In contrast to existing quantization with low precision data format and projection layer, we propose a novel method based on shared labels, which focuses on compressing the fully-connected layer before Softmax for models with a huge number of labels in TTS polyphone selection.
CPR reduces the semantic variance by selecting a semantic centre point in a neighbourhood region to replace the initial annotated point.
An obvious obstacle lies in the absence of a specific benchmark to evaluate the effectiveness of MLLMs on aesthetic perception.
In this paper, we introduce a cost-effective category-specific segmenter using SAM.
Object detection via inaccurate bounding boxes supervision has boosted a broad interest due to the expensive high-quality annotation data or the occasional inevitability of low annotation quality (\eg tiny objects).
Besides, experiments with different training datasets, different optimization objectives and different machine learning platforms verify that HyperTuner can well adapt to various data analytic service scenarios.
Aspect sentiment triplet extraction is a subtask of aspect based sentiment analysis, which has attracted considerable attention in recent years.
However, the performance gap between point supervised object detection (PSOD) and bounding box supervised detection remains large.
In this paper, we propose a novel collaborative training paradigm with global and local representation learning for robust medical image classification from noisy-labeled data to combat the lack of high quality annotated medical data.
Due to the difficulty of collecting exhaustive multi-label annotations, multi-label datasets often contain partial labels.
In this study, we propose a POL method using coarse point annotations, relaxing the supervision signals from accurate key points to freely spotted points.
Value function is the central notion of Reinforcement Learning (RL).
From this adaptation, we split the data in target domain into confident and uncertain subdomains using the proposed uncertainty-based ranking function, through measuring their prediction confidences.
The noise in stochastic gradient descent (SGD) provides a crucial implicit regularization effect, previously studied in optimization by analyzing the dynamics of parameter updates.
In this work, we present a theoretical hypothesis testing and prove that noise in real-world dataset is unlikely to be CCN, which confirms that label noise should depend on the instance and justifies the urgent need to go beyond the CCN assumption. The theoretical results motivate us to study the more general and practical-relevant instance-dependent noise (IDN).
Ranked #44 on Image Classification on Clothing1M
For validation, we prove that a noisy validation set is reliable, addressing the critical demand of model selection in scenarios like hyperparameter-tuning and early stopping.
In this paper, we design an integrated simulation-prediction system which estimates the Origin-Destination (OD) matrix of a road network using only flow rate information and predicts the behavior of the road network in different simulation scenarios.
1 code implementation • 22 Jun 2019 • Guangyong Chen, Pengfei Chen, Chang-Yu Hsieh, Chee-Kong Lee, Benben Liao, Renjie Liao, Weiwen Liu, Jiezhong Qiu, Qiming Sun, Jie Tang, Richard Zemel, Shengyu Zhang
We introduce a new molecular dataset, named Alchemy, for developing machine learning models useful in chemistry and material science.
Most recent efforts have been devoted to defending noisy labels by discarding noisy samples from the training set or assigning weights to training samples, where the weight associated with a noisy sample is expected to be small.
The IGNN model is based on an elegant and fundamental idea in information theory as explained in the main text, and it could be easily generalized beyond the contexts of molecular graphs considered in this work.
Value functions are crucial for model-free Reinforcement Learning (RL) to obtain a policy implicitly or guide the policy updates.
Our work is based on an excellent idea that whitening the inputs of neural networks can achieve a fast convergence speed.
Noisy labels are ubiquitous in real-world datasets, which poses a challenge for robustly training deep neural networks (DNNs) as DNNs usually have the high capacity to memorize the noisy labels.
Ranked #37 on Image Classification on mini WebVision 1.0
In Variational Auto-Encoder (VAE), the default choice of reconstruction loss function between the decoded sample and the input is the squared $L_2$.
This framework 1) effectively enlarges the receptive fields (RF) of the network to aggregate global information; 2) alleviates what we call the "gridding issue" caused by the standard dilated convolution operation.
Ranked #20 on Semantic Segmentation on PASCAL VOC 2012 test