Related papers: Exploring and Leveraging Class Vectors for Classif…
A fundamental requirement for intelligent systems is the ability to learn continuously under changing environments. However, models trained in this regime often suffer from catastrophic forgetting. Leveraging pre-trained models has recently…
Despite the recent success of instruction-tuned language models and their ubiquitous usage, very little is known of how models process instructions internally. In this work, we address this gap from a mechanistic point of view by…
Model editing aims to data-efficiently correct predictive errors of large pre-trained models while ensuring generalization to neighboring failures and locality to minimize unintended effects on unrelated examples. While significant progress…
Learning useful representations of complex data has been the subject of extensive research for many years. With the diffusion of Deep Neural Networks, Variational Autoencoders have gained lots of attention since they provide an explicit…
Instruction guided image editing has advanced substantially with recent generative models, yet it still fails to produce reliable results across many seemingly simple cases. We observe that a large portion of these failures stem not from…
Current state-of-the-art approaches to text classification typically leverage BERT-style Transformer models with a softmax classifier, jointly fine-tuned to predict class labels of a target task. In this paper, we instead propose an…
Vision transformers combined with self-supervised learning have enabled the development of models which scale across large datasets for several downstream tasks like classification, segmentation and detection. The low-shot learning…
Explainability is a longstanding challenge in deep learning, especially in high-stakes domains like healthcare. Common explainability methods highlight image regions that drive an AI model's decision. Humans, however, heavily rely on…
Visual counterfactual explanations are ideal hypothetical images that change the decision-making of the classifier with high confidence toward the desired class while remaining visually plausible and close to the initial image. In this…
Machine unlearning (MU), which seeks to erase the influence of specific unwanted data from already-trained models, is becoming increasingly vital in model editing, particularly to comply with evolving data regulations like the ``right to be…
Training of deep neural networks heavily depends on the data distribution. In particular, the networks easily suffer from class imbalance. The trained networks would recognize the frequent classes better than the infrequent classes. To…
We introduce a method to provide vectorial representations of visual classification tasks which can be used to reason about the nature of those tasks and their relations. Given a dataset with ground-truth labels and a loss function defined…
Recently, with the advancement of deep learning, several applications in text classification have advanced significantly. However, this improvement comes with a cost because deep learning is vulnerable to adversarial examples. This weakness…
Visual place recognition tasks often encounter significant challenges in landmark detection due to the presence of irrelevant objects such as humans, cars, and trees, despite the remarkable progress achieved by previous models, especially…
While machine learning is currently transforming the field of histopathology, the domain lacks a comprehensive evaluation of state-of-the-art models based on essential but complementary quality requirements beyond a mere classification…
Despite numerous attempts to defend deep learning based image classifiers, they remain susceptible to the adversarial attacks. This paper proposes a technique to identify susceptible classes, those classes that are more easily subverted. To…
Medical image segmentation aims to identify anatomical structures at the voxel-level. Segmentation accuracy relies on distinguishing voxel differences. Compared to advancements achieved in studies of the inter-class variance, the…
Semantic segmentation is a fundamental computer vision task with a vast number of applications. State of the art methods increasingly rely on deep learning models, known to incorrectly estimate uncertainty and being overconfident in…
Attributes act as intermediate representations that enable parameter sharing between classes, a must when training data is scarce. We propose to view attribute-based image classification as a label-embedding problem: each class is embedded…
Zooplankton images, like many other real world data types, have intrinsic properties that make the design of effective classification systems difficult. For instance, the number of classes encountered in practical settings is potentially…