Related papers: Information Bottleneck Approach to Spatial Attenti…
Blind-spot networks (BSN) have been prevalent neural architectures in self-supervised image denoising (SSID). However, most existing BSNs are conducted with convolution layers. Although transformers have shown the potential to overcome the…
We propose augmenting deep neural networks with an attention mechanism for the visual object detection task. As perceiving a scene, humans have the capability of multiple fixation points, each attended to scene content at different…
Large vision-language models show tremendous potential in understanding visual information through human languages. However, they are prone to suffer from object hallucination, i.e., the generated image descriptions contain objects that do…
Deep neural networks perform well on classification tasks where data streams are i.i.d. and labeled data is abundant. Challenges emerge with non-stationary training data streams such as continual learning. One powerful approach that has…
Concept-bottleneck models (CBMs) are neural classifiers that compute predictions from high-level concepts extracted from the input. CBMs ensure stakeholders can understand the concepts -- and the predictions they entail -- by learning these…
The Information Bottleneck (IB) method frequently suffers from unstable optimization, characterized by abrupt representation shifts near critical points of the IB trade-off parameter, beta. In this paper, I introduce a novel approach to…
Statistical shape modeling (SSM) directly from 3D medical images is an underutilized tool for detecting pathology, diagnosing disease, and conducting population-level morphology analysis. Deep learning frameworks have increased the…
Mapping X-ray images, radiology reports, and other medical data as binary codes in the common space, which can assist clinicians to retrieve pathology-related data from heterogeneous modalities (i.e., hashing-based cross-modal medical data…
The ability to make sense of the massive amounts of high-dimensional data generated from molecular dynamics (MD) simulations is heavily dependent on the knowledge of a low dimensional manifold (parameterized by a reaction coordinate or RC)…
Attention networks have successfully boosted the performance in various vision problems. Previous works lay emphasis on designing a new attention module and individually plug them into the networks. Our paper proposes a novel-and-simple…
By "intelligently" fusing the complementary information across different views, multi-view learning is able to improve the performance of classification tasks. In this work, we extend the information bottleneck principle to a supervised…
Numerous deep learning algorithms have been inspired by and understood via the notion of information bottleneck, where unnecessary information is (often implicitly) minimized while task-relevant information is maximized. However, a rigorous…
Visual attention is a fundamental mechanism in the human brain, and it inspires the design of attention mechanisms in deep neural networks. However, most of the visual attention studies adopted eye-tracking data rather than the direct…
The training dynamics of hidden layers in deep learning are poorly understood in theory. Recently, the Information Plane (IP) was proposed to analyze them, which is based on the information-theoretic concept of mutual information (MI). The…
Multi-label classification (MLC) of medical images aims to identify multiple diseases and holds significant clinical potential. A critical step is to learn class-specific features for accurate diagnosis and improved interpretability…
Spiking neural networks (SNNs) mimic brain computational strategies, and exhibit substantial capabilities in spatiotemporal information processing. As an essential factor for human perception, visual attention refers to the dynamic process…
Semantic communication shifts the focus from bit-level accuracy to task-relevant semantic delivery, enabling efficient and intelligent communication for next-generation networks. However, existing multi-modal solutions often process all…
In this manuscript, we study the learning of deep attention neural networks, defined as the composition of multiple self-attention layers, with tied and low-rank weights. We first establish a mapping of such models to sequence multi-index…
In computer vision, the performance of deep neural networks (DNNs) is highly related to the feature extraction ability, i.e., the ability to recognize and focus on key pixel regions in an image. However, in this paper, we quantitatively and…
Exploiting recent developments in information theory, we propose, illustrate, and validate a principled information-theoretic algorithm for module discovery and resulting measure of network modularity. This measure is an order parameter (a…