Noisy labels, inevitably existing in pseudo segmentation labels generated from weak object-level annotations, severely hampers model optimization for semantic segmentation. Previous works often rely on massive hand-crafted losses and carefully-tuned hyper-parameters to resist noise, suffering poor generalization capability and high model complexity. Inspired by recent advances in meta learning, we argue that rather than struggling to tolerate noise hidden behind clean labels passively, a more feasible solution would be to find out the noisy regions actively, so as to simply ignore them during model optimization. With this in mind, this work presents a novel meta learning based semantic segmentation method, MetaSeg, that comprises a primary content-aware meta-net (CAM-Net) to sever as a noise indicator for an arbitrary segmentation model counterpart. Specifically, CAM-Net learns to generate pixel-wise weights to suppress noisy regions with incorrect pseudo labels while highlighting clean ones by exploiting hybrid strengthened features from image content, providing straightforward and reliable guidance for optimizing the segmentation model. Moreover, to break the barrier of time-consuming training when applying meta learning to common large segmentation models, we further present a new decoupled training strategy that optimizes different model layers in a divide-and-conquer manner. Extensive experiments on object, medical, remote sensing and human segmentation shows that our method achieves superior performance, approaching that of fully supervised settings, which paves a new promising way for omni-supervised semantic segmentation.
Referring Image Segmentation (RIS) is a challenging task that requires an algorithm to segment objects referred by free-form language expressions. Despite significant progress in recent years, most state-of-the-art (SOTA) methods still suffer from considerable language-image modality gap at the pixel and word level. These methods generally 1) rely on sentence-level language features for language-image alignment and 2) lack explicit training supervision for fine-grained visual grounding. Consequently, they exhibit weak object-level correspondence between visual and language features. Without well-grounded features, prior methods struggle to understand complex expressions that require strong reasoning over relationships among multiple objects, especially when dealing with rarely used or ambiguous clauses. To tackle this challenge, we introduce a novel Mask Grounding auxiliary task that significantly improves visual grounding within language features, by explicitly teaching the model to learn fine-grained correspondence between masked textual tokens and their matching visual objects. Mask Grounding can be directly used on prior RIS methods and consistently bring improvements. Furthermore, to holistically address the modality gap, we also design a cross-modal alignment loss and an accompanying alignment module. These additions work synergistically with Mask Grounding. With all these techniques, our comprehensive approach culminates in MagNet Mask-grounded Network), an architecture that significantly outperforms prior arts on three key benchmarks (RefCOCO, RefCOCO+ and G-Ref), demonstrating our method's effectiveness in addressing current limitations of RIS algorithms. Our code and pre-trained weights will be released.
The deep unfolding approach has attracted significant attention in computer vision tasks, which well connects conventional image processing modeling manners with more recent deep learning techniques. Specifically, by establishing a direct correspondence between algorithm operators at each implementation step and network modules within each layer, one can rationally construct an almost ``white box'' network architecture with high interpretability. In this architecture, only the predefined component of the proximal operator, known as a proximal network, needs manual configuration, enabling the network to automatically extract intrinsic image priors in a data-driven manner. In current deep unfolding methods, such a proximal network is generally designed as a CNN architecture, whose necessity has been proven by a recent theory. That is, CNN structure substantially delivers the translational invariant image prior, which is the most universally possessed structural prior across various types of images. However, standard CNN-based proximal networks have essential limitations in capturing the rotation symmetry prior, another universal structural prior underlying general images. This leaves a large room for further performance improvement in deep unfolding approaches. To address this issue, this study makes efforts to suggest a high-accuracy rotation equivariant proximal network that effectively embeds rotation symmetry priors into the deep unfolding framework. Especially, we deduce, for the first time, the theoretical equivariant error for such a designed proximal network with arbitrary layers under arbitrary rotation degrees. This analysis should be the most refined theoretical conclusion for such error evaluation to date and is also indispensable for supporting the rationale behind such networks with intrinsic interpretability requirements.
Text-guided diffusion models offer powerful new ways to generate and manipulate images. Several applications of these models, including image editing interpolation, and semantic augmentation, require diffusion inversion. This is the process of finding a noise seed that can be used to generate a given image. Current techniques for inverting a given image can be slow or inaccurate. The technical challenge for inverting the diffusion process arises from an implicit equation over the latent that cannot be solved in closed form. Previous approaches proposed to solve this issue by approximation or various learning schemes. Here, we formulate the problem as a fixed-point equation problem and solve it using fixed-point iterations, a well-studied approach in numerical analysis. We further identify a source of inconsistency that significantly hurts the inversion of real images encoded to the latent space. We show how to correct it by applying a prompt-aware adjustment of the encoding. Our solution, Fixed-point inversion, is much faster than previous techniques like EDICT and Null-text, with similar inversion quality. It can be combined with any pretrained diffusion model and requires no model training, prompt tuning, or additional parameters. In a series of experiments, we find that Fixed-point inversion shows improved results in several downstream tasks: image editing, image interpolation, and generation of rare objects.
Rigorousness and clarity are both essential for interpretations of DNNs to engender human trust. Path methods are commonly employed to generate rigorous attributions that satisfy three axioms. However, the meaning of attributions remains ambiguous due to distinct path choices. To address the ambiguity, we introduce \textbf{Concentration Principle}, which centrally allocates high attributions to indispensable features, thereby endowing aesthetic and sparsity. We then present \textbf{SAMP}, a model-agnostic interpreter, which efficiently searches the near-optimal path from a pre-defined set of manipulation paths. Moreover, we propose the infinitesimal constraint (IC) and momentum strategy (MS) to improve the rigorousness and optimality. Visualizations show that SAMP can precisely reveal DNNs by pinpointing salient image pixels. We also perform quantitative experiments and observe that our method significantly outperforms the counterparts. Code: https://github.com/zbr17/SAMP.
Computational efficiency and adversarial robustness are critical factors in real-world engineering applications. Yet, conventional neural networks often fall short in addressing both simultaneously, or even separately. Drawing insights from natural physical systems and existing literature, it is known that an input convex architecture enhances computational efficiency, while a Lipschitz-constrained architecture bolsters adversarial robustness. By leveraging the strengths of convexity and Lipschitz continuity, we develop a novel network architecture, termed Input Convex Lipschitz Recurrent Neural Networks. This model outperforms existing recurrent units across a spectrum of engineering tasks in terms of computational efficiency and adversarial robustness. These tasks encompass a benchmark MNIST image classification, real-world solar irradiance prediction for Solar PV system planning at LHT Holdings in Singapore, and real-time Model Predictive Control optimization for a chemical reactor.
The deployment of multimodal large language models (MLLMs) has brought forth a unique vulnerability: susceptibility to malicious attacks through visual inputs. We delve into the novel challenge of defending MLLMs against such attacks. We discovered that images act as a "foreign language" that is not considered during alignment, which can make MLLMs prone to producing harmful responses. Unfortunately, unlike the discrete tokens considered in text-based LLMs, the continuous nature of image signals presents significant alignment challenges, which poses difficulty to thoroughly cover the possible scenarios. This vulnerability is exacerbated by the fact that open-source MLLMs are predominantly fine-tuned on limited image-text pairs that is much less than the extensive text-based pretraining corpus, which makes the MLLMs more prone to catastrophic forgetting of their original abilities during explicit alignment tuning. To tackle these challenges, we introduce MLLM-Protector, a plug-and-play strategy combining a lightweight harm detector and a response detoxifier. The harm detector's role is to identify potentially harmful outputs from the MLLM, while the detoxifier corrects these outputs to ensure the response stipulates to the safety standards. This approach effectively mitigates the risks posed by malicious visual inputs without compromising the model's overall performance. Our results demonstrate that MLLM-Protector offers a robust solution to a previously unaddressed aspect of MLLM security.
Segmenting organs in CT scan images is a necessary process for multiple downstream medical image analysis tasks. Currently, manual CT scan segmentation by radiologists is prevalent, especially for organs like the pancreas, which requires a high level of domain expertise for reliable segmentation due to factors like small organ size, occlusion, and varying shapes. When resorting to automated pancreas segmentation, these factors translate to limited reliable labeled data to train effective segmentation models. Consequently, the performance of contemporary pancreas segmentation models is still not within acceptable ranges. To improve that, we propose M3BUNet, a fusion of MobileNet and U-Net neural networks, equipped with a novel Mean-Max (MM) attention that operates in two stages to gradually segment pancreas CT images from coarse to fine with mask guidance for object detection. This approach empowers the network to surpass segmentation performance achieved by similar network architectures and achieve results that are on par with complex state-of-the-art methods, all while maintaining a low parameter count. Additionally, we introduce external contour segmentation as a preprocessing step for the coarse stage to assist in the segmentation process through image standardization. For the fine segmentation stage, we found that applying a wavelet decomposition filter to create multi-input images enhances pancreas segmentation performance. We extensively evaluate our approach on the widely known NIH pancreas dataset and MSD pancreas dataset. Our approach demonstrates a considerable performance improvement, achieving an average Dice Similarity Coefficient (DSC) value of up to 89.53% and an Intersection Over Union (IOU) score of up to 81.16 for the NIH pancreas dataset, and 88.60% DSC and 79.90% IOU for the MSD Pancreas dataset.
Wave runup is a critical factor affecting coastal flooding, shoreline changes, and damage to coastal structures. Climate change is also expected to amplify wave runup's impact on coastal areas. Therefore, fast and accurate wave runup estimation is essential for effective coastal engineering design and management. However, predicting the time-dependent wave runup is challenging due to the intrinsic nonlinearities and non-stationarity of the process, even with the use of the most advanced machine learning techniques. In this study, a physics-informed machine learning-based approach is proposed to efficiently and accurately simulate time-series wave runup. The methodology combines the computational efficiency of the Surfbeat (XBSB) mode with the accuracy of the nonhydrostatic (XBNH) mode of the XBeach model. Specifically, a conditional generative adversarial network (cGAN) is used to map the image representation of wave runup from XBSB to the corresponding image from XBNH. These images are generated by first converting wave runup signals into time-frequency scalograms and then transforming them into image representations. The cGAN model achieves improved performance in image-to-image mapping tasks by incorporating physics-based knowledge from XBSB. After training the model, the high-fidelity XBNH-based scalograms can be predicted, which are then employed to reconstruct the time-series wave runup using the inverse wavelet transform. The simulation results underscore the efficiency and robustness of the proposed model in predicting wave runup, suggesting its potential value for applications in risk assessment and management.
With the rapid progression of deep learning technologies, multi-modality image fusion has become increasingly prevalent in object detection tasks. Despite its popularity, the inherent disparities in how different sources depict scene content make fusion a challenging problem. Current fusion methodologies identify shared characteristics between the two modalities and integrate them within this shared domain using either iterative optimization or deep learning architectures, which often neglect the intricate semantic relationships between modalities, resulting in a superficial understanding of inter-modal connections and, consequently, suboptimal fusion outcomes. To address this, we introduce a text-guided multi-modality image fusion method that leverages the high-level semantics from textual descriptions to integrate semantics from infrared and visible images. This method capitalizes on the complementary characteristics of diverse modalities, bolstering both the accuracy and robustness of object detection. The codebook is utilized to enhance a streamlined and concise depiction of the fused intra- and inter-domain dynamics, fine-tuned for optimal performance in detection tasks. We present a bilevel optimization strategy that establishes a nexus between the joint problem of fusion and detection, optimizing both processes concurrently. Furthermore, we introduce the first dataset of paired infrared and visible images accompanied by text prompts, paving the way for future research. Extensive experiments on several datasets demonstrate that our method not only produces visually superior fusion results but also achieves a higher detection mAP over existing methods, achieving state-of-the-art results.