Search Results for author:
Found 13 papers, 5 papers with code
Interactive Multi-Head Self-Attention with Linear Complexity
In this work, we propose an effective method to decompose the attention operation into query- and key-less components.
Gramian Attention Heads are Strong yet Efficient Vision Learners
We introduce a novel architecture design that enhances expressiveness by incorporating multiple head classifiers (\ie, classification heads) instead of relying on channel expansion or additional building blocks.
Towards long-tailed, multi-label disease classification from chest X-ray: Overview of the CXR-LT challenge
Many real-world image recognition problems, such as diagnostic medical imaging exams, are "long-tailed" $\unicode{x2013}$ there are a few common findings followed by many more relatively rare conditions.
Robust Asymmetric Loss for Multi-Label Long-Tailed Learning
Although a model can be highly fine-tuned due to a large number of hyper-parameters, it is difficult to optimize all hyper-parameters at the same time, and there might be a risk of overfitting a model.
Fine-Grained Self-Supervised Learning with Jigsaw Puzzles for Medical Image Classification
Therefore, in this paper, we introduce Fine-Grained Self-Supervised Learning(FG-SSL) method for classifying subtle lesions in medical images.
Spatial Bias for Attention-free Non-local Neural Networks
Our method is very fast and lightweight due to the attention-free non-local method while improving the performance of neural networks considerably.
Generalized Convolutional Forest Networks for Domain Generalization and Visual Recognition
When constructing random forests, it is of prime importance to ensure high accuracy and low correlation of individual tree classifiers for good performance.
Collaborative Training of Balanced Random Forests for Open Set Domain Adaptation
In this paper, we introduce a collaborative training algorithm of balanced random forests with convolutional neural networks for domain adaptation tasks.
OmniMVS: End-to-End Learning for Omnidirectional Stereo Matching
The 3D encoder-decoder block takes the aligned feature volume to produce the omnidirectional depth estimate with regularization on uncertain regions utilizing the global context information.
SweepNet: Wide-baseline Omnidirectional Depth Estimation
Omnidirectional depth sensing has its advantage over the conventional stereo systems since it enables us to recognize the objects of interest in all directions without any blind regions.
DFT-based Transformation Invariant Pooling Layer for Visual Classification
The proposed methods are extensively evaluated on various classification tasks using the ImageNet, CUB 2010-2011, MIT Indoors, Caltech 101, FMD and DTD datasets.
Recognizing Dynamic Scenes with Deep Dual Descriptor based on Key Frames and Key Segments
A fully connected layer is used to select the key frames and key segments, while the convolutional layer is used to describe them.
SSPP-DAN: Deep Domain Adaptation Network for Face Recognition with Single Sample Per Person
In the proposed approach, domain adaptation, feature extraction, and classification are performed jointly using a deep architecture with domain-adversarial training.
