Related papers: Studying How to Efficiently and Effectively Guide …

Deep neural networks have demonstrated remarkable performance across various domains, yet their decision-making processes remain opaque. Although many explanation methods are dedicated to bringing the obscurity of DNNs to light, they…

Decision Focused Learning has emerged as a critical paradigm for integrating machine learning with downstream optimisation. Despite its promise, existing methodologies predominantly rely on probabilistic models and focus narrowly on task…

Supervised deep learning requires a large amount of training samples with annotations (e.g. label class for classification task, pixel- or voxel-wised label map for segmentation tasks), which are expensive and time-consuming to obtain.…

Fine-tuning LLMs for classification typically maps inputs directly to labels. We ask whether attaching brief explanations to each label during fine-tuning yields better models. We evaluate conversational response quality along three axes:…

Classifier-guided diffusion models have emerged as a powerful approach for conditional image generation, but they suffer from overconfident predictions during early denoising steps, causing the guidance gradient to vanish. This paper…

Deep convolutional neural networks have driven substantial advancements in the automatic understanding of images. Requiring a large collection of images and their associated annotations is one of the main bottlenecks limiting the adoption…

This paper explores the intricate relationship between interpretability and robustness in deep learning models. Despite their remarkable performance across various tasks, deep learning models often exhibit critical vulnerabilities,…

State-of-the-art supervised NLP models achieve high accuracy but are also susceptible to failures on inputs from low-data regimes, such as domains that are not represented in training data. As an approximation to collecting ground-truth…

Explaining recommendations enables users to understand whether recommended items are relevant to their needs and has been shown to increase their trust in the system. More generally, if designing explainable machine learning models is key…

The excellent performance of deep neural networks is usually accompanied by a large number of parameters and computations, which have limited their usage on the resource-limited edge devices. To address this issue, abundant methods such as…

Exploiting pre-trained diffusion models for restoration has recently become a favored alternative to the traditional task-specific training approach. Previous works have achieved noteworthy success by limiting the solution space using…

Supervised learning of deep neural networks heavily relies on large-scale datasets annotated by high-quality labels. In contrast, mislabeled samples can significantly degrade the generalization of models and result in memorizing samples,…

Due to the expensive costs of collecting labels in multi-label classification datasets, partially annotated multi-label classification has become an emerging field in computer vision. One baseline approach to this task is to assume…

The memorization effect of deep neural networks (DNNs) plays a pivotal role in recent label noise learning methods. To exploit this effect, the model prediction-based methods have been widely adopted, which aim to exploit the outputs of…

The remarkable success of pretrain-then-finetune paradigm has led to a proliferation of available pre-trained models for vision tasks. This surge presents a significant challenge in efficiently choosing the most suitable pre-trained models…

Neural coreference resolution models trained on one dataset may not transfer to new, low-resource domains. Active learning mitigates this problem by sampling a small subset of data for annotators to label. While active learning is…

Pixel-wise annotations are notoriously labourious and costly to obtain in the medical domain. To mitigate this burden, weakly supervised approaches based on bounding box annotations-much easier to acquire-offer a practical alternative.…

For speech classification tasks, deep learning models often achieve high accuracy but exhibit shortcomings in calibration, manifesting as classifiers exhibiting overconfidence. The significance of calibration lies in its critical role in…

We found that enforcing guidance throughout the sampling process is often counterproductive due to the model-fitting issue, where samples are 'tuned' to match the classifier's parameters rather than generalizing the expected condition. This…

Multimodal deep learning, especially vision-language models, have gained significant traction in recent years, greatly improving performance on many downstream tasks, including content moderation and violence detection. However, standard…