Large language models are visual reasoning coordinators
Visual reasoning requires multimodal perception and commonsense cognition of the world.
Recently, multiple vision-language models (VLMs) have been proposed with excellent …
Recently, multiple vision-language models (VLMs) have been proposed with excellent …
Robust mixture-of-expert training for convolutional neural networks
Abstract Sparsely-gated Mixture of Expert (MoE), an emerging deep model architecture, has
demonstrated a great promise to enable high-accuracy and ultra-efficient model inference …
demonstrated a great promise to enable high-accuracy and ultra-efficient model inference …
Aloft: A lightweight mlp-like architecture with dynamic low-frequency transform for domain generalization
Abstract Domain generalization (DG) aims to learn a model that generalizes well to unseen
target domains utilizing multiple source domains without re-training. Most existing DG works …
target domains utilizing multiple source domains without re-training. Most existing DG works …
Dgmamba: Domain generalization via generalized state space model
Domain generalization (DG) aims at solving distribution shift problems in various scenes.
Existing approaches are based on Convolution Neural Networks (CNNs) or Vision …
Existing approaches are based on Convolution Neural Networks (CNNs) or Vision …
Moe-ffd: Mixture of experts for generalized and parameter-efficient face forgery detection
Deepfakes have recently raised significant trust issues and security concerns among the
public. Compared to CNN face forgery detectors, ViT-based methods take advantage of the …
public. Compared to CNN face forgery detectors, ViT-based methods take advantage of the …
Knowledge distillation-based domain-invariant representation learning for domain generalization
Domain generalization (DG) aims to generalize the knowledge learned from multiple source
domains to unseen target domains. Existing DG techniques can be subsumed under two …
domains to unseen target domains. Existing DG techniques can be subsumed under two …
Graph mixture of experts: Learning on large-scale graphs with explicit diversity modeling
Graph neural networks (GNNs) have found extensive applications in learning from graph
data. However, real-world graphs often possess diverse structures and comprise nodes and …
data. However, real-world graphs often possess diverse structures and comprise nodes and …
Statistical perspective of top-k sparse softmax gating mixture of experts
Top-K sparse softmax gating mixture of experts has been widely used for scaling up massive
deep-learning architectures without increasing the computational cost. Despite its popularity …
deep-learning architectures without increasing the computational cost. Despite its popularity …
How well does gpt-4v (ision) adapt to distribution shifts? a preliminary investigation
In machine learning, generalization against distribution shifts--where deployment conditions
diverge from the training scenarios--is crucial, particularly in fields like climate modeling …
diverge from the training scenarios--is crucial, particularly in fields like climate modeling …
Rethinking domain generalization: Discriminability and generalizability
Domain generalization (DG) endeavours to develop robust models that possess strong
generalizability while preserving excellent discriminability. Nonetheless, pivotal DG …
generalizability while preserving excellent discriminability. Nonetheless, pivotal DG …