Related papers: Mitigating Negative Flips via Margin Preserving Tr…

As part of autonomous car driving systems, semantic segmentation is an essential component to obtain a full understanding of the car's environment. One difficulty, that occurs while training neural networks for this purpose, is class…

Machine learning models can perform well on in-distribution data but often fail on biased subgroups that are underrepresented in the training data, hindering the robustness of models for reliable applications. Such subgroups are typically…

Finetuning image-text models such as CLIP achieves state-of-the-art accuracies on a variety of benchmarks. However, recent works like WiseFT (Wortsman et al., 2021) and LP-FT (Kumar et al., 2022) have shown that even subtle differences in…

The main requisite for fine-grained recognition task is to focus on subtle discriminative details that make the subordinate classes different from each other. We note that existing methods implicitly address this requirement and leave it to…

Deep learning has achieved remarkable success in image classification and segmentation tasks. However, fairness concerns persist, as models often exhibit biases that disproportionately affect demographic groups defined by sensitive…

Learning from imbalanced data is one of the most significant challenges in real-world classification tasks. In such cases, neural networks performance is substantially impaired due to preference towards the majority class. Existing…

Compounding error, where small prediction mistakes accumulate over time, presents a major challenge in learning-based control. For example, this issue often limits the performance of model-based reinforcement learning and imitation…

Contrastive learning is a major studied topic in metric learning. However, sampling effective contrastive pairs remains a challenge due to factors such as limited batch size, imbalanced data distribution, and the risk of overfitting. In…

Metric learning is a fundamental problem in computer vision whereby a model is trained to learn a semantically useful embedding space via ranking losses. Traditionally, the effectiveness of a ranking loss depends on the minibatch size, and…

We present a novel class incremental learning approach based on deep neural networks, which continually learns new tasks with limited memory for storing examples in the previous tasks. Our algorithm is based on knowledge distillation and…

Human beings are able to master a variety of knowledge and skills with ongoing learning. By contrast, dramatic performance degradation is observed when new tasks are added to an existing neural network model. This phenomenon, termed as…

In this paper, we propose a new max-margin based discriminative feature learning method. Specifically, we aim at learning a low-dimensional feature representation, so as to maximize the global margin of the data and make the samples from…

The CLIP (Contrastive Language-Image Pre-training) model and its variants are becoming the de facto backbone in many applications. However, training a CLIP model from hundreds of millions of image-text pairs can be prohibitively expensive.…

We consider the problem of online multiclass classification with partial feedback, where an algorithm predicts a class for a new instance in each round and only receives its correctness. Although several methods have been developed for this…

Class-incremental learning is a challenging problem, where the goal is to train a model that can classify data from an increasing number of classes over time. With the advancement of vision-language pre-trained models such as CLIP, they…

Training large language models (LLMs) presents numerous challenges, including gradient instability and loss spikes. These phenomena can lead to catastrophic divergence, requiring costly checkpoint restoration and data batch skipping.…

Most modern neural networks for classification fail to take into account the concept of the unknown. Trained neural networks are usually tested in an unrealistic scenario with only examples from a closed set of known classes. In an attempt…

One-shot image classification aims to train image classifiers over the dataset with only one image per category. It is challenging for modern deep neural networks that typically require hundreds or thousands of images per class. In this…

Semi-supervised learning frameworks usually adopt mutual learning approaches with multiple submodels to learn from different perspectives. To avoid transferring erroneous pseudo labels between these submodels, a high threshold is usually…

Recent works have shown that deep neural networks can achieve super-human performance in a wide range of image classification tasks in the medical imaging domain. However, these works have primarily focused on classification accuracy,…