Search

Ordinal regression is a fundamental problem within the field of computer vision, with customised well-trained models on specific tasks. While pre-trained vision-language models (VLMs) have exhibited impressive performance on various vision tasks, their potential for ordinal regression has received less exploration. In this study, we first investigate CLIP's potential for ordinal regression, from which we expect the model could generalise to different ordinal regression tasks and scenarios. Unfortunately, vanilla CLIP fails on this task, since current VLMs have a well-documented limitation of encapsulating compositional concepts such as number sense. We propose a simple yet effective method called NumCLIP to improve the quantitative understanding of VLMs. We disassemble the exact image to number-specific text matching problem into coarse classification and fine prediction stages. We discretize and phrase each numerical bin with common language concept to better leverage the available pre-trained alignment in CLIP. To consider the inherent continuous property of ordinal regression, we propose a novel fine-grained cross-modal ranking-based regularisation loss specifically designed to keep both semantic and ordinal alignment in CLIP's feature space. Experimental results on three general ordinal regression tasks demonstrate the effectiveness of NumCLIP, with 10% and 3.83% accuracy improvement on historical image dating and image aesthetics assessment task, respectively. Code is publicly available at https://github.com/xmed-lab/NumCLIP., Comment: Accepted by ECCV 2024

Detecting objects seamlessly blended into their surroundings represents a complex task for both human cognitive capabilities and advanced artificial intelligence algorithms. Currently, the majority of methodologies for detecting camouflaged objects mainly focus on utilizing discriminative models with various unique designs. However, it has been observed that generative models, such as Stable Diffusion, possess stronger capabilities for understanding various objects in complex environments; Yet their potential for the cognition and detection of camouflaged objects has not been extensively explored. In this study, we present a novel denoising diffusion model, namely FocusDiffuser, to investigate how generative models can enhance the detection and interpretation of camouflaged objects. We believe that the secret to spotting camouflaged objects lies in catching the subtle nuances in details. Consequently, our FocusDiffuser innovatively integrates specialized enhancements, notably the Boundary-Driven LookUp (BDLU) module and Cyclic Positioning (CP) module, to elevate standard diffusion models, significantly boosting the detail-oriented analytical capabilities. Our experiments demonstrate that FocusDiffuser, from a generative perspective, effectively addresses the challenge of camouflaged object detection, surpassing leading models on benchmarks like CAMO, COD10K and NC4K., Comment: 18 pages,7figures

Confining glassy polymer into films can substantially modify their local and film-averaged properties. We present a lattice model of film geometry with void-mediated facilitation behaviors but free from any elasticity effect. We analyze the spatially varying viscosity to delineate the transport property of glassy films. The film mobility measurements reported by [Yang et. al., Science, 2010, 328, 1676] are successfully reproduced. The flow exhibits a crossover from simple viscous flow to a surface-dominated regime as temperature decreases. The propagation of a highly mobile front induced by the free surface is visualized in real space. Our approach provides a microscopic treatment of the observed glassy phenomena.

Glass formers are in general classified as strong or fragile depending on whether their relaxation rates follow Arrhenius or super-Arrhenius temperature dependence. There are however notable exceptions such as water, which exhibit a fragile-to-strong (FTS) transition and behave as fragile and strong respectively at high and low temperatures. In this work, the FTS transition is studied using a distinguishable-particle lattice model previously demonstrated to be capable of simulating both strong and fragile glasses [Phys. Rev. Lett. 125, 265703 (2020)]. Starting with a bimodal pair-interaction distribution appropriate for fragile glasses, we show that by narrowing down the energy dispersion in the low-energy component of the distribution, a FTS transition is observed. The transition occurs at a temperature at which the stretching exponent of the relaxation is minimized, in agreement with previous molecular dynamics simulations.

Geolocation is a fundamental component of route planning and navigation for unmanned vehicles, but GNSS-based geolocation fails under denial-of-service conditions. Cross-view geo-localization (CVGL), which aims to estimate the geographical location of the ground-level camera by matching against enormous geo-tagged aerial (\emph{e.g.}, satellite) images, has received lots of attention but remains extremely challenging due to the drastic appearance differences across aerial-ground views. In existing methods, global representations of different views are extracted primarily using Siamese-like architectures, but their interactive benefits are seldom taken into account. In this paper, we present a novel approach using cross-view knowledge generative techniques in combination with transformers, namely mutual generative transformer learning (MGTL), for CVGL. Specifically, by taking the initial representations produced by the backbone network, MGTL develops two separate generative sub-modules -- one for aerial-aware knowledge generation from ground-view semantics and vice versa -- and fully exploits the entirely mutual benefits through the attention mechanism. Moreover, to better capture the co-visual relationships between aerial and ground views, we introduce a cascaded attention masking algorithm to further boost accuracy. Extensive experiments on challenging public benchmarks, \emph{i.e.}, {CVACT} and {CVUSA}, demonstrate the effectiveness of the proposed method which sets new records compared with the existing state-of-the-art models., Comment: 21pages

Automatically detecting/segmenting object(s) that blend in with their surroundings is difficult for current models. A major challenge is that the intrinsic similarities between such foreground objects and background surroundings make the features extracted by deep model indistinguishable. To overcome this challenge, an ideal model should be able to seek valuable, extra clues from the given scene and incorporate them into a joint learning framework for representation co-enhancement. With this inspiration, we design a novel Mutual Graph Learning (MGL) model, which generalizes the idea of conventional mutual learning from regular grids to the graph domain. Specifically, MGL decouples an image into two task-specific feature maps -- one for roughly locating the target and the other for accurately capturing its boundary details -- and fully exploits the mutual benefits by recurrently reasoning their high-order relations through graphs. Importantly, in contrast to most mutual learning approaches that use a shared function to model all between-task interactions, MGL is equipped with typed functions for handling different complementary relations to maximize information interactions. Experiments on challenging datasets, including CHAMELEON, CAMO and COD10K, demonstrate the effectiveness of our MGL with superior performance to existing state-of-the-art methods.

We study the field cooled magnetization of a CuMn spin glass under temperature perturbations. The $T$-cycling curves are compared with the reference curve without temperature cycling. There is a crossover from the cumulative aging region to noncumulative aging region as the temperature change is increased. The cumulative aging range scales with the chaos length $\ell_\mathrm{c}$, becoming comparable to the correlation length, $\xi$, at the crossover boundary. The extracted chaos exponent, $\zeta = 1.1$, is in agreement with theoretical predictions. Our results strongly suggest temperature chaos exists in real spin glasses system.

With the maturity of Artificial Intelligence (AI) technology, Large Scale Visual Geo-Localization (LSVGL) is increasingly important in urban computing, where the task is to accurately and efficiently recognize the geo-location of a given query image. The main challenge of LSVGL faced by many experiments due to the appearance of real-word places may differ in various ways. While perspective deviation almost inevitably exists between training images and query images because of the arbitrary perspective. To cope with this situation, in this paper, we in-depth analyze the limitation of triplet loss which is the most commonly used metric learning loss in state-of-the-art LSVGL framework, and propose a new QUInTuplet Loss (QUITLoss) by embedding all the potential positive samples to the primitive triplet loss. Extensive experiments have been conducted to verify the effectiveness of the proposed approach and the results demonstrate that our new loss can enhance various LSVGL methods.