Related papers: Beyond Prototypes: Semantic Anchor Regularization …
Sparse autoencoders (SAEs) are one of the main methods to interpret the inner workings of deep neural networks (DNNs), decomposing activations into higher-dimensional features. However, they exhibit critical shortcomings where a large…
Deep learning models achieve strong performance across various domains but often rely on spurious correlations, making them vulnerable to distribution shifts. This issue is particularly severe in subpopulation shift scenarios, where models…
One of the most significant challenges facing a few-shot learning task is the generalizability of the (meta-)model from the base to the novel categories. Most of existing few-shot learning models attempt to address this challenge by either…
Supervision for metric learning has long been given in the form of equivalence between human-labeled classes. Although this type of supervision has been a basis of metric learning for decades, we argue that it hinders further advances in…
Research on speech processing has traditionally considered the task of designing hand-engineered acoustic features (feature engineering) as a separate distinct problem from the task of designing efficient machine learning (ML) models to…
Zero-shot learning (ZSL) aims at recognizing classes for which no visual sample is available at training time. To address this issue, one can rely on a semantic description of each class. A typical ZSL model learns a mapping between the…
Unsupervised medical anomaly detection is severely limited by the scarcity of normal training samples. Existing methods typically train dedicated models for each dataset or disease, requiring hundreds of normal images per task and lacking…
Continual Learning (CL) aims to enable models to sequentially learn multiple tasks without forgetting previous knowledge. Recent studies have shown that optimizing towards flatter loss minima can improve model generalization. However,…
As neural networks increasingly make critical decisions in high-stakes settings, monitoring and explaining their behavior in an understandable and trustworthy manner is a necessity. One commonly used type of explainer is post hoc feature…
Human action understanding is crucial for the advancement of multimodal systems. While recent developments, driven by powerful large language models (LLMs), aim to be general enough to cover a wide range of categories, they often overlook…
Complex structures are typical in machine learning. Tailoring learning algorithms for every structure requires an effort that may be saved by defining a generic learning procedure adaptive to any complex structure. In this paper, we propose…
The role of semantics in zero-shot learning is considered. The effectiveness of previous approaches is analyzed according to the form of supervision provided. While some learn semantics independently, others only supervise the semantic…
One-shot semantic image segmentation aims to segment the object regions for the novel class with only one annotated image. Recent works adopt the episodic training strategy to mimic the expected situation at testing time. However, these…
Streaming neural network models for fast frame-wise responses to various speech and sensory signals are widely adopted on resource-constrained platforms. Hence, increasing the learning capacity of such streaming models (i.e., by adding more…
Centralized training is the standard paradigm in deep learning, enabling models to learn from a unified dataset in a single location. In such setup, isotropic feature distributions naturally arise as a mean to support well-structured and…
Zero-Shot Learning (ZSL) presents the challenge of identifying categories not seen during training. This task is crucial in domains where it is costly, prohibited, or simply not feasible to collect training data. ZSL depends on a mapping…
Compact models often lose the structure of their embedding space. The issue shows up when the capacity is tight or the data spans several languages. Such collapse makes it difficult for downstream tasks to build on the resulting…
Though offering amazing contextualized token-level representations, current pre-trained language models take less attention on accurately acquiring sentence-level representation during their self-supervised pre-training. However,…
Symmetric objects are common in daily life and industry, yet their inherent orientation ambiguities that impede the training of deep learning networks for pose estimation are rarely discussed in the literature. To cope with these…
Self-supervised pretraining has been extensively studied in language and vision domains, where a unified model can be easily adapted to various downstream tasks by pretraining representations without explicit labels. When it comes to…