Convolutional Neural Networks (ConvNets) at present achieve remarkable performance in image classification tasks. However, current ConvNets cannot guarantee the capabilities of the mammalian visual systems such as invariance to contrast and illumination changes. Some ideas to overcome the illumination and contrast variations usually have to be tuned manually and tend to fail when tested with other types of data degradation. In this context, we present a new bio-inspired {entry} layer, M6, which detects low-level geometric features (lines, edges, and orientations) which are similar to patterns detected by the V1 visual cortex. This new trainable layer is capable of coping with image classification even with large contrast variations. The explanation for this behavior is the monogenic signal geometry, which represents each pixel value in a 3D space using quaternions, a fact that confers a degree of explainability to the networks. We compare M6 with a conventional convolutional layer (C) and a deterministic quaternion local phase layer (Q9). The experimental setup {is designed to evaluate the robustness} of our M6 enriched ConvNet model and includes three architectures, four datasets, three types of contrast degradation (including non-uniform haze degradations). The numerical results reveal that the models with M6 are the most robust in front of any kind of contrast variations. This amounts to a significant enhancement of the C models, which usually have reasonably good performance only when the same training and test degradation are used, except for the case of maximum degradation. Moreover, the Structural Similarity Index Measure (SSIM) is used to analyze and explain the robustness effect of the M6 feature maps under any kind of contrast degradations.
In this work, we study over-parameterization as a necessary condition for having the ability for the models to extrapolate outside the convex hull of training set. We specifically, consider classification models, e.g., image classification and other applications of deep learning. Such models are classification functions that partition their domain and assign a class to each partition \cite{strang2019linear}. Partitions are defined by decision boundaries and so is the classification model/function. Convex hull of training set may occupy only a subset of the domain, but trained model may partition the entire domain and not just the convex hull of training set. This is important because many of the testing samples may be outside the convex hull of training set and the way in which a model partitions its domain outside the convex hull would be influential in its generalization. Using approximation theory, we prove that over-parameterization is a necessary condition for having control over the partitioning of the domain outside the convex hull of training set. We also propose a more clear definition for the notion of over-parametrization based on the learning task and the training set at hand. We present empirical evidence about geometry of datasets, both image and non-image, to provide insights about the extent of extrapolation performed by the models. We consider a 64-dimensional feature space learned by a ResNet model and investigate the geometric arrangements of convex hulls and decision boundaries in that space. We also formalize the notion of extrapolation and relate it to the scope of the model. Finally, we review the rich extrapolation literature in pure and applied mathematics, e.g., the Whitney's Extension Problem, and place our theory in that context.
Vision Transformers (ViT) become widely-adopted architectures for various vision tasks. Masked auto-encoding for feature pretraining and multi-scale hybrid convolution-transformer architectures can further unleash the potentials of ViT, leading to state-of-the-art performances on image classification, detection and semantic segmentation. In this paper, our ConvMAE framework demonstrates that multi-scale hybrid convolution-transformer can learn more discriminative representations via the mask auto-encoding scheme. However, directly using the original masking strategy leads to the heavy computational cost and pretraining-finetuning discrepancy. To tackle the issue, we adopt the masked convolution to prevent information leakage in the convolution blocks. A simple block-wise masking strategy is proposed to ensure computational efficiency. We also propose to more directly supervise the multi-scale features of the encoder to boost multi-scale features. Based on our pretrained ConvMAE models, ConvMAE-Base improves ImageNet-1K finetuning accuracy by 1.4% compared with MAE-Base. On object detection, ConvMAE-Base finetuned for only 25 epochs surpasses MAE-Base fined-tuned for 100 epochs by 2.9% box AP and 2.2% mask AP respectively. Code and pretrained models are available at https://github.com/Alpha-VL/ConvMAE.
Intrinsic image decomposition is the classical task of mapping image to albedo. The WHDR dataset allows methods to be evaluated by comparing predictions to human judgements ("lighter", "same as", "darker"). The best modern intrinsic image methods learn a map from image to albedo using rendered models and human judgements. This is convenient for practical methods, but cannot explain how a visual agent without geometric, surface and illumination models and a renderer could learn to recover intrinsic images. This paper describes a method that learns intrinsic image decomposition without seeing WHDR annotations, rendered data, or ground truth data. The method relies on paradigms - fake albedos and fake shading fields - together with a novel smoothing procedure that ensures good behavior at short scales on real images. Long scale error is controlled by averaging. Our method achieves WHDR scores competitive with those of strong recent methods allowed to see training WHDR annotations, rendered data, and ground truth data. Because our method is unsupervised, we can compute estimates of the test/train variance of WHDR scores; these are quite large, and it is unsafe to rely small differences in reported WHDR.
Multi-modal aerial view object classification (MAVOC) in Automatic target recognition (ATR), although an important and challenging problem, has been under studied. This paper firstly finds that fine-grained data, class imbalance and various shooting conditions preclude the representational ability of general image classification. Moreover, the MAVOC dataset has scene aggregation characteristics. By exploiting these properties, we propose Scene Clustering Based Pseudo-labeling Strategy (SCP-Label), a simple yet effective method to employ in post-processing. The SCP-Label brings greater accuracy by assigning the same label to objects within the same scene while also mitigating bias and confusion with model ensembles. Its performance surpasses the official baseline by a large margin of +20.57% Accuracy on Track 1 (SAR), and +31.86% Accuracy on Track 2 (SAR+EO), demonstrating the potential of SCP-Label as post-processing. Finally, we win the championship both on Track1 and Track2 in the CVPR 2022 Perception Beyond the Visible Spectrum (PBVS) Workshop MAVOC Challenge. Our code is available at https://github.com/HowieChangchn/SCP-Label.
Semantic, instance, and panoptic segmentations have been addressed using different and specialized frameworks despite their underlying connections. This paper presents a unified, simple, and effective framework for these essentially similar tasks. The framework, named K-Net, segments both instances and semantic categories consistently by a group of learnable kernels, where each kernel is responsible for generating a mask for either a potential instance or a stuff class. To remedy the difficulties of distinguishing various instances, we propose a kernel update strategy that enables each kernel dynamic and conditional on its meaningful group in the input image. K-Net can be trained in an end-to-end manner with bipartite matching, and its training and inference are naturally NMS-free and box-free. Without bells and whistles, K-Net surpasses all previous state-of-the-art single-model results of panoptic segmentation on MS COCO and semantic segmentation on ADE20K with 52.1% PQ and 54.3% mIoU, respectively. Its instance segmentation performance is also on par with Cascade Mask R-CNNon MS COCO with 60%-90% faster inference speeds. Code and models will be released at https://github.com/open-mmlab/mmdetection.
Hashing images with a perceptual algorithm is a common approach to solving duplicate image detection problems. However, perceptual image hashing algorithms are differentiable, and are thus vulnerable to gradient-based adversarial attacks. We demonstrate that not only is it possible to modify an image to produce an unrelated hash, but an exact image hash collision between a source and target image can be produced via minuscule adversarial perturbations. In a white box setting, these collisions can be replicated across nearly every image pair and hash type (including both deep and non-learned hashes). Furthermore, by attacking points other than the output of a hashing function, an attacker can avoid having to know the details of a particular algorithm, resulting in collisions that transfer across different hash sizes or model architectures. Using these techniques, an adversary can poison the image lookup table of a duplicate image detection service, resulting in undefined or unwanted behavior. Finally, we offer several potential mitigations to gradient-based image hash attacks.
Pansharpening aims to fuse a registered high-resolution panchromatic image (PAN) with a low-resolution hyperspectral image (LR-HSI) to generate an enhanced HSI with high spectral and spatial resolution. Existing pansharpening approaches neglect using an attention mechanism to transfer HR texture features from PAN to LR-HSI features, resulting in spatial and spectral distortions. In this paper, we present a novel attention mechanism for pansharpening called HyperTransformer, in which features of LR-HSI and PAN are formulated as queries and keys in a transformer, respectively. HyperTransformer consists of three main modules, namely two separate feature extractors for PAN and HSI, a multi-head feature soft attention module, and a spatial-spectral feature fusion module. Such a network improves both spatial and spectral quality measures of the pansharpened HSI by learning cross-feature space dependencies and long-range details of PAN and LR-HSI. Furthermore, HyperTransformer can be utilized across multiple spatial scales at the backbone for obtaining improved performance. Extensive experiments conducted on three widely used datasets demonstrate that HyperTransformer achieves significant improvement over the state-of-the-art methods on both spatial and spectral quality measures. Implementation code and pre-trained weights can be accessed at https://github.com/wgcban/HyperTransformer.
Recently, deep convolutional neural networks (CNNs) have been widely explored in single image super-resolution (SISR) and contribute remarkable progress. However, most of the existing CNNs-based SISR methods do not adequately explore contextual information in the feature extraction stage and pay little attention to the final high-resolution (HR) image reconstruction step, hence hindering the desired SR performance. To address the above two issues, in this paper, we propose a two-stage attentive network (TSAN) for accurate SISR in a coarse-to-fine manner. Specifically, we design a novel multi-context attentive block (MCAB) to make the network focus on more informative contextual features. Moreover, we present an essential refined attention block (RAB) which could explore useful cues in HR space for reconstructing fine-detailed HR image. Extensive evaluations on four benchmark datasets demonstrate the efficacy of our proposed TSAN in terms of quantitative metrics and visual effects. Code is available at https://github.com/Jee-King/TSAN.
Image quality assessment (IQA) models aim to establish a quantitative relationship between visual images and their perceptual quality by human observers. IQA modeling plays a special bridging role between vision science and engineering practice, both as a test-bed for vision theories and computational biovision models, and as a powerful tool that could potentially make profound impact on a broad range of image processing, computer vision, and computer graphics applications, for design, optimization, and evaluation purposes. IQA research has enjoyed an accelerated growth in the past two decades. Here we present an overview of IQA methods from a Bayesian perspective, with the goals of unifying a wide spectrum of IQA approaches under a common framework and providing useful references to fundamental concepts accessible to vision scientists and image processing practitioners. We discuss the implications of the successes and limitations of modern IQA methods for biological vision and the prospect for vision science to inform the design of future artificial vision systems.