with Bayesian methods.
Enhances few-shot image classification using unlabelled examples.
Paper proposes LMM-PQS for cross-domain few-shot learning.
Breast CT provides image volumes with isotropic resolution in high contrast, enabling detection of small calcification (down to a few hundred microns in size) and subtle density differences. Since breast is sensitive to x-ray radiation, dose reduction of breast CT is an important topic, and for this purpose, few-view s…
Few-shot cell segmentation from diverse sources to target domain.
Accurate image classification given small amounts of labelled data (few-shot classification) remains an open problem in computer vision. In this work we examine how the known texture bias of Convolutional Neural Networks (CNNs) affects few-shot classification performance. Although texture bias can help in standard imag…
SketchEmbedNet learns image representations from sketches, useful for few-shot learning.
Few-step distillation improves T2I models without real images or CFG trade-offs.
Few-Shot Diffusion Models generate new samples from small image sets.
The goal of few-shot learning is to learn a model that can recognize novel classes based on one or few training data. It is challenging mainly due to two aspects: (1) it lacks good feature representation of novel classes; (2) a few of labeled data could not accurately represent the true data distribution and thus it's …
Unified framework explains few-shot multimodal medical imaging performance.
TPM improves medical image segmentation by separating foreground and background.
Untrained neural networks can recover natural images from few measurements.
Previous work on adversarially robust neural networks for image classification requires large training sets and computationally expensive training procedures. On the other hand, few-shot learning methods are highly vulnerable to adversarial examples. The goal of our work is to produce networks which both perform well a…
We present an image preprocessing technique capable of improving the performance of few-shot classifiers on abstract visual reasoning tasks. Many visual reasoning tasks with abstract features are easy for humans to learn with few examples but very difficult for computer vision approaches with the same number of samples…
New method learns fusion rules from few images using granular ball priors.
Deep convolutional neural networks trained on large datsets have emerged as an intriguing alternative for compressing images and solving inverse problems such as denoising and compressive sensing. However, it has only recently been realized that even without training, convolutional networks can function as concise imag…
URT layer improves few-shot image classification across diverse domains.
Self-augmentation improves deep networks for few-shot learning with minimal training data.
Few-shot DP image classification models need more data as privacy increases.
Improves memory efficiency for meta-learning with large images.
The field of few-shot learning has been laboriously explored in the supervised setting, where per-class labels are available. On the other hand, the unsupervised few-shot learning setting, where no labels of any kind are required, has seen little investigation. We propose a method, named Assume, Augment and Learn or AA…
Develops methods for training models with few annotations in computer vision tasks.
LSTMs show surprising few-shot learning ability, improving on MAML.
This paper considers the problem of inferring image labels from images when only a few annotated examples are available at training time. This setup is often referred to as low-shot learning, where a standard approach is to re-train the last few layers of a convolutional neural network learned on separate classes for w…
We prove that, except for a few explicit roots of unity, the quantum image of any Johnson subgroup of the mapping class group contains an explicit free non-abelian subgroup.
Image modality recognition is essential for efficient imaging workflows in current clinical environments, where multiple imaging modalities are used to better comprehend complex diseases. Emerging biomarkers from novel, rare modalities are being developed to aid in such understanding, however the availability of these …
FiT combines transfer and meta-learning for efficient few-shot image classification.
We consider the problem of semi-supervised few-shot classification where a classifier needs to adapt to new tasks using a few labeled examples and (potentially many) unlabeled examples. We propose a clustering approach to the problem. The features extracted with Prototypical Networks are clustered using -means with …
This paper proposes a multi-layer neural network structure for few-shot image recognition of novel categories. The proposed multi-layer neural network architecture encodes transferable knowledge extracted from a large annotated dataset of base categories. This architecture is then applied to novel categories containing…
Learning-based methods for visual segmentation have made progress on particular types of segmentation tasks, but are limited by the necessary supervision, the narrow definitions of fixed tasks, and the lack of control during inference for correcting errors. To remedy the rigidity and annotation burden of standard appro…
Proposes a method for weakly-supervised object localization to improve few-shot learning.
Adaptive object detection method synthesizes target domain images from source domain images.
Metric-based meta-learning techniques have successfully been applied to few-shot classification problems. In this paper, we propose to leverage cross-modal information to enhance metric-based few-shot learning methods. Visual and semantic feature spaces have different structures by definition. For certain concepts, vis…
New method generates universal adversarial perturbations across different image sources.
NeRF-VAE generates 3D scenes with geometric structure from few images.
Fine-tuning a deep network trained with the standard cross-entropy loss is a strong baseline for few-shot learning. When fine-tuned transductively, this outperforms the current state-of-the-art on standard datasets such as Mini-ImageNet, Tiered-ImageNet, CIFAR-FS and FC-100 with the same hyper-parameters. The simplicit…
We propose to study the problem of few-shot learning with the prism of inference on a partially observed graphical model, constructed from a collection of input images whose label can be either observed or not. By assimilating generic message-passing inference algorithms with their neural-network counterparts, we defin…
DistillKac generates images quickly using damped wave equations.
Defense against small image patches using occlusions.
Few random images can improve anomaly detection performance.
Recent algorithms with state-of-the-art few-shot classification results start their procedure by computing data features output by a large pretrained model. In this paper we systematically investigate which models provide the best representations for a few-shot image classification task when pretrained on the Imagenet …