We propose a novel prompt tuning method called CoAPT(Context Attribute words in Prompt Tuning) for few/zero-shot image classification. The core motivation is that attributes are descriptive words with rich information about a given concept. Thus, we aim to enrich text queries of existing prompt tuning methods, improving alignment between text and image embeddings in CLIP embedding space. To do so, CoAPT integrates attribute words as additional prompts within learnable prompt tuning and can be easily incorporated into various existing prompt tuning methods. To facilitate the incorporation of attributes into text embeddings and the alignment with image embeddings, soft prompts are trained together with an additional meta-network that generates input-image-wise feature biases from the concatenated feature encodings of the image-text combined queries. Our experiments demonstrate that CoAPT leads to considerable improvements for existing baseline methods on several few/zero-shot image classification tasks, including base-to-novel generalization, cross-dataset transfer, and domain generalization. Our findings highlight the importance of combining hard and soft prompts and pave the way for future research on the interplay between text and image latent spaces in pre-trained models.
Convolutional Neural Networks (CNNs) have reigned for a decade as the de facto approach to automated medical image diagnosis, pushing the state-of-the-art in classification, detection and segmentation tasks. Over the last years, vision transformers (ViTs) have appeared as a competitive alternative to CNNs, yielding impressive levels of performance in the natural image domain, while possessing several interesting properties that could prove beneficial for medical imaging tasks. In this work, we explore the benefits and drawbacks of transformer-based models for medical image classification. We conduct a series of experiments on several standard 2D medical image benchmark datasets and tasks. Our findings show that, while CNNs perform better if trained from scratch, off-the-shelf vision transformers can perform on par with CNNs when pretrained on ImageNet, both in a supervised and self-supervised setting, rendering them as a viable alternative to CNNs.
Contrastive language image pretraining (CLIP) is a standard method for training vision-language models. While CLIP is scalable, promptable, and robust to distribution shifts on image classification tasks, it lacks object localization capabilities. This paper studies the following question: Can we augment CLIP training with task-specific vision models from model zoos to improve its visual representations? Towards this end, we leverage open-source task-specific vision models to generate pseudo-labels for an uncurated and noisy image-text dataset. Subsequently, we train CLIP models on these pseudo-labels in addition to the contrastive training on image and text pairs. This simple setup shows substantial improvements of up to 16.3% across different vision tasks, including segmentation, detection, depth estimation, and surface normal estimation. Importantly, these enhancements are achieved without compromising CLIP's existing capabilities, including its proficiency in promptable zero-shot classification.
Evolutionary computation methods have been successfully applied to neural networks since two decades ago, while those methods cannot scale well to the modern deep neural networks due to the complicated architectures and large quantities of connection weights. In this paper, we propose a new method using genetic algorithms for evolving the architectures and connection weight initialization values of a deep convolutional neural network to address image classification problems. In the proposed algorithm, an efficient variable-length gene encoding strategy is designed to represent the different building blocks and the unpredictable optimal depth in convolutional neural networks. In addition, a new representation scheme is developed for effectively initializing connection weights of deep convolutional neural networks, which is expected to avoid networks getting stuck into local minima which is typically a major issue in the backward gradient-based optimization. Furthermore, a novel fitness evaluation method is proposed to speed up the heuristic search with substantially less computational resource. The proposed algorithm is examined and compared with 22 existing algorithms on nine widely used image classification tasks, including the state-of-the-art methods. The experimental results demonstrate the remarkable superiority of the proposed algorithm over the state-of-the-art algorithms in terms of classification error rate and the number of parameters (weights).
Knowledge distillation (KD) has been actively studied for image classification tasks in deep learning, aiming to improve the performance of a student based on the knowledge from a teacher. However, applying KD in image regression with a scalar response variable has been rarely studied, and there exists no KD method applicable to both classification and regression tasks yet. Moreover, existing KD methods often require a practitioner to carefully select or adjust the teacher and student architectures, making these methods less flexible in practice. To address the above problems in a unified way, we propose a comprehensive KD framework based on cGANs, termed cGAN-KD. Fundamentally different from existing KD methods, cGAN-KD distills and transfers knowledge from a teacher model to a student model via cGAN-generated samples. This novel mechanism makes cGAN-KD suitable for both classification and regression tasks, compatible with other KD methods, and insensitive to the teacher and student architectures. An error bound for a student model trained in the cGAN-KD framework is derived in this work, providing a theory for why cGAN-KD is effective as well as guiding the practical implementation of cGAN-KD. Extensive experiments on CIFAR-100 and ImageNet-100 show that we can combine state of the art KD methods with the cGAN-KD framework to yield a new state of the art. Moreover, experiments on Steering Angle and UTKFace demonstrate the effectiveness of cGAN-KD in image regression tasks, where existing KD methods are inapplicable.
Deep learning for histopathology has been successfully used for disease classification, image segmentation and more. However, combining image and text modalities using current state-of-the-art (SOTA) methods has been a challenge due to the high resolution of histopathology images. Automatic report generation for histopathology images is one such challenge. In this work, we show that using an existing pre-trained Vision Transformer (ViT) to encode 4096x4096 sized patches of the Whole Slide Image (WSI) and a pre-trained Bidirectional Encoder Representations from Transformers (BERT) model for language modeling-based decoder for report generation, we can build a performant and portable report generation mechanism that takes into account the whole high resolution image. Our method allows us to not only generate and evaluate captions that describe the image, but also helps us classify the image into tissue types and the gender of the patient as well. Our best performing model achieves a 89.52% accuracy in Tissue Type classification with a BLEU-4 score of 0.12 in our caption generation task.
The interpretation of deep learning models is a challenge due to their size, complexity, and often opaque internal state. In addition, many systems, such as image classifiers, operate on low-level features rather than high-level concepts. To address these challenges, we introduce Concept Activation Vectors (CAVs), which provide an interpretation of a neural net's internal state in terms of human-friendly concepts. The key idea is to view the high-dimensional internal state of a neural net as an aid, not an obstacle. We show how to use CAVs as part of a technique, Testing with CAVs (TCAV), that uses directional derivatives to quantify the degree to which a user-defined concept is important to a classification result--for example, how sensitive a prediction of "zebra" is to the presence of stripes. Using the domain of image classification as a testing ground, we describe how CAVs may be used to explore hypotheses and generate insights for a standard image classification network as well as a medical application.
Current artificial neural networks are trained with parameters encoded as floating point numbers that occupy lots of memory space at inference time. Due to the increase in the size of deep learning models, it is becoming very difficult to consider training and using artificial neural networks on edge devices. Binary neural networks promise to reduce the size of deep neural network models, as well as to increase inference speed while decreasing energy consumption. Thus, they may allow the deployment of more powerful models on edge devices. However, binary neural networks are still proven to be difficult to train using the backpropagation-based gradient descent scheme. This paper extends the work of \cite{crulis2023alternatives}, which proposed adapting to binary neural networks two promising alternatives to backpropagation originally designed for continuous neural networks, and experimented with them on simple image classification datasets. This paper proposes new experiments on the ImageNette dataset, compares three different model architectures for image classification, and adds two additional alternatives to backpropagation.
When deploying large-scale machine learning models for smart city applications, such as image-based parking lot monitoring, data often must be sent to a central server to perform classification tasks. This is challenging for the city's infrastructure, where image-based applications require transmitting large volumes of data, necessitating complex network and hardware infrastructures to process the data. To address this issue in image-based parking space classification, we propose creating a robust ensemble of classifiers to serve as Teacher models. These Teacher models are distilled into lightweight and specialized Student models that can be deployed directly on edge devices. The knowledge is distilled to the Student models through pseudo-labeled samples generated by the Teacher model, which are utilized to fine-tune the Student models on the target scenario. Our results show that the Student models, with 26 times fewer parameters than the Teacher models, achieved an average accuracy of 96.6% on the target test datasets, surpassing the Teacher models, which attained an average accuracy of 95.3%.
The importance of organizing medical images according to their nature, application and relevance is increasing. Furhermore, a previous selection of medical images can be useful to accelerate the task of analysis by pathologists. Herein this work we propose an image classifier to integrate a CBIR (Content-Based Image Retrieval) selection system. This classifier is based on pattern spectra and neural networks. Feature selection is performed using pattern spectra and principal component analysis, whilst image classification is based on multilayer perceptrons and a composition of self-organizing maps and learning vector quantization. These methods were applied for content selection of immunohistochemical images of placenta and newdeads lungs. Results demonstrated that this approach can reach reasonable classification performance.
The NASA Planetary Data System hosts millions of images acquired from the planet Mars. To help users quickly find images of interest, we have developed and deployed content-based classification and search capabilities for Mars orbital and surface images. The deployed systems are publicly accessible using the PDS Image Atlas. We describe the process of training, evaluating, calibrating, and deploying updates to two CNN classifiers for images collected by Mars missions. We also report on three years of deployment including usage statistics, lessons learned, and plans for the future.
Large diffusion models have become mainstream generative models in both academic studies and industrial AIGC applications. Recently, a number of works further explored how to employ the power of large diffusion models as zero-shot classifiers. While recent zero-shot diffusion-based classifiers have made performance advancement on benchmark datasets, they still suffered badly from extremely slow classification speed (e.g., ~1000 seconds per classifying single image on ImageNet). The extremely slow classification speed strongly prohibits existing zero-shot diffusion-based classifiers from practical applications. In this paper, we propose an embarrassingly simple and efficient zero-shot Gaussian Diffusion Classifiers (GDC) via pretrained text-to-image diffusion models and DINOv2. The proposed GDC can not only significantly surpass previous zero-shot diffusion-based classifiers by over 10 points (61.40% - 71.44%) on ImageNet, but also accelerate more than 30000 times (1000 - 0.03 seconds) classifying a single image on ImageNet. Additionally, it provides probability interpretation of the results. Our extensive experiments further demonstrate that GDC can achieve highly competitive zero-shot classification performance over various datasets and can promisingly self-improve with stronger diffusion models. To the best of our knowledge, the proposed GDC is the first zero-shot diffusionbased classifier that exhibits both competitive accuracy and practical efficiency.
Hyperspectral image classification (HIC) is an active research topic in remote sensing. Hyperspectral images typically generate large data cubes posing big challenges in data acquisition, storage, transmission and processing. To overcome these limitations, this paper develops a novel deep learning HIC approach based on compressive measurements of coded-aperture snapshot spectral imagers (CASSI), without reconstructing the complete hyperspectral data cube. A new kind of deep learning strategy, namely 3D coded convolutional neural network (3D-CCNN) is proposed to efficiently solve for the classification problem, where the hardware-based coded aperture is regarded as a pixel-wise connected network layer. An end-to-end training method is developed to jointly optimize the network parameters and the coded apertures with periodic structures. The accuracy of classification is effectively improved by exploiting the synergy between the deep learning network and coded apertures. The superiority of the proposed method is assessed over the state-of-the-art HIC methods on several hyperspectral datasets.
Microtubule networks (MTs) are a component of a cell that may indicate the presence of various chemical compounds and can be used to recognize properties such as treatment resistance. Therefore, the classification of MT images is of great relevance for cell diagnostics. Human experts find it particularly difficult to recognize the levels of chemical compound exposure of a cell. Improving the accuracy with automated techniques would have a significant impact on cell therapy. In this paper we present the application of Deep Learning to MT image classification and evaluate it on a large MT image dataset of animal cells with three degrees of exposure to a chemical agent. The results demonstrate that the learned deep network performs on par or better at the corresponding cell classification task than human experts. Specifically, we show that the task of recognizing different levels of chemical agent exposure can be handled significantly better by the neural network than by human experts.
We introduce the integrative task of few-shot classification and segmentation (FS-CS) that aims to both classify and segment target objects in a query image when the target classes are given with a few examples. This task combines two conventional few-shot learning problems, few-shot classification and segmentation. FS-CS generalizes them to more realistic episodes with arbitrary image pairs, where each target class may or may not be present in the query. To address the task, we propose the integrative few-shot learning (iFSL) framework for FS-CS, which trains a learner to construct class-wise foreground maps for multi-label classification and pixel-wise segmentation. We also develop an effective iFSL model, attentive squeeze network (ASNet), that leverages deep semantic correlation and global self-attention to produce reliable foreground maps. In experiments, the proposed method shows promising performance on the FS-CS task and also achieves the state of the art on standard few-shot segmentation benchmarks.
Hateful meme detection is a new multimodal task that has gained significant traction in academic and industry research communities. Recently, researchers have applied pre-trained visual-linguistic models to perform the multimodal classification task, and some of these solutions have yielded promising results. However, what these visual-linguistic models learn for the hateful meme classification task remains unclear. For instance, it is unclear if these models are able to capture the derogatory or slurs references in multimodality (i.e., image and text) of the hateful memes. To fill this research gap, this paper propose three research questions to improve our understanding of these visual-linguistic models performing the hateful meme classification task. We found that the image modality contributes more to the hateful meme classification task, and the visual-linguistic models are able to perform visual-text slurs grounding to a certain extent. Our error analysis also shows that the visual-linguistic models have acquired biases, which resulted in false-positive predictions.
Research in the field of malware classification often relies on machine learning models that are trained on high-level features, such as opcodes, function calls, and control flow graphs. Extracting such features is costly, since disassembly or code execution is generally required. In this paper, we conduct experiments to train and evaluate machine learning models for malware classification, based on features that can be obtained without disassembly or execution of code. Specifically, we visualize malware samples as images and employ image analysis techniques. In this context, we focus on two machine learning models, namely, Convolutional Neural Networks (CNN) and Extreme Learning Machines (ELM). Surprisingly, we find that ELMs can achieve accuracies on par with CNNs, yet ELM training requires less than~2\%\ of the time needed to train a comparable CNN.
This paper presents a proof of concept for the usefulness of second-order texture features for the qualitative analysis and classification of chromogenic in-situ hybridization whole slide images in high-throughput imaging experiments. The challenge is that currently, the gold standard for gene expression grading in such images is expert assessment. The idea of the research team is to use different approaches in the analysis of these images that will be used for structural segmentation and functional analysis in gene expression. The article presents such perspective idea to select a number of textural features that are going to be used for classification. In our experiment, natural grouping of image samples (tiles) depending on their local texture properties was explored in an unsupervised classification procedure. The features are reduced to two dimensions with fuzzy c-means clustering. The overall conclusion of this experiment is that Haralick features are a viable choice for classification and analysis of chromogenic in-situ hybridization image data. The principal component analysis approach produced slightly more "understandable" from an annotator's point of view classes.
Most medical image lesion segmentation methods rely on hand-crafted accurate annotations of the original image for supervised learning. Recently, a series of weakly supervised or unsupervised methods have been proposed to reduce the dependence on pixel-level annotations. However, these methods are essentially based on pixel-level annotation, ignoring the image-level diagnostic results of the current massive medical images. In this paper, we propose a dual U-shaped two-stage framework that utilizes image-level labels to prompt the segmentation. In the first stage, we pre-train a classification network with image-level labels, which is used to obtain the hierarchical pyramid features and guide the learning of downstream branches. In the second stage, we feed the hierarchical features obtained from the classification branch into the downstream branch through short-skip and long-skip and get the lesion masks under the supervised learning of pixel-level labels. Experiments show that our framework achieves better results than networks simply using pixel-level annotations.
We provide a large image parameter dataset extracted from the Solar Dynamics Observatory (SDO) mission's AIA instrument, for the period of January 2011 through the current date, with the cadence of six minutes, for nine wavelength channels. The volume of the dataset for each year is just short of 1 TiB. Towards achieving better results in the region classification of active regions and coronal holes, we improve upon the performance of a set of ten image parameters, through an in depth evaluation of various assumptions that are necessary for calculation of these image parameters. Then, where possible, a method for finding an appropriate settings for the parameter calculations was devised, as well as a validation task to show our improved results. In addition, we include comparisons of JP2 and FITS image formats using supervised classification models, by tuning the parameters specific to the format of the images from which they are extracted, and specific to each wavelength. The results of these comparisons show that utilizing JP2 images, which are significantly smaller files, is not detrimental to the region classification task that these parameters were originally intended for. Finally, we compute the tuned parameters on the AIA images and provide a public API (http://dmlab.cs.gsu.edu/dmlabapi) to access the dataset. This dataset can be used in a range of studies on AIA images, such as content-based image retrieval or tracking of solar events, where dimensionality reduction on the images is necessary for feasibility of the tasks.