Miguel P. Eckstein

Ziqi Wen, Parsa Madinei, Miguel P. Eckstein

Evaluating whether large vision-language models (VLMs) align with human perception for high-level semantic scene comprehension remains a challenge. Traditional white-box interpretability methods are inapplicable to closed-source architectures and passive metrics fail to isolate causal features. We introduce Counterfactual Semantic Saliency (CSS). This black-box, model-agnostic framework quantifies the importance of objects by measuring the semantic shift induced by their causal ablation from a scene. To evaluate AI-human semantic alignment, we tested prominent VLMs against a human psychophysics baseline comprising 16,289 valid responses across 307 complex natural scenes and 1,306 high-fidelity counterfactual variants. Our analysis reveals a pervasive scene comprehension gap: models exhibit an overreliance (relative to humans) on large objects (size bias), objects at the center of the image (center bias), and high saliency objects. In contrast, models rely less on people in the scenes than our human participants to describe the images. A model's size bias is a primary driver explaining variations in model-human semantic divergence. Code and data will be available at https://github.com/starsky77/Counterfactual-Semantic-Saliency.

Shravan Murlidaran, Ziqi Wen, Sana Shehabi et al.

When humans view scenes without a specific task (free-viewing), they initially direct their eye movements toward the scene center and then fixate on people, text, objects being gazed at or grasped, and semantically meaningful regions. What these signature fixation patterns reflect and whether they optimize an underlying perceptual task remain unknown. We show that a computational agent with simulated foveation, trained to optimize scene comprehension, exhibits emergent human fixation signature patterns. In contrast, versions of the agent trained to search or classify scenes, or equipped with peripheral vision that was better or worse than human vision, predicted human fixation patterns less accurately. Thus, human free-viewing fixation patterns may emerge as a functional byproduct of optimizing scene comprehension under the biological constraints of foveated vision.

Parsa Madinei, Srijita Karmakar, Russell Cohen Hoffing et al.

We introduce IRIS (Intent Resolution via Inference-time Saccades), a novel training-free approach that uses eye-tracking data in real-time to resolve ambiguity in open-ended VQA. Through a comprehensive user study with 500 unique image-question pairs, we demonstrate that fixations closest to the time participants start verbally asking their questions are the most informative for disambiguation in Large VLMs, more than doubling the accuracy of responses on ambiguous questions (from 35.2% to 77.2%) while maintaining performance on unambiguous queries. We evaluate our approach across state-of-the-art VLMs, showing consistent improvements when gaze data is incorporated in ambiguous image-question pairs, regardless of architectural differences. We release a new benchmark dataset to use eye movement data for disambiguated VQA, a novel real-time interactive protocol, and an evaluation suite.

Aditya Jonnalagadda, Bruno B. Barufaldi, Andrew D. A. Maidment et al.

Model observers are computational tools to evaluate and optimize task-based medical image quality. Linear model observers, such as the Channelized Hotelling Observer (CHO), predict human accuracy in detection tasks with a few possible signal locations in clinical phantoms or real anatomic backgrounds. In recent years, Convolutional Neural Networks (CNNs) have been proposed as a new type of model observer. What is not well understood is what CNNs add over the more common linear model observer approaches. We compare the CHO and CNN detection accuracy to the radiologist's accuracy in searching for two types of signals (mass and microcalcification) embedded in 2D/3D breast tomosynthesis phantoms (DBT). We show that the CHO model's accuracy is comparable to the CNN's performance for a location-known-exactly detection task. However, for the search task with 2D/3D DBT phantoms, the CHO's detection accuracy was significantly lower than the CNN accuracy. A comparison to the radiologist's accuracy showed that the CNN but not the CHO could match or exceed the radiologist's accuracy in the 2D microcalcification and 3D mass search conditions. An analysis of the eye position showed that radiologists fixated more often and longer at the locations corresponding to CNN false positives. Most CHO false positives were the phantom's normal anatomy and were not fixated by radiologists. In conclusion, we show that CNNs can be used as an anthropomorphic model observer for the search task for which traditional linear model observers fail due to their inability to discount false positives arising from the anatomical backgrounds.

Ziqi Wen, Jonathan Skaza, Shravan Murlidaran et al.

Although models exist that predict human response times (RTs) in tasks such as target search and visual discrimination, the development of image-computable predictors for scene understanding time remains an open challenge. Recent advances in vision-language models (VLMs), which can generate scene descriptions for arbitrary images, combined with the availability of quantitative metrics for comparing linguistic descriptions, offer a new opportunity to model human scene understanding. We hypothesize that the primary bottleneck in human scene understanding and the driving source of variability in response times across scenes is the interaction between the foveated nature of the human visual system and the spatial distribution of task-relevant visual information within an image. Based on this assumption, we propose a novel image-computable model that integrates foveated vision with VLMs to produce a spatially resolved map of scene understanding as a function of fixation location (Foveated Scene Understanding Map, or F-SUM), along with an aggregate F-SUM score. This metric correlates with average (N=17) human RTs (r=0.47) and number of saccades (r=0.51) required to comprehend a scene (across 277 scenes). The F-SUM score also correlates with average (N=16) human description accuracy (r=-0.56) in time-limited presentations. These correlations significantly exceed those of standard image-based metrics such as clutter, visual complexity, and scene ambiguity based on language entropy. Together, our work introduces a new image-computable metric for predicting human response times in scene understanding and demonstrates the importance of foveated visual processing in shaping comprehension difficulty.

Weimin Zhou, Miguel P. Eckstein

Humans process visual information with varying resolution (foveated visual system) and explore images by orienting through eye movements the high-resolution fovea to points of interest. The Bayesian ideal searcher (IS) that employs complete knowledge of task-relevant information optimizes eye movement strategy and achieves the optimal search performance. The IS can be employed as an important tool to evaluate the optimality of human eye movements, and potentially provide guidance to improve human observer visual search strategies. Najemnik and Geisler (2005) derived an IS for backgrounds of spatial 1/f noise. The corresponding template responses follow Gaussian distributions and the optimal search strategy can be analytically determined. However, the computation of the IS can be intractable when considering more realistic and complex backgrounds such as medical images. Modern reinforcement learning methods, successfully applied to obtain optimal policy for a variety of tasks, do not require complete knowledge of the background generating functions and can be potentially applied to anatomical backgrounds. An important first step is to validate the optimality of the reinforcement learning method. In this study, we investigate the ability of a reinforcement learning method that employs Q-network to approximate the IS. We demonstrate that the search strategy corresponding to the Q-network is consistent with the IS search strategy. The findings show the potential of the reinforcement learning with Q-network approach to estimate optimal eye movement planning with real anatomical backgrounds.

Aditya Jonnalagadda, William Yang Wang, B. S. Manjunath et al.

Many animals and humans process the visual field with a varying spatial resolution (foveated vision) and use peripheral processing to make eye movements and point the fovea to acquire high-resolution information about objects of interest. This architecture results in computationally efficient rapid scene exploration. Recent progress in self-attention-based Vision Transformers, an alternative to the traditionally convolution-reliant computer vision systems. However, the Transformer models do not explicitly model the foveated properties of the visual system nor the interaction between eye movements and the classification task. We propose Foveated Transformer (FoveaTer) model, which uses pooling regions and eye movements to perform object classification tasks using a Vision Transformer architecture. Using square pooling regions or biologically-inspired radial-polar pooling regions, our proposed model pools the image features from the convolution backbone and uses the pooled features as an input to transformer layers. It decides on subsequent fixation location based on the attention assigned by the Transformer to various locations from past and present fixations. It dynamically allocates more fixation/computational resources to more challenging images before making the final image category decision. Using five ablation studies, we evaluate the contribution of different components of the Foveated model. We perform a psychophysics scene categorization task and use the experimental data to find a suitable radial-polar pooling region combination. We also show that the Foveated model better explains the human decisions in a scene categorization task than a Baseline model. We demonstrate our model's robustness against PGD adversarial attacks with both types of pooling regions, where we see the Foveated model outperform the Baseline model.

Shravan Murlidaran, William Yang Wang, Miguel P. Eckstein

Recent advances in natural language processing and computer vision have led to AI models that interpret simple scenes at human levels. Yet, we do not have a complete understanding of how humans and AI models differ in their interpretation of more complex scenes. We created a dataset of complex scenes that contained human behaviors and social interactions. AI and humans had to describe the scenes with a sentence. We used a quantitative metric of similarity between scene descriptions of the AI/human and ground truth of five other human descriptions of each scene. Results show that the machine/human agreement scene descriptions are much lower than human/human agreement for our complex scenes. Using an experimental manipulation that occludes different spatial regions of the scenes, we assessed how machines and humans vary in utilizing regions of images to understand the scenes. Together, our results are a first step toward understanding how machines fall short of human visual reasoning with complex scenes depicting human behaviors.

Nicole X. Han, William Yang Wang, Miguel P. Eckstein

Making accurate inferences about other individuals' locus of attention is essential for human social interactions and will be important for AI to effectively interact with humans. In this study, we compare how a CNN (convolutional neural network) based model of gaze and humans infer the locus of attention in images of real-world scenes with a number of individuals looking at a common location. We show that compared to the model, humans' estimates of the locus of attention are more influenced by the context of the scene, such as the presence of the attended target and the number of individuals in the image.

Tsu-Jui Fu, Xin Eric Wang, Scott T. Grafton et al.

Video editing tools are widely used nowadays for digital design. Although the demand for these tools is high, the prior knowledge required makes it difficult for novices to get started. Systems that could follow natural language instructions to perform automatic editing would significantly improve accessibility. This paper introduces the language-based video editing (LBVE) task, which allows the model to edit, guided by text instruction, a source video into a target video. LBVE contains two features: 1) the scenario of the source video is preserved instead of generating a completely different video; 2) the semantic is presented differently in the target video, and all changes are controlled by the given instruction. We propose a Multi-Modal Multi-Level Transformer (M$^3$L) to carry out LBVE. M$^3$L dynamically learns the correspondence between video perception and language semantic at different levels, which benefits both the video understanding and video frame synthesis. We build three new datasets for evaluation, including two diagnostic and one from natural videos with human-labeled text. Extensive experimental results show that M$^3$L is effective for video editing and that LBVE can lead to a new field toward vision-and-language research.

Arturo Deza, Amit Surana, Miguel P. Eckstein

With the advent of modern expert systems driven by deep learning that supplement human experts (e.g. radiologists, dermatologists, surveillance scanners), we analyze how and when do such expert systems enhance human performance in a fine-grained small target visual search task. We set up a 2 session factorial experimental design in which humans visually search for a target with and without a Deep Learning (DL) expert system. We evaluate human changes of target detection performance and eye-movements in the presence of the DL system. We find that performance improvements with the DL system (computed via a Faster R-CNN with a VGG16) interacts with observer's perceptual abilities (e.g., sensitivity). The main results include: 1) The DL system reduces the False Alarm rate per Image on average across observer groups of both high/low sensitivity; 2) Only human observers with high sensitivity perform better than the DL system, while the low sensitivity group does not surpass individual DL system performance, even when aided with the DL system itself; 3) Increases in number of trials and decrease in viewing time were mainly driven by the DL system only for the low sensitivity group. 4) The DL system aids the human observer to fixate at a target by the 3rd fixation. These results provide insights of the benefits and limitations of deep learning systems that are collaborative or competitive with humans.

Arturo Deza, Jeffrey R. Peters, Grant S. Taylor et al.

This paper outlines the development and testing of a novel, feedback-enabled attention allocation aid (AAAD), which uses real-time physiological data to improve human performance in a realistic sequential visual search task. Indeed, by optimizing over search duration, the aid improves efficiency, while preserving decision accuracy, as the operator identifies and classifies targets within simulated aerial imagery. Specifically, using experimental eye-tracking data and measurements about target detectability across the human visual field, we develop functional models of detection accuracy as a function of search time, number of eye movements, scan path, and image clutter. These models are then used by the AAAD in conjunction with real time eye position data to make probabilistic estimations of attained search accuracy and to recommend that the observer either move on to the next image or continue exploring the present image. An experimental evaluation in a scenario motivated from human supervisory control in surveillance missions confirms the benefits of the AAAD.

Arturo Deza, Miguel P. Eckstein

Previous studies have proposed image-based clutter measures that correlate with human search times and/or eye movements. However, most models do not take into account the fact that the effects of clutter interact with the foveated nature of the human visual system: visual clutter further from the fovea has an increasing detrimental influence on perception. Here, we introduce a new foveated clutter model to predict the detrimental effects in target search utilizing a forced fixation search task. We use Feature Congestion (Rosenholtz et al.) as our non foveated clutter model, and we stack a peripheral architecture on top of Feature Congestion for our foveated model. We introduce the Peripheral Integration Feature Congestion (PIFC) coefficient, as a fundamental ingredient of our model that modulates clutter as a non-linear gain contingent on eccentricity. We finally show that Foveated Feature Congestion (FFC) clutter scores r(44) = -0.82 correlate better with target detection (hit rate) than regular Feature Congestion r(44) = -0.19 in forced fixation search. Thus, our model allows us to enrich clutter perception research by computing fixation specific clutter maps. A toolbox for creating peripheral architectures: Piranhas: Peripheral Architectures for Natural, Hybrid and Artificial Systems will be made available.

Emre Akbas, Miguel P. Eckstein

We present a foveated object detector (FOD) as a biologically-inspired alternative to the sliding window (SW) approach which is the dominant method of search in computer vision object detection. Similar to the human visual system, the FOD has higher resolution at the fovea and lower resolution at the visual periphery. Consequently, more computational resources are allocated at the fovea and relatively fewer at the periphery. The FOD processes the entire scene, uses retino-specific object detection classifiers to guide eye movements, aligns its fovea with regions of interest in the input image and integrates observations across multiple fixations. Our approach combines modern object detectors from computer vision with a recent model of peripheral pooling regions found at the V1 layer of the human visual system. We assessed various eye movement strategies on the PASCAL VOC 2007 dataset and show that the FOD performs on par with the SW detector while bringing significant computational cost savings.

Vaibhav Srivastava, Amit Surana, Miguel P. Eckstein et al.

We study the mixed human-robot team design in a system theoretic setting using the context of a surveillance mission. The three key coupled components of a mixed team design are (i) policies for the human operator, (ii) policies to account for erroneous human decisions, and (iii) policies to control the automaton. In this paper, we survey elements of human decision-making, including evidence aggregation, situational awareness, fatigue, and memory effects. We bring together the models for these elements in human decision-making to develop a single coherent model for human decision-making in a two-alternative choice task. We utilize the developed model to design efficient attention allocation policies for the human operator. We propose an anomaly detection algorithm that utilizes potentially erroneous decision by the operator to ascertain an anomalous region among the set of regions surveilled. Finally, we propose a stochastic vehicle routing policy that surveils an anomalous region with high probability. Our mixed team design relies on the certainty-equivalent receding-horizon control framework.