Search Results for author:
Found 15 papers, 8 papers with code
StochCA: A Novel Approach for Exploiting Pretrained Models with Cross-Attention
By doing so, queries and channel-mixing multi-layer perceptron layers of a target model are fine-tuned to target tasks to learn how to effectively exploit rich representations of pretrained models.
GTA: Guided Transfer of Spatial Attention from Object-Centric Representations
Through experimental analysis using attention maps in ViT, we observe that the rich representations deteriorate when trained on a small dataset.
Rethinking Evaluation Protocols of Visual Representations Learned via Self-supervised Learning
Linear probing (LP) (and $k$-NN) on the upstream dataset with labels (e. g., ImageNet) and transfer learning (TL) to various downstream datasets are commonly employed to evaluate the quality of visual representations learned via self-supervised learning (SSL).
Few-shot Fine-tuning is All You Need for Source-free Domain Adaptation
These limitations include a lack of principled ways to determine optimal hyperparameters and performance degradation when the unlabeled target data fail to meet certain requirements such as a closed-set and identical label distribution to the source data.
Source-Free Domain Adaptation
Unsupervised Domain Adaptation
Deep Active Learning with Contrastive Learning Under Realistic Data Pool Assumptions
Active learning aims to identify the most informative data from an unlabeled data pool that enables a model to reach the desired accuracy rapidly.
A Unified Benchmark for the Unknown Detection Capability of Deep Neural Networks
Therefore, we introduce the unknown detection task, an integration of previous individual tasks, for a rigorous examination of the detection capability of deep neural networks on a wide spectrum of unknown samples.
Elucidating Robust Learning with Uncertainty-Aware Corruption Pattern Estimation
Robust learning methods aim to learn a clean target distribution from noisy and corrupted training data where a specific corruption pattern is often assumed a priori.
Confidence-Aware Learning for Deep Neural Networks
Despite the power of deep neural networks for a wide range of tasks, an overconfident prediction issue has limited their practical use in many safety-critical applications.
Self-Knowledge Distillation with Progressive Refinement of Targets
Hence, it can be interpreted within a framework of knowledge distillation as a student becomes a teacher itself.
Ranked #1 on
Multimodal Machine Translation
on Multi30K
(BLUE (DE-EN) metric)
Predicting breast tumor proliferation from whole-slide images: the TUPAC16 challenge
The best performing automatic method for the first task achieved a quadratic-weighted Cohen's kappa score of $\kappa$ = 0. 567, 95% CI [0. 464, 0. 671] between the predicted scores and the ground truth.
Accurate Lung Segmentation via Network-Wise Training of Convolutional Networks
We introduce an accurate lung segmentation model for chest radiographs based on deep convolutional neural networks.
A Unified Framework for Tumor Proliferation Score Prediction in Breast Histopathology
We present a unified framework to predict tumor proliferation scores from breast histopathology whole slide images.
Semantic Noise Modeling for Better Representation Learning
From the base model, we introduce a semantic noise modeling method which enables class-conditional perturbation on latent space to enhance the representational power of learned latent feature.
Deconvolutional Feature Stacking for Weakly-Supervised Semantic Segmentation
The unpooling-deconvolution combination helps to eliminate less discriminative features in a feature extraction stage, since output features of the deconvolution layer are reconstructed from the most discriminative unpooled features instead of the raw one.
Self-Transfer Learning for Fully Weakly Supervised Object Localization
With the help of transfer learning which adopts weight parameters of a pre-trained network, the weakly supervised learning framework for object localization performs well because the pre-trained network already has well-trained class-specific features.
