Image classification is the task of classifying images into various categories.
|Trend||Dataset||Best Method||Paper title||Paper||Code||Compare|
Probabilistic graphical models are traditionally known for their successes in generative modeling. In this work, we advocate layered graphical models (LGMs) for probabilistic discriminative learning.
It achieved a kappa score of 0.525 and an agreement of 66.6% with three pathologists for classifying the predominant patterns, slightly higher than the inter-pathologist kappa score of 0.485 and agreement of 62.7% on this test set. If confirmed in clinical practice, our model can assist pathologists in improving classification of lung adenocarcinoma patterns by automatically pre-screening and highlighting cancerous regions prior to review.
In this paper, we propose a new image classification task called Top-2 classification to evaluate the generalization ability of CNNs and CapsNets. The models are trained on single label image samples same as the traditional image classification task.
If the same patterns also occur at the deeper layers of the network, why wouldn't the same convolutional filters be used also in those layers? In this paper, we propose a CNN architecture, Layer Reuse Network (LruNet), where the convolutional layers are used repeatedly without the need of introducing new layers to get a better performance.
Normalization layers are a staple in state-of-the-art deep neural network architectures. They are widely believed to stabilize training, enable higher learning rate, accelerate convergence and improve generalization, though the reason for their effectiveness is still an active research topic.
SOTA for Image Classification on SVHN
How can prior knowledge on the transformation invariances of a domain be incorporated into the architecture of a neural network? We propose Equivariant Transformers (ETs), a family of differentiable image-to-image mappings that improve the robustness of models towards pre-defined continuous transformation groups.
In this paper, we conduct extensive experiments using various datasets to demonstrate and analyze how and why training based on fine-grain labeling, such as "Persian cat" can improve CNN accuracy on classifying coarse-grain classes, in this case "cat." For example, a CNN trained with fine-grain labels and only 40% of the total training data can achieve higher accuracy than a CNN trained with the full training dataset and coarse-grain labels.
To automate the process of learning a CNN architecture, this letter attempts at finding the relationship between Fully Connected (FC) layers with some of the characteristics of the datasets. (i) What is the impact of deeper/shallow architectures on the performance of the CNN w.r.t FC layers?, (ii) How the deeper/wider datasets influence the performance of CNN w.r.t FC layers?, and (iii) Which kind of architecture (deeper/ shallower) is better suitable for which kind of (deeper/ wider) datasets.
With the rapid increase of large-scale, real-world datasets, it becomes critical to address the problem of long-tailed data distribution (i.e., a few classes account for most of the data, while most classes are under-represented). We design a re-weighting scheme that uses the effective number of samples for each class to re-balance the loss, thereby yielding a class-balanced loss.
The basic principles in designing convolutional neural network (CNN) structures for predicting objects on different levels, e.g., image-level, region-level, and pixel-level are diverging. Generally, network structures designed specifically for image classification are directly used as default backbone structure for other tasks including detection and segmentation, but there is seldom backbone structure designed under the consideration of unifying the advantages of networks designed for pixel-level or region-level predicting tasks, which may require very deep features with high resolution.