Related papers: Memory-Modular Classification: Learning to General…

Despite the popularity and success of deep learning, there is limited understanding of when, how, and why neural networks generalize to unseen examples. Since learning can be seen as extracting information from data, we formally study…

Recent advances in zero-shot image recognition suggest that vision-language models learn generic visual representations with a high degree of semantic information that may be arbitrarily probed with natural language phrases. Understanding…

Deep learning has recently achieved remarkable performance in image classification tasks, which depends heavily on massive annotation. However, the classification mechanism of existing deep learning models seems to contrast to humans'…

Neural networks often learn simple explanations that fit the majority of the data while memorizing exceptions that deviate from these explanations.This behavior leads to poor generalization when the learned explanations rely on spurious…

Recent work has shown that memory modules are crucial for the generalization ability of neural networks on learning simple algorithms. However, we still have little understanding of the working mechanism of memory modules. To alleviate this…

Few-shot image classification requires the classifier to robustly cope with unseen classes even if there are only a few samples for each class. Recent advances benefit from the meta-learning process where episodic tasks are formed to train…

The majority of computer vision algorithms fail to find higher-order (abstract) patterns in an image so are not robust against adversarial attacks, unlike human lateralized vision. Deep learning considers each input pixel in a homogeneous…

In this paper, we present a new kind of learning implementation to recognize the patterns using the concept of Mirroring Neural Network (MNN) which can extract information from distinct sensory input patterns and perform pattern recognition…

It has been observed that neural networks perform poorly when the data or tasks are presented sequentially. Unlike humans, neural networks suffer greatly from catastrophic forgetting, making it impossible to perform life-long learning. To…

The impressive capability of modern text-to-image models to generate realistic visuals has come with a serious drawback: they can be misused to create harmful, deceptive or unlawful content. This has accelerated the push for machine…

One of the key limitations of modern deep learning approaches lies in the amount of data required to train them. Humans, by contrast, can learn to recognize novel categories from just a few examples. Instrumental to this rapid learning…

Memorisation is a natural part of learning from real-world data: neural models pick up on atypical input-output combinations and store those training examples in their parameter space. That this happens is well-known, but how and where are…

Humans can quickly learn new visual concepts, perhaps because they can easily visualize or imagine what novel objects look like from different views. Incorporating this ability to hallucinate novel instances of new concepts might help…

Machine unlearning has emerged as a new paradigm to deliberately forget data samples from a given model in order to adhere to stringent regulations. However, existing machine unlearning methods have been primarily focused on classification…

Currently, the state-of-the-art methods treat few-shot semantic segmentation task as a conditional foreground-background segmentation problem, assuming each class is independent. In this paper, we introduce the concept of meta-class, which…

This paper introduces a probabilistic framework for k-shot image classification. The goal is to generalise from an initial large-scale classification task to a separate task comprising new classes and small numbers of examples. The new…

One of the hallmarks of human intelligence is the ability to compose learned knowledge into novel concepts which can be recognized without a single training example. In contrast, current state-of-the-art methods require hundreds of training…

Few-shot learning remains challenging for meta-learning that learns a learning algorithm (meta-learner) from many related tasks. In this work, we argue that this is due to the lack of a good representation for meta-learning, and propose…

The success of modern neural networks has prompted study of the connection between memorisation and generalisation: overparameterised models generalise well, despite being able to perfectly fit (memorise) completely random labels. To…

In few-shot learning, classifiers are expected to generalize to unseen classes given only a small number of instances of each new class. One of the popular solutions to few-shot learning is metric-based meta-learning. However, it highly…