Related papers: SimLoss: Class Similarities in Cross Entropy
This paper introduces the concept of uniform classification, which employs a unified threshold to classify all samples rather than adaptive threshold classifying each individual sample. We also propose the uniform classification accuracy as…
Class labels used for machine learning are relatable to each other, with certain class labels being more similar to each other than others (e.g. images of cats and dogs are more similar to each other than those of cats and cars). Such…
We explore loss functions for fact verification in the FEVER shared task. While the cross-entropy loss is a standard objective for training verdict predictors, it fails to capture the heterogeneity among the FEVER verdict classes. In this…
Error-correcting codes (ECC) are used to reduce multiclass classification tasks to multiple binary classification subproblems. In ECC, classes are represented by the rows of a binary matrix, corresponding to codewords in a codebook.…
The backbone of traditional CNN classifier is generally considered as a feature extractor, followed by a linear layer which performs the classification. We propose a novel loss function, termed as CAM-loss, to constrain the embedded feature…
In neural networks, the loss function represents the core of the learning process that leads the optimizer to an approximation of the optimal convergence error. Convolutional neural networks (CNN) use the loss function as a supervisory…
State-of-the-art natural language understanding classification models follow two-stages: pre-training a large language model on an auxiliary task, and then fine-tuning the model on a task-specific labeled dataset using cross-entropy loss.…
Continual learning aims to accumulate knowledge over a data stream while mitigating catastrophic forgetting. In Non-exemplar Class Incremental Learning (NECIL), forgetting arises during incremental optimization because old classes are…
Cross-Entropy Method (CEM) is commonly used for planning in model-based reinforcement learning (MBRL) where a centralized approach is typically utilized to update the sampling distribution based on only the top-$k$ operation's results on…
Labeling a training set is often expensive and susceptible to errors, making the design of robust loss functions for label noise an important problem. The symmetry condition provides theoretical guarantees for robustness to such noise. In…
Simile recognition is to detect simile sentences and to extract simile components, i.e., tenors and vehicles. It involves two subtasks: {\it simile sentence classification} and {\it simile component extraction}. Recent work has shown that…
Modern recommendation systems fuse user behavior graphs and review texts but often encounter a "Fusion Gap" caused by False Negatives, Popularity Bias, and Signal Ambiguity. We propose SymCERE (Symmetric NCE), a contrastive learning…
Contrastive representation learning has proven to be an effective self-supervised learning method for images and videos. Most successful approaches are based on Noise Contrastive Estimation (NCE) and use different views of an instance as…
Recent end-to-end deep neural networks for disparity regression have achieved the state-of-the-art performance. However, many well-acknowledged specific properties of disparity estimation are omitted in these deep learning algorithms.…
In this paper, we focus on multi-task classification, where related classification tasks share the same label space and are learned simultaneously. In particular, we tackle a new setting, which is more realistic than currently addressed in…
Deep learning has become the method of choice in many application domains of machine learning in recent years, especially for multi-class classification tasks. The most common loss function used in this context is the cross-entropy loss,…
Nowadays, most classification networks use one-hot encoding to represent categorical data because of its simplicity. However, one-hot encoding may affect the generalization ability as it neglects inter-class correlations. We observe that,…
Deep Learning has become interestingly popular in computer vision, mostly attaining near or above human-level performance in various vision tasks. But recent work has also demonstrated that these deep neural networks are very vulnerable to…
While deep learning has led to huge progress in complex image classification tasks like ImageNet, unexpected failure modes, e.g. via spurious features, call into question how reliably these classifiers work in the wild. Furthermore, for…
Large Language Models (LLMs) have demonstrated impressive performance across various tasks. However, current training approaches combine standard cross-entropy loss with extensive data, human feedback, or ad hoc methods to enhance…