State classification of objects and their relations is core to many long-horizon tasks, particularly in robot planning and manipulation. However, the combinatorial explosion of possible object-predicate combinations, coupled with the need to adapt to novel real-world environments, makes it a desideratum for state classification models to generalize to novel queries with few examples. To this end, we propose PHIER, which leverages predicate hierarchies to generalize effectively in few-shot scenarios. PHIER uses an object-centric scene encoder, self-supervised losses that infer semantic relations between predicates, and a hyperbolic distance metric that captures hierarchical structure; it learns a structured latent space of image-predicate pairs that guides reasoning over state classification queries. We evaluate PHIER in the CALVIN and BEHAVIOR robotic environments and show that PHIER significantly outperforms existing methods in few-shot, out-of-distribution state classification, and demonstrates strong zero- and few-shot generalization from simulated to real-world tasks. Our results demonstrate that leveraging predicate hierarchies improves performance on state classification tasks with limited data.
This paper addresses representational block named Hierarchical-Split Block, which can be taken as a plug-and-play block to upgrade existing convolutional neural networks, improves model performance significantly in a network. Hierarchical-Split Block contains many hierarchical split and concatenate connections within one single residual block. We find multi-scale features is of great importance for numerous vision tasks. Moreover, Hierarchical-Split block is very flexible and efficient, which provides a large space of potential network architectures for different applications. In this work, we present a common backbone based on Hierarchical-Split block for tasks: image classification, object detection, instance segmentation and semantic image segmentation/parsing. Our approach shows significant improvements over all these core tasks in comparison with the baseline. As shown in Figure1, for image classification, our 50-layers network(HS-ResNet50) achieves 81.28% top-1 accuracy with competitive latency on ImageNet-1k dataset. It also outperforms most state-of-the-art models. The source code and models will be available on: https://github.com/PaddlePaddle/PaddleClas
Fine-grained image recognition is very challenging due to the difficulty of capturing both semantic global features and discriminative local features. Meanwhile, these two features are not easy to be integrated, which are even conflicting when used simultaneously. In this paper, a retrieval-based coarse-to-fine framework is proposed, where we re-rank the TopN classification results by using the local region enhanced embedding features to improve the Top1 accuracy (based on the observation that the correct category usually resides in TopN results). To obtain the discriminative regions for distinguishing the fine-grained images, we introduce a weakly-supervised method to train a box generating branch with only image-level labels. In addition, to learn more effective semantic global features, we design a multi-level loss over an automatically constructed hierarchical category structure. Experimental results show that our method achieves state-of-the-art performance on three benchmarks: CUB-200-2011, Stanford Cars, and FGVC Aircraft. Also, visualizations and analysis are provided for better understanding.
Deep Neural Networks (DNN's) are a widely-used solution for a variety of machine learning problems. However, it is often necessary to invest a significant amount of a data scientist's time to pre-process input data, test different neural network architectures, and tune hyper-parameters for optimal performance. Automated machine learning (autoML) methods automatically search the architecture and hyper-parameter space for optimal neural networks. However, current state-of-the-art (SOTA) methods do not include traditional methods for manipulating input data as part of the algorithmic search space. We adapt the Evolutionary Multi-objective Algorithm Design Engine (EMADE), a multi-objective evolutionary search framework for traditional machine learning methods, to perform neural architecture search. We also integrate EMADE's signal processing and image processing primitives. These primitives allow EMADE to manipulate input data before ingestion into the simultaneously evolved DNN. We show that including these methods as part of the search space shows potential to provide benefits to performance on the CIFAR-10 image classification benchmark dataset.
Image distortion classification and detection is an important task in many applications. For example when compressing images, if we know the exact location of the distortion, then it is possible to re-compress images by adjusting the local compression level dynamically. In this paper, we address the problem of detecting the distortion region and classifying the distortion type of a given image. We show that our model significantly outperforms the state-of-the-art distortion classifier, and report accurate detection results for the first time. We expect that such results prove the usefulness of our approach in many potential applications such as image compression or distortion restoration.
Prototypes in classification models are almost always vectors, and a vector has no readable form. This paper asks what happens when a prototype is an image. Documents give the question a natural form, because a document can be rendered as a multi-channel image in which every token becomes a pixel, so a class representative can take the same shape and the same channel semantics as the inputs it stands for. ProtoSemImage represents each class by one or more visual archetypes: prototype images in a four-channel HSV space whose channels carry named linguistic factors. A Skip-Gram objective learns that color space end to end through a four-dimensional bottleneck, discourse boundary rows become differentiable typed difference rows, and classification reduces to 2D visual template matching: a deformable row alignment between a document image and the archetype bank, in the spirit of dynamic time warping. Because the match is a spatial pattern comparison rather than a linear readout, the model reports where an input departs from its archetype and along which channel, and a generative head decodes each archetype back into text. The image representation works: it beats an otherwise identical model with vector prototypes in all three paired seeds, by between 4.3 and 11.8 points on a ten-class task. The distance-based matching does not. A diagnostic that keeps the representation fixed and swaps only the classifier recovers the sequence baselines, which locates a 20.6-point shortfall in the matching rather than in the color compression, and a benchmark built so that a pair of documents shares a bag of words and differs only in arrangement confirms the layout-preservation it was designed for. We report both directions, because for a representation whose whole purpose is inspect ability, the failure modes are as informative as the gains.
Deep artificial neural networks have made remarkable progress in different tasks in the field of computer vision. However, the empirical analysis of these models and investigation of their failure cases has received attention recently. In this work, we show that deep learning models cannot generalize to atypical images that are substantially different from training images. This is in contrast to the superior generalization ability of the visual system in the human brain. We focus on Convolutional Neural Networks (CNN) as the state-of-the-art models in object recognition and classification; investigate this problem in more detail, and hypothesize that training CNN models suffer from unstructured loss minimization. We propose computational models to improve the generalization capacity of CNNs by considering how typical a training image looks like. By conducting an extensive set of experiments we show that involving a typicality measure can improve the classification results on a new set of images by a large margin. More importantly, this significant improvement is achieved without fine-tuning the CNN model on the target image set.
Hyperspectral Image Classification (HSIC) is a difficult task due to high inter and intra-class similarity and variability, nested regions, and overlapping. 2D Convolutional Neural Networks (CNN) emerged as a viable network whereas, 3D CNNs are a better alternative due to accurate classification. However, 3D CNNs are highly computationally complex due to their volume and spectral dimensions. Moreover, down-sampling and hierarchical filtering (high frequency) i.e., texture features need to be smoothed during the forward pass which is crucial for accurate HSIC. Furthermore, CNN requires tons of tuning parameters which increases the training time. Therefore, to overcome the aforesaid issues, Sharpened Cosine Similarity (SCS) concept as an alternative to convolutions in a Neural Network for HSIC is introduced. SCS is exceptionally parameter efficient due to skipping the non-linear activation layers, normalization, and dropout after the SCS layer. Use of MaxAbsPool instead of MaxPool which selects the element with the highest magnitude of activity, even if it's negative. Experimental results on publicly available HSI datasets proved the performance of SCS as compared to the convolutions in Neural Networks.
Deep Neural Networks have often been called the black box because of the complex, deep architecture and non-transparency presented by the inner layers. There is a lack of trust to use Artificial Intelligence in critical and high-precision fields such as security, finance, health, and manufacturing industries. A lot of focused work has been done to provide interpretable models, intending to deliver meaningful insights into the thoughts and behavior of neural networks. In our research, we compare the state-of-the-art methods in the Activation-based methods (ABM) for interpreting predictions of CNN models, specifically in the application of Image Classification. We then extend the same for eight CNN-based architectures to compare the differences in visualization and thus interpretability. We introduced a novel technique Feature CAM, which falls in the perturbation-activation combination, to create fine-grained, class-discriminative visualizations. The resulting saliency maps from our experiments proved to be 3-4 times better human interpretable than the state-of-the-art in ABM. At the same time it reserves machine interpretability, which is the average confidence scores in classification.
We have developed a deep learning network for classification of different flowers. For this, we have used Visual Geometry Group's 102 category flower dataset having 8189 images of 102 different flowers from University of Oxford. The method is basically divided into two parts; Image segmentation and classification. We have compared the performance of two different Convolutional Neural Network architectures GoogLeNet and AlexNet for classification purpose. By keeping the hyper parameters same for both architectures, we have found that the top 1 and top 5 accuracies of GoogLeNet are 47.15% and 69.17% respectively whereas the top 1 and top 5 accuracies of AlexNet are 43.39% and 68.68% respectively. These results are extremely good when compared to random classification accuracy of 0.98%. This method for classification of flowers can be implemented in real time applications and can be used to help botanists for their research as well as camping enthusiasts.
Eye movements have been widely investigated to study the atypical visual attention in Autism Spectrum Disorder (ASD). The majority of these studies have been focused on limited eye movement features by statistical comparisons between ASD and Typically Developing (TD) groups, which make it difficult to accurately separate ASD from TD at the individual level. The deep learning technology has been highly successful in overcoming this issue by automatically extracting features important for classification through a data-driven learning process. However, there is still a lack of end-to-end deep learning framework for recognition of abnormal attention in ASD. In this study, we developed a novel two-stream deep learning network for this recognition based on 700 images and corresponding eye movement patterns of ASD and TD, and obtained an accuracy of 0.95, which was higher than the previous state-of-the-art. We next characterized contributions to the classification at the single image level and non-linearly integration of this single image level information during the classification. Moreover, we identified a group of pixel-level visual features within these images with greater impacts on the classification. Together, this two-stream deep learning network provides us a novel and powerful tool to recognize and understand abnormal visual attention in ASD.
Although various methods have been proposed for multi-label classification, most approaches still follow the feature learning mechanism of the single-label (multi-class) classification, namely, learning a shared image feature to classify multiple labels. However, we find this One-shared-Feature-for-Multiple-Labels (OFML) mechanism is not conducive to learning discriminative label features and makes the model non-robustness. For the first time, we mathematically prove that the inferiority of the OFML mechanism is that the optimal learned image feature cannot maintain high similarities with multiple classifiers simultaneously in the context of minimizing cross-entropy loss. To address the limitations of the OFML mechanism, we introduce the One-specific-Feature-for-One-Label (OFOL) mechanism and propose a novel disentangled label feature learning (DLFL) framework to learn a disentangled representation for each label. The specificity of the framework lies in a feature disentangle module, which contains learnable semantic queries and a Semantic Spatial Cross-Attention (SSCA) module. Specifically, learnable semantic queries maintain semantic consistency between different images of the same label. The SSCA module localizes the label-related spatial regions and aggregates located region features into the corresponding label feature to achieve feature disentanglement. We achieve state-of-the-art performance on eight datasets of three tasks, \ie, multi-label classification, pedestrian attribute recognition, and continual multi-label learning.
The field of Explainable Artificial Intelligence (XAI) aims to improve the interpretability of black-box machine learning models. Building a heatmap based on the importance value of input features is a popular method for explaining the underlying functions of such models in producing their predictions. Heatmaps are almost understandable to humans, yet they are not without flaws. Non-expert users, for example, may not fully understand the logic of heatmaps (the logic in which relevant pixels to the model's prediction are highlighted with different intensities or colors). Additionally, objects and regions of the input image that are relevant to the model prediction are frequently not entirely differentiated by heatmaps. In this paper, we propose a framework called TbExplain that employs XAI techniques and a pre-trained object detector to present text-based explanations of scene classification models. Moreover, TbExplain incorporates a novel method to correct predictions and textually explain them based on the statistics of objects in the input image when the initial prediction is unreliable. To assess the trustworthiness and validity of the text-based explanations, we conducted a qualitative experiment, and the findings indicated that these explanations are sufficiently reliable. Furthermore, our quantitative and qualitative experiments on TbExplain with scene classification datasets reveal an improvement in classification accuracy over ResNet variants.
Intracerebral hemorrhage (ICH) is a severe and sudden medical condition caused by the rupture of blood vessels in the brain, leading to permanent damage to brain tissue and often resulting in functional disabilities or death in patients. Diagnosis and analysis of ICH typically rely on brain CT imaging. Given the urgency of ICH conditions, early treatment is crucial, necessitating rapid analysis of CT images to formulate tailored treatment plans. However, the complexity of ICH CT images and the frequent scarcity of specialist radiologists pose significant challenges. Therefore, we collect a dataset from the real world for ICH and normal classification and three types of ICH image classification based on the hemorrhage location, i.e., Deep, Subcortical, and Lobar. In addition, we propose a neural network structure, dual-task vision transformer (DTViT), for the automated classification and diagnosis of ICH images. The DTViT deploys the encoder from the Vision Transformer (ViT), employing attention mechanisms for feature extraction from CT images. The proposed DTViT framework also incorporates two multilayer perception (MLP)-based decoders to simultaneously identify the presence of ICH and classify the three types of hemorrhage locations. Experimental results demonstrate that DTViT performs well on the real-world test dataset. The code and newly collected dataset for this work are available at: https://github.com/jfan1997/DTViT.
With the rapid development of deep learning technology and improvement in computing capability, deep learning has been widely used in the field of hyperspectral image (HSI) classification. In general, deep learning models often contain many trainable parameters and require a massive number of labeled samples to achieve optimal performance. However, in regard to HSI classification, a large number of labeled samples is generally difficult to acquire due to the difficulty and time-consuming nature of manual labeling. Therefore, many research works focus on building a deep learning model for HSI classification with few labeled samples. In this article, we concentrate on this topic and provide a systematic review of the relevant literature. Specifically, the contributions of this paper are twofold. First, the research progress of related methods is categorized according to the learning paradigm, including transfer learning, active learning and few-shot learning. Second, a number of experiments with various state-of-the-art approaches has been carried out, and the results are summarized to reveal the potential research directions. More importantly, it is notable that although there is a vast gap between deep learning models (that usually need sufficient labeled samples) and the HSI scenario with few labeled samples, the issues of small-sample sets can be well characterized by fusion of deep learning methods and related techniques, such as transfer learning and a lightweight model. For reproducibility, the source codes of the methods assessed in the paper can be found at https://github.com/ShuGuoJ/HSI-Classification.git.
In this paper we study the problem of estimating the migration direction of cells based on a single image. To the best of our knowledge, there is only one related work that uses a classification CNN for four classes (quadrants). This approach does not allow detailed directional resolution. We solve the single image estimation problem using deep circular regression with special attention to cycle-sensitive methods. On two databases we achieve an average accuracy of $\sim$17 degrees, which is a significant improvement over the previous work.
Remote sensing image classification exploiting multiple sensors is a very challenging problem: data from different modalities are affected by spectral distortions and mis-alignments of all kinds, and this hampers re-using models built for one image to be used successfully in other scenes. In order to adapt and transfer models across image acquisitions, one must be able to cope with datasets that are not co-registered, acquired under different illumination and atmospheric conditions, by different sensors, and with scarce ground references. Traditionally, methods based on histogram matching have been used. However, they fail when densities have very different shapes or when there is no corresponding band to be matched between the images. An alternative builds upon \emph{manifold alignment}. Manifold alignment performs a multidimensional relative normalization of the data prior to product generation that can cope with data of different dimensionality (e.g. different number of bands) and possibly unpaired examples. Aligning data distributions is an appealing strategy, since it allows to provide data spaces that are more similar to each other, regardless of the subsequent use of the transformed data. In this paper, we study a methodology that aligns data from different domains in a nonlinear way through {\em kernelization}. We introduce the Kernel Manifold Alignment (KEMA) method, which provides a flexible and discriminative projection map, exploits only a few labeled samples (or semantic ties) in each domain, and reduces to solving a generalized eigenvalue problem. We successfully test KEMA in multi-temporal and multi-source very high resolution classification tasks, as well as on the task of making a model invariant to shadowing for hyperspectral imaging.
This paper discusses the challenges of using big Earth observation data for land classification. The approach taken is to consider pure data-driven methods to be insufficient to represent continuous change. We argue for sound theories when working with big data. After revising existing classification schemes such as FAO's Land Cover Classification System (LCCS), we conclude that LCCS and similar proposals cannot capture the complexity of landscape dynamics. We then investigate concepts that are being used for analyzing satellite image time series; we show these concepts to be instances of events. Therefore, for continuous monitoring of land change, event recognition needs to replace object identification as the prevailing paradigm. The paper concludes by showing how event semantics can improve data-driven methods to fulfil the potential of big data.
Very recently, Window-based Transformers, which computed self-attention within non-overlapping local windows, demonstrated promising results on image classification, semantic segmentation, and object detection. However, less study has been devoted to the cross-window connection which is the key element to improve the representation ability. In this work, we revisit the spatial shuffle as an efficient way to build connections among windows. As a result, we propose a new vision transformer, named Shuffle Transformer, which is highly efficient and easy to implement by modifying two lines of code. Furthermore, the depth-wise convolution is introduced to complement the spatial shuffle for enhancing neighbor-window connections. The proposed architectures achieve excellent performance on a wide range of visual tasks including image-level classification, object detection, and semantic segmentation. Code will be released for reproduction.
Recent work has shown that convolutional neural network classifiers overly rely on texture at the expense of shape cues. We make a similar but different distinction between shape and local image cues, on the one hand, and global image statistics, on the other. Our method, called Permuted Adaptive Instance Normalization (pAdaIN), reduces the representation of global statistics in the hidden layers of image classifiers. pAdaIN samples a random permutation $\pi$ that rearranges the samples in a given batch. Adaptive Instance Normalization (AdaIN) is then applied between the activations of each (non-permuted) sample $i$ and the corresponding activations of the sample $\pi(i)$, thus swapping statistics between the samples of the batch. Since the global image statistics are distorted, this swapping procedure causes the network to rely on cues, such as shape or texture. By choosing the random permutation with probability $p$ and the identity permutation otherwise, one can control the effect's strength. With the correct choice of $p$, fixed apriori for all experiments and selected without considering test data, our method consistently outperforms baselines in multiple settings. In image classification, our method improves on both CIFAR100 and ImageNet using multiple architectures. In the setting of robustness, our method improves on both ImageNet-C and Cifar-100-C for multiple architectures. In the setting of domain adaptation and domain generalization, our method achieves state of the art results on the transfer learning task from GTAV to Cityscapes and on the PACS benchmark.