The performance of current Scene Graph Generation models is severely hampered by some hard-to-distinguish predicates, e.g., "woman-on/standing on/walking on-beach" or "woman-near/looking at/in front of-child". While general SGG models are prone to predict head predicates and existing re-balancing strategies prefer tail categories, none of them can appropriately handle these hard-to-distinguish predicates. To tackle this issue, inspired by fine-grained image classification, which focuses on differentiating among hard-to-distinguish object classes, we propose a method named Fine-Grained Predicates Learning (FGPL) which aims at differentiating among hard-to-distinguish predicates for Scene Graph Generation task. Specifically, we first introduce a Predicate Lattice that helps SGG models to figure out fine-grained predicate pairs. Then, utilizing the Predicate Lattice, we propose a Category Discriminating Loss and an Entity Discriminating Loss, which both contribute to distinguishing fine-grained predicates while maintaining learned discriminatory power over recognizable ones. The proposed model-agnostic strategy significantly boosts the performances of three benchmark models (Transformer, VCTree, and Motif) by 22.8\%, 24.1\% and 21.7\% of Mean Recall (mR@100) on the Predicate Classification sub-task, respectively. Our model also outperforms state-of-the-art methods by a large margin (i.e., 6.1\%, 4.6\%, and 3.2\% of Mean Recall (mR@100)) on the Visual Genome dataset.
While local-window self-attention performs notably in vision tasks, it suffers from limited receptive field and weak modeling capability issues. This is mainly because it performs self-attention within non-overlapped windows and shares weights on the channel dimension. We propose MixFormer to find a solution. First, we combine local-window self-attention with depth-wise convolution in a parallel design, modeling cross-window connections to enlarge the receptive fields. Second, we propose bi-directional interactions across branches to provide complementary clues in the channel and spatial dimensions. These two designs are integrated to achieve efficient feature mixing among windows and dimensions. Our MixFormer provides competitive results on image classification with EfficientNet and shows better results than RegNet and Swin Transformer. Performance in downstream tasks outperforms its alternatives by significant margins with less computational costs in 5 dense prediction tasks on MS COCO, ADE20k, and LVIS. Code is available at \url{https://github.com/PaddlePaddle/PaddleClas}.
The new alternative is to use deep learning to inpaint any image by utilizing image classification and computer vision techniques. In general, image inpainting is a task of recreating or reconstructing any broken image which could be a photograph or oil/acrylic painting. With the advancement in the field of Artificial Intelligence, this topic has become popular among AI enthusiasts. With our approach, we propose an initial end-to-end pipeline for inpainting images using a complete Machine Learning approach instead of a conventional application-based approach. We first use the YOLO model to automatically identify and localize the object we wish to remove from the image. Using the result obtained from the model we can generate a mask for the same. After this, we provide the masked image and original image to the GAN model which uses the Contextual Attention method to fill in the region. It consists of two generator networks and two discriminator networks and is also called a coarse-to-fine network structure. The two generators use fully convolutional networks while the global discriminator gets hold of the entire image as input while the local discriminator gets the grip of the filled region as input. The contextual Attention mechanism is proposed to effectively borrow the neighbor information from distant spatial locations for reconstructing the missing pixels. The third part of our implementation uses SRGAN to resolve the inpainted image back to its original size. Our work is inspired by the paper Free-Form Image Inpainting with Gated Convolution and Generative Image Inpainting with Contextual Attention.
India is the second largest producer of fruits and vegetables in the world, and one of the largest consumers of fruits like Banana, Papaya and Mangoes through retail and ecommerce giants like BigBasket, Grofers and Amazon Fresh. However, adoption of technology in supply chain and retail stores is still low and there is a great potential to adopt computer-vision based technology for identification and classification of fruits. We have chosen banana fruit to build a computer vision based model to carry out the following three use-cases (a) Identify Banana from a given image (b) Determine sub-family or variety of Banana (c) Determine the quality of Banana. Successful execution of these use-cases using computer-vision model would greatly help with overall inventory management automation, quality control, quick and efficient weighing and billing which all are manual labor intensive currently. In this work, we suggest a machine learning pipeline that combines the ideas of CNNs, transfer learning, and data augmentation towards improving Banana fruit sub family and quality image classification. We have built a basic CNN and then went on to tune a MobileNet Banana classification model using a combination of self-curated and publicly-available dataset of 3064 images. The results show an overall 93.4% and 100% accuracy for sub-family/variety and for quality test classifications respectively.
Currently available benchmarks for few-shot learning (machine learning with few training examples) are limited in the domains they cover, primarily focusing on image classification. This work aims to alleviate this reliance on image-based benchmarks by offering the first comprehensive, public and fully reproducible audio based alternative, covering a variety of sound domains and experimental settings. We compare the few-shot classification performance of a variety of techniques on seven audio datasets (spanning environmental sounds to human-speech). Extending this, we carry out in-depth analyses of joint training (where all datasets are used during training) and cross-dataset adaptation protocols, establishing the possibility of a generalised audio few-shot classification algorithm. Our experimentation shows gradient-based meta-learning methods such as MAML and Meta-Curvature consistently outperform both metric and baseline methods. We also demonstrate that the joint training routine helps overall generalisation for the environmental sound databases included, as well as being a somewhat-effective method of tackling the cross-dataset/domain setting.
Visual Geo-localization (VG) is the task of estimating the position where a given photo was taken by comparing it with a large database of images of known locations. To investigate how existing techniques would perform on a real-world city-wide VG application, we build San Francisco eXtra Large, a new dataset covering a whole city and providing a wide range of challenging cases, with a size 30x bigger than the previous largest dataset for visual geo-localization. We find that current methods fail to scale to such large datasets, therefore we design a new highly scalable training technique, called CosPlace, which casts the training as a classification problem avoiding the expensive mining needed by the commonly used contrastive learning. We achieve state-of-the-art performance on a wide range of datasets and find that CosPlace is robust to heavy domain changes. Moreover, we show that, compared to the previous state-of-the-art, CosPlace requires roughly 80% less GPU memory at train time, and it achieves better results with 8x smaller descriptors, paving the way for city-wide real-world visual geo-localization. Dataset, code and trained models are available for research purposes at https://github.com/gmberton/CosPlace.
Hyperspectral imaging has attracted significant attention to identify spectral signatures for image classification and automated pattern recognition in computer vision. State-of-the-art implementations of snapshot hyperspectral imaging rely on bulky, non-integrated, and expensive optical elements, including lenses, spectrometers, and filters. These macroscopic components do not allow fast data processing for, e.g real-time and high-resolution videos. This work introduces Hyplex, a new integrated architecture addressing the limitations discussed above. Hyplex is a CMOS-compatible, fast hyperspectral camera that replaces bulk optics with nanoscale metasurfaces inversely designed through artificial intelligence. Hyplex does not require spectrometers but makes use of conventional monochrome cameras, opening up the possibility for real-time and high-resolution hyperspectral imaging at inexpensive costs. Hyplex exploits a model-driven optimization, which connects the physical metasurfaces layer with modern visual computing approaches based on end-to-end training. We design and implement a prototype version of Hyplex and compare its performance against the state-of-the-art for typical imaging tasks such as spectral reconstruction and semantic segmentation. In all benchmarks, Hyplex reports the smallest reconstruction error. We additionally present what is, to the best of our knowledge, the largest publicly available labeled hyperspectral dataset for semantic segmentation.
In autoencoder, the encoder generally approximates the latent distribution over the dataset, and the decoder generates samples using this learned latent distribution. There is very little control over the latent vector as using the random latent vector for generation will lead to trivial outputs. This work tries to address this issue by using the LatentGAN generator to directly learn to approximate the latent distribution of the autoencoder and show meaningful results on MNIST, 3D Chair, and CelebA datasets, an additional information-theoretic constrain is used which successfully learns to control autoencoder latent distribution. With this, our model also achieves an error rate of 2.38 on MNIST unsupervised image classification, which is better as compared to InfoGAN and AAE.
In many real world medical image classification settings we do not have access to samples of all possible disease classes, while a robust system is expected to give high performance in recognizing novel test data. We propose a generalized zero shot learning (GZSL) method that uses self supervised learning (SSL) for: 1) selecting anchor vectors of different disease classes; and 2) training a feature generator. Our approach does not require class attribute vectors which are available for natural images but not for medical images. SSL ensures that the anchor vectors are representative of each class. SSL is also used to generate synthetic features of unseen classes. Using a simpler architecture, our method matches a state of the art SSL based GZSL method for natural images and outperforms all methods for medical images. Our method is adaptable enough to accommodate class attribute vectors when they are available for natural images.
Transformers have recently gained significant attention in the computer vision community. However, the lack of scalability of self-attention mechanisms with respect to image size has limited their wide adoption in state-of-the-art vision backbones. In this paper we introduce an efficient and scalable attention model we call multi-axis attention, which consists of two aspects: blocked local and dilated global attention. These design choices allow global-local spatial interactions on arbitrary input resolutions with only linear complexity. We also present a new architectural element by effectively blending our proposed attention model with convolutions, and accordingly propose a simple hierarchical vision backbone, dubbed MaxViT, by simply repeating the basic building block over multiple stages. Notably, MaxViT is able to ''see'' globally throughout the entire network, even in earlier, high-resolution stages. We demonstrate the effectiveness of our model on a broad spectrum of vision tasks. On image classification, MaxViT achieves state-of-the-art performance under various settings: without extra data, MaxViT attains 86.5% ImageNet-1K top-1 accuracy; with ImageNet-21K pre-training, our model achieves 88.7% top-1 accuracy. For downstream tasks, MaxViT as a backbone delivers favorable performance on object detection as well as visual aesthetic assessment. We also show that our proposed model expresses strong generative modeling capability on ImageNet, demonstrating the superior potential of MaxViT blocks as a universal vision module. The source code and trained models will be available at https://github.com/google-research/maxvit.
Lipschitz constants of neural networks allow for guarantees of robustness in image classification, safety in controller design, and generalizability beyond the training data. As calculating Lipschitz constants is NP-hard, techniques for estimating Lipschitz constants must navigate the trade-off between scalability and accuracy. In this work, we significantly push the scalability frontier of a semidefinite programming technique known as LipSDP while achieving zero accuracy loss. We first show that LipSDP has chordal sparsity, which allows us to derive a chordally sparse formulation that we call Chordal-LipSDP. The key benefit is that the main computational bottleneck of LipSDP, a large semidefinite constraint, is now decomposed into an equivalent collection of smaller ones: allowing Chordal-LipSDP to outperform LipSDP particularly as the network depth grows. Moreover, our formulation uses a tunable sparsity parameter that enables one to gain tighter estimates without incurring a significant computational cost. We illustrate the scalability of our approach through extensive numerical experiments.
We propose a pre-training strategy called Multi-modal Multi-task Masked Autoencoders (MultiMAE). It differs from standard Masked Autoencoding in two key aspects: I) it can optionally accept additional modalities of information in the input besides the RGB image (hence "multi-modal"), and II) its training objective accordingly includes predicting multiple outputs besides the RGB image (hence "multi-task"). We make use of masking (across image patches and input modalities) to make training MultiMAE tractable as well as to ensure cross-modality predictive coding is indeed learned by the network. We show this pre-training strategy leads to a flexible, simple, and efficient framework with improved transfer results to downstream tasks. In particular, the same exact pre-trained network can be flexibly used when additional information besides RGB images is available or when no information other than RGB is available - in all configurations yielding competitive to or significantly better results than the baselines. To avoid needing training datasets with multiple modalities and tasks, we train MultiMAE entirely using pseudo labeling, which makes the framework widely applicable to any RGB dataset. The experiments are performed on multiple transfer tasks (image classification, semantic segmentation, depth estimation) and datasets (ImageNet, ADE20K, Taskonomy, Hypersim, NYUv2). The results show an intriguingly impressive capability by the model in cross-modal/task predictive coding and transfer.
Transferability metrics is a maturing field with increasing interest, which aims at providing heuristics for selecting the most suitable source models to transfer to a given target dataset, without fine-tuning them all. However, existing works rely on custom experimental setups which differ across papers, leading to inconsistent conclusions about which transferability metrics work best. In this paper we conduct a large-scale study by systematically constructing a broad range of 715k experimental setup variations. We discover that even small variations to an experimental setup lead to different conclusions about the superiority of a transferability metric over another. Then we propose better evaluations by aggregating across many experiments, enabling to reach more stable conclusions. As a result, we reveal the superiority of LogME at selecting good source datasets to transfer from in a semantic segmentation scenario, NLEEP at selecting good source architectures in an image classification scenario, and GBC at determining which target task benefits most from a given source model. Yet, no single transferability metric works best in all scenarios.
Attention mechanisms have been very popular in deep neural networks, where the Transformer architecture has achieved great success in not only natural language processing but also visual recognition applications. Recently, a new Transformer module, applying on batch dimension rather than spatial/channel dimension, i.e., BatchFormer [18], has been introduced to explore sample relationships for overcoming data scarcity challenges. However, it only works with image-level representations for classification. In this paper, we devise a more general batch Transformer module, BatchFormerV2, which further enables exploring sample relationships for dense representation learning. Specifically, when applying the proposed module, it employs a two-stream pipeline during training, i.e., either with or without a BatchFormerV2 module, where the batchformer stream can be removed for testing. Therefore, the proposed method is a plug-and-play module and can be easily integrated into different vision Transformers without any extra inference cost. Without bells and whistles, we show the effectiveness of the proposed method for a variety of popular visual recognition tasks, including image classification and two important dense prediction tasks: object detection and panoptic segmentation. Particularly, BatchFormerV2 consistently improves current DETR-based detection methods (e.g., DETR, Deformable-DETR, Conditional DETR, and SMCA) by over 1.3%. Code will be made publicly available.
Unsupervised Domain Adaptation (UDA) essentially trades a model's performance on a source domain for improving its performance on a target domain. To resolve the issue, Unsupervised Domain Expansion (UDE) has been proposed recently. UDE tries to adapt the model for the target domain as UDA does, and in the meantime maintains its source-domain performance. In both UDA and UDE settings, a model tailored to a given domain, let it be the source or the target domain, is assumed to well handle samples from the given domain. We question the assumption by reporting the existence of cross-domain visual ambiguity: Given the lack of a crystally clear boundary between the two domains, samples from one domain can be visually close to the other domain. Such sorts of samples are typically in minority in their host domain, so they tend to be overlooked by the domain-specific model, but can be better handled by a model from the other domain. We exploit this finding, and accordingly propose Co-Teaching (CT). The CT method is instantiated with knowledge distillation based CT (kdCT) plus mixup based CT (miCT). Specifically, kdCT transfers knowledge from a leading-teacher network and an assistant-teacher network to a student network, so the cross-domain ambiguity will be better handled by the student. Meanwhile, miCT further enhances the generalization ability of the student. Extensive experiments on two image classification datasets and two driving-scene segmentation datasets justify the viability of CT for UDA and UDE.
Any-shot image classification allows to recognize novel classes with only a few or even zero samples. For the task of zero-shot learning, visual attributes have been shown to play an important role, while in the few-shot regime, the effect of attributes is under-explored. To better transfer attribute-based knowledge from seen to unseen classes, we argue that an image representation with integrated attribute localization ability would be beneficial for any-shot, i.e. zero-shot and few-shot, image classification tasks. To this end, we propose a novel representation learning framework that jointly learns discriminative global and local features using only class-level attributes. While a visual-semantic embedding layer learns global features, local features are learned through an attribute prototype network that simultaneously regresses and decorrelates attributes from intermediate features. Furthermore, we introduce a zoom-in module that localizes and crops the informative regions to encourage the network to learn informative features explicitly. We show that our locality augmented image representations achieve a new state-of-the-art on challenging benchmarks, i.e. CUB, AWA2, and SUN. As an additional benefit, our model points to the visual evidence of the attributes in an image, confirming the improved attribute localization ability of our image representation. The attribute localization is evaluated quantitatively with ground truth part annotations, qualitatively with visualizations, and through well-designed user studies.
In existing image classification systems that use deep neural networks, the knowledge needed for image classification is implicitly stored in model parameters. If users want to update this knowledge, then they need to fine-tune the model parameters. Moreover, users cannot verify the validity of inference results or evaluate the contribution of knowledge to the results. In this paper, we investigate a system that stores knowledge for image classification, such as image feature maps, labels, and original images, not in model parameters but in external high-capacity storage. Our system refers to the storage like a database when classifying input images. To increase knowledge, our system updates the database instead of fine-tuning model parameters, which avoids catastrophic forgetting in incremental learning scenarios. We revisit a kNN (k-Nearest Neighbor) classifier and employ it in our system. By analyzing the neighborhood samples referred by the kNN algorithm, we can interpret how knowledge learned in the past is used for inference results. Our system achieves 79.8% top-1 accuracy on the ImageNet dataset without fine-tuning model parameters after pretraining, and 90.8% accuracy on the Split CIFAR-100 dataset in the task incremental learning setting.
The transformer models have shown promising effectiveness in dealing with various vision tasks. However, compared with training Convolutional Neural Network (CNN) models, training Vision Transformer (ViT) models is more difficult and relies on the large-scale training set. To explain this observation we make a hypothesis that \textit{ViT models are less effective in capturing the high-frequency components of images than CNN models}, and verify it by a frequency analysis. Inspired by this finding, we first investigate the effects of existing techniques for improving ViT models from a new frequency perspective, and find that the success of some techniques (e.g., RandAugment) can be attributed to the better usage of the high-frequency components. Then, to compensate for this insufficient ability of ViT models, we propose HAT, which directly augments high-frequency components of images via adversarial training. We show that HAT can consistently boost the performance of various ViT models (e.g., +1.2% for ViT-B, +0.5% for Swin-B), and especially enhance the advanced model VOLO-D5 to 87.3% that only uses ImageNet-1K data, and the superiority can also be maintained on out-of-distribution data and transferred to downstream tasks. The code is available at: https://github.com/jiawangbai/HAT.
To improve the classification performance and generalization ability of the hyperspectral image classification algorithm, this paper uses Multi-Scale Total Variation (MSTV) to extract the spectral features, local binary pattern (LBP) to extract spatial features, and feature superposition to obtain the fused features of hyperspectral images. A new swarm intelligence optimization method with high convergence and strong global search capability, the Sparrow Search Algorithm (SSA), is used to optimize the kernel parameters and regularization coefficients of the Kernel Extreme Learning Machine (KELM). In summary, a multiscale fusion feature hyperspectral image classification method (MLS-KELM) is proposed in this paper. The Indian Pines, Pavia University and Houston 2013 datasets were selected to validate the classification performance of MLS-KELM, and the method was applied to ZY1-02D hyperspectral data. The experimental results show that MLS-KELM has better classification performance and generalization ability compared with other popular classification methods, and MLS-KELM shows its strong robustness in the small sample case.
In image classification, it is common practice to train deep networks to extract a single feature vector per input image. Few-shot classification methods also mostly follow this trend. In this work, we depart from this established direction and instead propose to extract sets of feature vectors for each image. We argue that a set-based representation intrinsically builds a richer representation of images from the base classes, which can subsequently better transfer to the few-shot classes. To do so, we propose to adapt existing feature extractors to instead produce sets of feature vectors from images. Our approach, dubbed SetFeat, embeds shallow self-attention mechanisms inside existing encoder architectures. The attention modules are lightweight, and as such our method results in encoders that have approximately the same number of parameters as their original versions. During training and inference, a set-to-set matching metric is used to perform image classification. The effectiveness of our proposed architecture and metrics is demonstrated via thorough experiments on standard few-shot datasets -- namely miniImageNet, tieredImageNet, and CUB -- in both the 1- and 5-shot scenarios. In all cases but one, our method outperforms the state-of-the-art.