RESUMO
Class incremental learning (CIL) aims to incrementally update a trained model with the new classes of samples (plasticity) while retaining previously learned ability (stability). To address the most challenging issue in this goal, i.e., catastrophic forgetting, the mainstream paradigm is memory-replay CIL, which consolidates old knowledge by replaying a small number of old classes of samples saved in the memory. Despite effectiveness, the inherent destruction-reconstruction dynamics in memory-replay CIL are an intrinsic limitation: if the old knowledge is severely destructed, it will be quite hard to reconstruct the lossless counterpart. Our theoretical analysis shows that the destruction of old knowledge can be effectively alleviated by balancing the contribution of samples from the current phase and those saved in the memory. Motivated by this theoretical finding, we propose a novel Balanced Destruction-Reconstruction module (BDR) for memory-replay CIL, which can achieve better knowledge reconstruction by reducing the degree of maximal destruction of old knowledge. Specifically, to achieve a better balance between old knowledge and new classes, the proposed BDR module takes into account two factors: the variance in training status across different classes and the quantity imbalance1 of samples from the current phase and memory. By dynamically manipulating the gradient during training based on these factors, BDR can effectively alleviate knowledge destruction and improve knowledge reconstruction. Extensive experiments on a range of CIL benchmarks have shown that as a lightweight plug-and-play module, BDR can significantly improve the performance of existing state-of-the-art methods with good generalization. Our code is publicly available here.
RESUMO
Vision-Language Pre-training (VLP) that utilizes the multi-modal information to promote the training efficiency and effectiveness, has achieved great success in vision recognition of natural domains and shown promise in medical imaging diagnosis for the Chest X-Rays (CXRs). However, current works mainly pay attention to the exploration on single dataset of CXRs, which locks the potential of this powerful paradigm on larger hybrid of multi-source CXRs datasets. We identify that although blending samples from the diverse sources offers the advantages to improve the model generalization, it is still challenging to maintain the consistent superiority for the task of each source due to the existing heterogeneity among sources. To handle this dilemma, we design a Conquer-and-Divide pre-training framework, termed as UniChest, aiming to make full use of the collaboration benefit of multiple sources of CXRs while reducing the negative influence of the source heterogeneity. Specially, the "Conquer" stage in UniChest encourages the model to sufficiently capture multi-source common patterns, and the "Divide" stage helps squeeze personalized patterns into different small experts (query networks). We conduct thorough experiments on many benchmarks, e.g., ChestX-ray14, CheXpert, Vindr-CXR, Shenzhen, Open-I and SIIM-ACR Pneumothorax, verifying the effectiveness of UniChest over a range of baselines, and release our codes and pre-training models at https://github.com/Elfenreigen/UniChest.
Assuntos
Algoritmos , Radiografia Torácica , Humanos , Radiografia Torácica/métodos , Interpretação de Imagem Radiográfica Assistida por Computador/métodos , Bases de Dados FactuaisRESUMO
Learning with noisy labels has become imperative in the Big Data era, which saves expensive human labors on accurate annotations. Previous noise-transition-based methods have achieved theoretically-grounded performance under the Class-Conditional Noise model (CCN). However, these approaches builds upon an ideal but impractical anchor set available to pre-estimate the noise transition. Even though subsequent works adapt the estimation as a neural layer, the ill-posed stochastic learning of its parameters in back-propagation easily falls into undesired local minimums. We solve this problem by introducing a Latent Class-Conditional Noise model (LCCN) to parameterize the noise transition under a Bayesian framework. By projecting the noise transition into the Dirichlet space, the learning is constrained on a simplex characterized by the complete dataset, instead of some ad-hoc parametric space wrapped by the neural layer. We then deduce a dynamic label regression method for LCCN, whose Gibbs sampler allows us efficiently infer the latent true labels to train the classifier and to model the noise. Our approach safeguards the stable update of the noise transition, which avoids previous arbitrarily tuning from a mini-batch of samples. We further generalize LCCN to different counterparts compatible with open-set noisy labels, semi-supervised learning as well as cross-model training. A range of experiments demonstrate the advantages of LCCN and its variants over the current state-of-the-art methods. The code is available at here.
Assuntos
Algoritmos , Big Data , Humanos , Teorema de Bayes , Aprendizado de Máquina SupervisionadoRESUMO
Graphs with complete node attributes have been widely explored recently. While in practice, there is a graph where attributes of only partial nodes could be available and those of the others might be entirely missing. This attribute-missing graph is related to numerous real-world applications and there are limited studies investigating the corresponding learning problems. Existing graph learning methods including the popular GNN cannot provide satisfied learning performance since they are not specified for attribute-missing graphs. Thereby, designing a new GNN for these graphs is a burning issue to the graph learning community. In this article, we make a shared-latent space assumption on graphs and develop a novel distribution matching-based GNN called structure-attribute transformer (SAT) for attribute-missing graphs. SAT leverages structures and attributes in a decoupled scheme and achieves the joint distribution modeling of structures and attributes by distribution matching techniques. It could not only perform the link prediction task but also the newly introduced node attribute completion task. Furthermore, practical measures are introduced to quantify the performance of node attribute completion. Extensive experiments on seven real-world datasets indicate SAT shows better performance than other methods on both link prediction and node attribute completion tasks.
RESUMO
There is an emerging trend to leverage noisy image datasets in many visual recognition tasks. However, the label noise among datasets severely degenerates the performance of deep learning approaches. Recently, one mainstream is to introduce the latent label to handle label noise, which has shown promising improvement in the network designs. Nevertheless, the mismatch between latent labels and noisy labels still affects the predictions in such methods. To address this issue, we propose a probabilistic model, which explicitly introduces an extra variable to represent the trustworthiness of noisy labels, termed as the quality variable. Our key idea is to identify the mismatch between the latent and noisy labels by embedding the quality variables into different subspaces, which effectively minimizes the influence of label noise. At the same time, reliable labels are still able to be applied for training. To instantiate the model, we further propose a Contrastive-Additive Noise network (CAN), which consists of two important layers: (1) the contrastive layer that estimates the quality variable in the embedding space to reduce the influence of noisy labels; and (2) the additive layer that aggregates the prior prediction and noisy labels as the posterior to train the classifier. Moreover, to tackle the challenges in optimization, we deduce an SGD algorithm with the reparameterization tricks, which makes our method scalable to big data.We validate the proposed method on a range of noisy image datasets. Comprehensive results have demonstrated that CAN outperforms the state-of-the-art deep learning approaches.
RESUMO
A series of 3-(4-phenoxyphenyl)-1H-pyrazoles were synthesized and characterized as potent state-dependent sodium channel blockers. A limited SAR study was carried out to delineate the chemical requirements for potency. The results indicate that the distal phenyl group is critical for activity but will tolerate lipophilic (+pi) electronegative (+sigma) substituents at the ortho and/or para position. Substitution at the pyrazole nitrogen with a H-bond donor improves potency. Compound 18 showed robust activity in the rat Chung neuropathy paradigm.
Assuntos
Analgésicos/síntese química , Pirazóis/síntese química , Bloqueadores dos Canais de Sódio/síntese química , Analgésicos/química , Analgésicos/farmacologia , Animais , Linhagem Celular , Humanos , Masculino , Dor/tratamento farmacológico , Dor/etiologia , Técnicas de Patch-Clamp , Doenças do Sistema Nervoso Periférico/complicações , Doenças do Sistema Nervoso Periférico/tratamento farmacológico , Pirazóis/química , Pirazóis/farmacologia , Ratos , Ratos Sprague-Dawley , Bloqueadores dos Canais de Sódio/química , Bloqueadores dos Canais de Sódio/farmacologia , Relação Estrutura-AtividadeRESUMO
A new general route to conjugated enynyl ketones was developed based on a two-step procedure. First, palladium-catalyzed cross-coupling reactions of 1-(benzotriazol-1-yl)propargyl ethyl ether (3) and vinyl triflates or vinyl bromides afforded the key intermediates [1-(benzotriazol-1-yl)-1-enynyl]methyl ethyl ethers 5a-d in good yields. Then reactions of compounds 5 with primary halides gave intermediates 8, which were hydrolyzed by dilute acid to enynyl ketones 9a-g. Similar palladium-catalyzed coupling reactions of 3 with various aryl iodides followed by an analogous sequence afforded aryl-substituted propargyl ethers 12a-d and thence alkynyl ketones 13a,b.