Semantic segmentation is an extensively studied task in computer vision, with numerous methods proposed every year. Thanks to the advent of deep learning in semantic segmentation, the performance on existing benchmarks is close to saturation. A natural question then arises: Does the superior performance on the closed (and frequently re-used) test sets transfer to the open visual world with unconstrained variations? In this paper, we take steps toward answering the question by exposing failures of existing semantic segmentation methods in the open visual world under the constraint of very limited human labeling effort. Inspired by previous research on model falsification, we start from an arbitrarily large image set, and automatically sample a small image set by MAximizing the Discrepancy (MAD) between two segmentation methods. The selected images have the greatest potential in falsifying either (or both) of the two methods. We also explicitly enforce several conditions to diversify the exposed failures, corresponding to different underlying root causes. A segmentation method, whose failures are more difficult to be exposed in the MAD competition, is considered better. We conduct a thorough MAD diagnosis of ten PASCAL VOC semantic segmentation algorithms. With detailed analysis of experimental results, we point out strengths and weaknesses of the competing algorithms, as well as potential research directions for further advancement in semantic segmentation. The codes are publicly available at \url{https://github.com/QTJiebin/MAD_Segmentation}.
The explosive growth of image data facilitates the fast development of image processing and computer vision methods for emerging visual applications, meanwhile introducing novel distortions to the processed images. This poses a grand challenge to existing blind image quality assessment (BIQA) models, failing to continually adapt to such subpopulation shift. Recent work suggests training BIQA methods on the combination of all available human-rated IQA datasets. However, this type of approach is not scalable to a large number of datasets, and is cumbersome to incorporate a newly created dataset as well. In this paper, we formulate continual learning for BIQA, where a model learns continually from a stream of IQA datasets, building on what was learned from previously seen data. We first identify five desiderata in the new setting with a measure to quantify the plasticity-stability trade-off. We then propose a simple yet effective method for learning BIQA models continually. Specifically, based on a shared backbone network, we add a prediction head for a new dataset, and enforce a regularizer to allow all prediction heads to evolve with new data while being resistant to catastrophic forgetting of old data. We compute the quality score by an adaptive weighted summation of estimates from all prediction heads. Extensive experiments demonstrate the promise of the proposed continual learning method in comparison to standard training techniques for BIQA.
Performance of blind image quality assessment (BIQA) models has been significantly boosted by end-to-end optimization of feature engineering and quality regression. Nevertheless, due to the distributional shifts between images simulated in the laboratory and captured in the wild, models trained on databases with synthetic distortions remain particularly weak at handling realistic distortions (and vice versa). To confront the cross-distortion-scenario challenge, we develop a unified BIQA model and an effective approach of training it for both synthetic and realistic distortions. We first sample pairs of images from the same IQA databases and compute a probability that one image of each pair is of higher quality as the supervisory signal. We then employ the fidelity loss to optimize a deep neural network for BIQA over a large number of such image pairs. We also explicitly enforce a hinge constraint to regularize uncertainty estimation during optimization. Extensive experiments on six IQA databases show the promise of the learned method in blindly assessing image quality in the laboratory and wild. In addition, we demonstrate the universality of the proposed training strategy by using it to improve existing BIQA models.
Omnidirectional images (also referred to as static 360{\deg} panoramas) impose viewing conditions much different from those of regular 2D images. A natural question arises: how do humans perceive image distortions in immersive virtual reality (VR) environments? We argue that, apart from the distorted panorama itself, three types of viewing behavior governed by VR conditions are crucial in determining its perceived quality: starting point, exploration time, and scanpath. In this paper, we propose a principled computational framework for objective quality assessment of 360{\deg} images, which embodies the threefold behavior in a delightful way. Specifically, we first transform an omnidirectional image to several video representations using viewing behavior of different users. We then leverage the recent advances in full-reference 2D image/video quality assessment to compute the perceived quality of the panorama. We construct a set of specific quality measures within the proposed framework, and demonstrate their promises on two VR quality databases.
The performance of objective image quality assessment (IQA) models has been evaluated primarily by comparing model predictions to human judgments. Perceptual datasets (e.g., LIVE and TID2013) gathered for this purpose provide useful benchmarks for improving IQA methods, but their heavy use creates a risk of overfitting. Here, we perform a large-scale comparison of perceptual IQA models in terms of their use as objectives for the optimization of image processing algorithms. Specifically, we evaluate eleven full-reference IQA models by using them as objective functions to train deep neural networks for four low-level vision tasks: denoising, deblurring, super-resolution, and compression. Extensive subjective testing on the optimized images allows us to rank the competing models in terms of their perceptual performance, elucidate their relative advantages and disadvantages for these tasks, and propose a set of desirable properties for incorporation into future IQA models. The implementations are available at https://github.com/dingkeyan93/IQA-optimization.
Objective measures of image quality generally operate by making local comparisons of pixels of a "degraded" image to those of the original. Relative to human observers, these measures are overly sensitive to resampling of texture regions (e.g., replacing one patch of grass with another). Here we develop the first full-reference image quality model with explicit tolerance to texture resampling. Using a convolutional neural network, we construct an injective and differentiable function that transforms images to a multi-scale overcomplete representation. We empirically show that the spatial averages of the feature maps in this representation capture texture appearance, in that they provide a set of sufficient statistical constraints to synthesize a wide variety of texture patterns. We then describe an image quality method that combines correlation of these spatial averages ("texture similarity") with correlation of the feature maps ("structure similarity"). The parameters of the proposed measure are jointly optimized to match human ratings of image quality, while minimizing the reported distances between subimages cropped from the same texture images. Experiments show that the optimized method explains human perceptual scores, both on conventional image quality databases, as well as on texture databases. The measure also offers competitive performance on related tasks such as texture classification and retrieval. Finally, we show that our method is relatively insensitive to geometric transformations (e.g., translation and dilation), without use of any specialized training or data augmentation. Code is available at https://github.com/dingkeyan93/DISTS.
The research in image quality assessment (IQA) has a long history, and significant progress has been made by leveraging recent advances in deep neural networks (DNNs). Despite high correlation numbers on existing IQA datasets, DNN-based models may be easily falsified in the group maximum differentiation (gMAD) competition with strong counterexamples being identified. Here we show that gMAD examples can be used to improve blind IQA (BIQA) methods. Specifically, we first pre-train a DNN-based BIQA model using multiple noisy annotators, and fine-tune it on multiple subject-rated databases of synthetically distorted images, resulting in a top-performing baseline model. We then seek pairs of images by comparing the baseline model with a set of full-reference IQA methods in gMAD. The resulting gMAD examples are most likely to reveal the relative weaknesses of the baseline, and suggest potential ways for refinement. We query ground truth quality annotations for the selected images in a well controlled laboratory environment, and further fine-tune the baseline on the combination of human-rated images from gMAD and existing databases. This process may be iterated, enabling active and progressive fine-tuning from gMAD examples for BIQA. We demonstrate the feasibility of our active learning scheme on a large-scale unlabeled image set, and show that the fine-tuned method achieves improved generalizability in gMAD, without destroying performance on previously trained databases.