Vision-and-Language Navigation (VLN) agents have made remarkable progress, but their robustness remains insufficiently studied. Existing adversarial evaluations often rely on perturbations that manifest as unusual textures rarely encountered in everyday indoor environments. Errors under such contrived conditions have limited practical relevance, as real-world agents are unlikely to encounter such artificial patterns. In this work, we focus on indoor lighting, an intrinsic yet largely overlooked scene attribute that strongly influences navigation. We propose Indoor Lighting-based Adversarial Attack (ILA), a black-box framework that manipulates global illumination to disrupt VLN agents. Motivated by typical household lighting usage, we design two attack modes: Static Indoor Lighting-based Attack (SILA), where the lighting intensity remains constant throughout an episode, and Dynamic Indoor Lighting-based Attack (DILA), where lights are switched on or off at critical moments to induce abrupt illumination changes. We evaluate ILA on two state-of-the-art VLN models across three navigation tasks. Results show that ILA significantly increases failure rates while reducing trajectory efficiency, revealing previously unrecognized vulnerabilities of VLN agents to realistic indoor lighting variations.

In this supplementary material we present more information about the dataset (including a datasheet for the dataset) and extensive results that could not fit in the main paper. In sec. 2 we include a datasheet for our dataset. In sec. 4 we look at the statistics of our two benchmarks CalFire and CaiRoad. The data is publicly available at https://www.cs.cornell.edu/projects/ Our code for accessing Sentinel-2 images, creating change events and baselines can be found at https://github.com/utkarshmall13/ We include a datasheet for our dataset following the methodology from "Datasheets for Datasets" [7]. In this section we include the prompts from [7] in blue and in black are our answers. Was there a specific task in mind? Was there a specific gap that needed to be filled? The dataset was created to foster research on the problem of automatic discovery and semantic understanding of change events in satellite imagery. More specifically, the dataset should aid in developing systems that can automatically detect change events in satellite imagery and assign to each a semantic label that indicates the nature of the event, e.g., forest fires, road construction etc. Who created the dataset (e.g., which team, research group) and on behalf of which entity (e.g., company, institution, organization)? Who funded the creation of the dataset? If there is an associated grant, please provide the name of the grantor and the grant name and number. The dataset contains RGB bands from Sentinel-2 satellite imagery. Users should keep in mind that changes smaller than the resolution be undetectable. For example, changes to roofs of houses, movements of traffic will not be detected. The datasets should be used for larger changes such as forest fire, crop changes etc. 2.2 Composition What do the instances that comprise the dataset represent (e.g., documents, photos, people, countries)? Are there multiple types of instances (e.g., movies, users, and ratings; people and interactions between them; nodes and edges)?

In section 1, we provide five alternatives to the FPN-like structure for fusing the dual-resolution feature maps of the feature backbone. The channels of all feature maps are aligned to 1024 by 1 1 conv layers. As shown in Figure 2, all five types of variants have similar overall performance. Additionally, we also compare type (a) and type (e) with their 256 channel counterparts in Figure 4. We can see that increasing number of channels does not affect the performance of type (e). This further justifies that type (a) is a more proper choice for DualRC-Net. 2 Figure 4: Comparison between 256 and 1024 output feature channels for type (a) and type (e).

In this work, we introduce a deep-learning framework designed for estimating dense image correspondences. Our fully convolutional model generates dense feature maps for images, where each pixel is associated with a descriptor that can be matched across multiple images. Unlike previous methods, our model is trained on synthetic data that includes significant distortions, such as perspective changes, illumination variations, shadows, and specular highlights. Utilizing contrastive learning, our feature maps achieve greater invariance to these distortions, enabling robust matching. Notably, our method eliminates the need for a keypoint detector, setting it apart from many existing image-matching techniques.

Color constancy (CC) describes the ability of the visual system to perceive an object as having a relatively constant color despite changes in lighting conditions. While CC and its limitations have been carefully characterized in humans, it is still unclear how the visual system acquires this ability during development. Here, we present a first study showing that CC develops in a neural network trained in a self-supervised manner through an invariance learning objective. During learning, objects are presented under changing illuminations, while the network aims to map subsequent views of the same object onto close-by latent representations. This gives rise to representations that are largely invariant to the illumination conditions, offering a plausible example of how CC could emerge during human cognitive development via a form of self-supervised learning.

Simultaneous Localization and Mapping (SLAM) is considered an ever-evolving problem due to its usage in many applications. Evaluation of SLAM is done typically using publicly available datasets which are increasing in number and the level of difficulty. Each dataset provides a certain level of dynamic range coverage that is a key aspect of measuring the robustness and resilience of SLAM. In this paper, we provide a systematic analysis of the dynamic range coverage of datasets based on a number of characterization metrics, and our analysis shows a huge level of redundancy within and between datasets. Subsequently, we propose a dynamic programming (DP) algorithm for eliminating the redundancy in the evaluation process of SLAM by selecting a subset of sequences that matches a single or multiple dynamic range coverage objectives. It is shown that, with the help of dataset characterization and DP selection algorithm, a reduction in the evaluation effort can be achieved while maintaining the same level of coverage. We also study how the evaluation process of a real-world SLAM system can be optimized utilizing the method proposed.

We present a general framework for accurate positioning of sensors and end effectors in farm settings using a camera mounted on a robotic manipulator. Our main contribution is a visual servoing approach based on a new and robust feature tracking algorithm. Results from field experiments performed at an apple orchard demonstrate that our approach converges to a given termination criterion even under environmental influences such as strong winds, varying illumination conditions and partial occlusion of the target object. Further, we show experimentally that the system converges to the desired view for a wide range of initial conditions. This approach opens possibilities for new applications such as automated fruit inspection, fruit picking or precise pesticide application.