Related papers: Beyond the final layer: Attentive multilayer fusio…

Although backpropagation is widely accepted as a training algorithm for artificial neural networks, researchers are always looking for inspiration from the brain to find ways with potentially better performance. Forward-Forward is a novel…

In recent years, deep learning has achieved innovative advancements in various fields, including the analysis of human emotions and behaviors. Initiatives such as the Affective Behavior Analysis in-the-wild (ABAW) competition have been…

With the success of self-supervised representations, researchers seek a better understanding of the information encapsulated within a representation. Among various interpretability methods, we focus on classification-based linear probing.…

Deep neural networks have evolved to become power demanding and consequently difficult to apply to small-size mobile platforms. Network parameter reduction methods have been introduced to systematically deal with the computational and…

The great advances of learning-based approaches in image processing and computer vision are largely based on deeply nested networks that compose linear transfer functions with suitable non-linearities. Interestingly, the most frequently…

While the approximation properties of single-layer Transformer architectures have been studied in recent works, a rigorous theoretical understanding of the multi-layer setting remains limited. In this work, we establish that multi-layer…

Early identification of high-risk ICU patients is crucial for directing limited medical resources. We introduce ALFIA (Adaptive Layer Fusion with Intelligent Attention), a modular, attention-based architecture that jointly trains LoRA…

Results in interpretability suggest that large vision and language models learn implicit linear encodings when models are biased by in-context prompting. However, the existence of similar linear representations in more general adaptation…

Learning based feature matching methods have been commonly studied in recent years. The core issue for learning feature matching is to how to learn (1) discriminative representations for feature points (or regions) within each intra-image…

Federated learning with heterogeneous clients remains a significant challenge for deep learning, primarily due to client drift arising from inconsistent local updates. Existing federated optimization methods typically address this issue…

Neural network models have a reputation for being black boxes. We propose to monitor the features at every layer of a model and measure how suitable they are for classification. We use linear classifiers, which we refer to as "probes",…

Prompt learning has emerged as an efficient alternative for fine-tuning foundational models, such as CLIP, for various downstream tasks. However, there is no work that provides a comprehensive explanation for the working mechanism of the…

Head pose estimation and face alignment constitute a backbone preprocessing for many applications relying on face analysis. While both are closely related tasks, they are generally addressed separately, e.g. by deducing the head pose from…

Head detection provides distribution information of pedestrian, which is crucial for scene statistical analysis, traffic management, and risk assessment and early warning. However, scene complexity and large-scale variation in the real…

Score-based diffusion models have captured widespread attention and funded fast progress of recent vision generative tasks. In this paper, we focus on diffusion model backbone which has been much neglected before. We systematically explore…

Pairwise dot product-based attention allows Transformers to exchange information between tokens in an input-dependent way, and is key to their success across diverse applications in language and vision. However, a typical Transformer model…

Transformer-based models have been achieving state-of-the-art results in several fields of Natural Language Processing. However, its direct application to speech tasks is not trivial. The nature of this sequences carries problems such as…

Transformer networks have achieved remarkable success across diverse domains, leveraging a variety of architectural innovations, including residual connections. However, traditional residual connections, which simply sum the outputs of…

Visual document retrieval has become essential for accessing information in visually rich documents. Existing approaches fall into two camps. Late-interaction retrievers achieve strong quality through fine-grained token-level matching but…

We propose an efficient transfer learning method for adapting ImageNet pre-trained Convolutional Neural Network (CNN) to fine-grained image classification task. Conventional transfer learning methods typically face the trade-off between…