arXiv subjects

Hanspeter Pfister

Publications and source records attributed to Hanspeter Pfister.

At least 73 records · Page 4Linked to original sources

arXiv2024

The time is ripe to reverse engineer an entire nervous system: simulating behavior from neural interactions

Just like electrical engineers understand how microprocessors execute programs in terms of how transistor currents are affected by their inputs, neuroscientists want to understand behavior production in terms of how neuronal outputs are affected by their inputs and internal states. This dependency of neuronal outputs on inputs can be described by a state-dependent input-output (IO)-function. However, to reliably identify these IO-functions, we need to perturb each input and combinations of inputs while observing all the outputs. Here, we argue that such completeness is possible in C. elegans; a complete description that goes all the way from the activity of every neuron to predict behavior. The established and growing toolkit of optophysiology can non-invasively capture and control every neuron's activity and scale to countless experiments. The information from many such experiments can be pooled while capturing the inter-individual variability because neuronal identity and function are largely conserved across individuals. Just like electrical engineers use transistor IO-functions to simulate program execution, we argue that neuronal IO-functions could be used to simulate the impressive breadth of brain states and behaviors of C. elegans.

q-bio.NC↗

arXiv2024

MoRA: LoRA Guided Multi-Modal Disease Diagnosis with Missing Modality

Multi-modal pre-trained models efficiently extract and fuse features from different modalities with low memory requirements for fine-tuning. Despite this efficiency, their application in disease diagnosis is under-explored. A significant challenge is the frequent occurrence of missing modalities, which impairs performance. Additionally, fine-tuning the entire pre-trained model demands substantial computational resources. To address these issues, we introduce Modality-aware Low-Rank Adaptation (MoRA), a computationally efficient method. MoRA projects each input to a low intrinsic dimension but uses different modality-aware up-projections for modality-specific adaptation in cases of missing modalities. Practically, MoRA integrates into the first block of the model, significantly improving performance when a modality is missing. It requires minimal computational resources, with less than 1.6% of the trainable parameters needed compared to training the entire model. Experimental results show that MoRA outperforms existing techniques in disease diagnosis, demonstrating superior performance, robustness, and training efficiency.

cs.CV↗

arXiv2024

TriSAM: Tri-Plane SAM for zero-shot cortical blood vessel segmentation in VEM images

While imaging techniques at macro and mesoscales have garnered substantial attention and resources, microscale Volume Electron Microscopy (vEM) imaging, capable of revealing intricate vascular details, has lacked the necessary benchmarking infrastructure. In this paper, we address a significant gap in this field of neuroimaging by introducing the first-in-class public benchmark, BvEM, designed specifically for cortical blood vessel segmentation in vEM images. Our BvEM benchmark is based on vEM image volumes from three mammals: adult mouse, macaque, and human. We standardized the resolution, addressed imaging variations, and meticulously annotated blood vessels through semi-automatic, manual, and quality control processes, ensuring high-quality 3D segmentation. Furthermore, we developed a zero-shot cortical blood vessel segmentation method named TriSAM, which leverages the powerful segmentation model SAM for 3D segmentation. To extend SAM from 2D to 3D volume segmentation, TriSAM employs a multi-seed tracking framework, leveraging the reliability of certain image planes for tracking while using others to identify potential turning points. This approach effectively achieves long-term 3D blood vessel segmentation without model training or fine-tuning. Experimental results show that TriSAM achieved superior performances on the BvEM benchmark across three species. Our dataset, code, and model are available online at \url{https://jia-wan.github.io/bvem}.

cs.CV↗

arXiv2024

Sportify: Question Answering with Embedded Visualizations and Personified Narratives for Sports Video

As basketball's popularity surges, fans often find themselves confused and overwhelmed by the rapid game pace and complexity. Basketball tactics, involving a complex series of actions, require substantial knowledge to be fully understood. This complexity leads to a need for additional information and explanation, which can distract fans from the game. To tackle these challenges, we present Sportify, a Visual Question Answering system that integrates narratives and embedded visualization for demystifying basketball tactical questions, aiding fans in understanding various game aspects. We propose three novel action visualizations (i.e., Pass, Cut, and Screen) to demonstrate critical action sequences. To explain the reasoning and logic behind players' actions, we leverage a large-language model (LLM) to generate narratives. We adopt a storytelling approach for complex scenarios from both first and third-person perspectives, integrating action visualizations. We evaluated Sportify with basketball fans to investigate its impact on understanding of tactics, and how different personal perspectives of narratives impact the understanding of complex tactic with action visualizations. Our evaluation with basketball fans demonstrates Sportify's capability to deepen tactical insights and amplify the viewing experience. Furthermore, third-person narration assists people in getting in-depth game explanations while first-person narration enhances fans' game engagement

cs.HC↗

arXiv2024

Measuring and Controlling Instruction (In)Stability in Language Model Dialogs

System-prompting is a standard tool for customizing language-model chatbots, enabling them to follow a specific instruction. An implicit assumption in the use of system prompts is that they will be stable, so the chatbot will continue to generate text according to the stipulated instructions for the duration of a conversation. We propose a quantitative benchmark to test this assumption, evaluating instruction stability via self-chats between two instructed chatbots. Testing popular models like LLaMA2-chat-70B and GPT-3.5, we reveal a significant instruction drift within eight rounds of conversations. An empirical and theoretical analysis of this phenomenon suggests the transformer attention mechanism plays a role, due to attention decay over long exchanges. To combat attention decay and instruction drift, we propose a lightweight method called split-softmax, which compares favorably against two strong baselines.

cs.CL↗

arXiv2024

$R^2$-Tuning: Efficient Image-to-Video Transfer Learning for Video Temporal Grounding

Video temporal grounding (VTG) is a fine-grained video understanding problem that aims to ground relevant clips in untrimmed videos given natural language queries. Most existing VTG models are built upon frame-wise final-layer CLIP features, aided by additional temporal backbones (e.g., SlowFast) with sophisticated temporal reasoning mechanisms. In this work, we claim that CLIP itself already shows great potential for fine-grained spatial-temporal modeling, as each layer offers distinct yet useful information under different granularity levels. Motivated by this, we propose Reversed Recurrent Tuning ($R^2$-Tuning), a parameter- and memory-efficient transfer learning framework for video temporal grounding. Our method learns a lightweight $R^2$ Block containing only 1.5% of the total parameters to perform progressive spatial-temporal modeling. Starting from the last layer of CLIP, $R^2$ Block recurrently aggregates spatial features from earlier layers, then refines temporal correlation conditioning on the given query, resulting in a coarse-to-fine scheme. $R^2$-Tuning achieves state-of-the-art performance across three VTG tasks (i.e., moment retrieval, highlight detection, and video summarization) on six public benchmarks (i.e., QVHighlights, Charades-STA, Ego4D-NLQ, TACoS, YouTube Highlights, and TVSum) even without the additional backbone, demonstrating the significance and effectiveness of the proposed scheme. Our code is available at https://github.com/yeliudev/R2-Tuning.

cs.CV↗

arXiv2024

Aligning Sight and Sound: Advanced Sound Source Localization Through Audio-Visual Alignment

Recent studies on learning-based sound source localization have mainly focused on the localization performance perspective. However, prior work and existing benchmarks overlook a crucial aspect: cross-modal interaction, which is essential for interactive sound source localization. Cross-modal interaction is vital for understanding semantically matched or mismatched audio-visual events, such as silent objects or off-screen sounds. In this paper, we first comprehensively examine the cross-modal interaction of existing methods, benchmarks, evaluation metrics, and cross-modal understanding tasks. Then, we identify the limitations of previous studies and make several contributions to overcome the limitations. First, we introduce a new synthetic benchmark for interactive sound source localization. Second, we introduce new evaluation metrics to rigorously assess sound source localization methods, focusing on accurately evaluating both localization performance and cross-modal interaction ability. Third, we propose a learning framework with a cross-modal alignment strategy to enhance cross-modal interaction. Lastly, we evaluate both interactive sound source localization and auxiliary cross-modal retrieval tasks together to thoroughly assess cross-modal interaction capabilities and benchmark competing methods. Our new benchmarks and evaluation metrics reveal previously overlooked issues in sound source localization studies. Our proposed novel method, with enhanced cross-modal alignment, shows superior sound source localization performance. This work provides the most comprehensive analysis of sound source localization to date, with extensive validation of competing methods on both existing and new benchmarks using new and standard evaluation metrics.

cs.MM↗

arXiv2024

Lite2Relight: 3D-aware Single Image Portrait Relighting

Achieving photorealistic 3D view synthesis and relighting of human portraits is pivotal for advancing AR/VR applications. Existing methodologies in portrait relighting demonstrate substantial limitations in terms of generalization and 3D consistency, coupled with inaccuracies in physically realistic lighting and identity preservation. Furthermore, personalization from a single view is difficult to achieve and often requires multiview images during the testing phase or involves slow optimization processes. This paper introduces Lite2Relight, a novel technique that can predict 3D consistent head poses of portraits while performing physically plausible light editing at interactive speed. Our method uniquely extends the generative capabilities and efficient volumetric representation of EG3D, leveraging a lightstage dataset to implicitly disentangle face reflectance and perform relighting under target HDRI environment maps. By utilizing a pre-trained geometry-aware encoder and a feature alignment module, we map input images into a relightable 3D space, enhancing them with a strong face geometry and reflectance prior. Through extensive quantitative and qualitative evaluations, we show that our method outperforms the state-of-the-art methods in terms of efficacy, photorealism, and practical application. This includes producing 3D-consistent results of the full head, including hair, eyes, and expressions. Lite2Relight paves the way for large-scale adoption of photorealistic portrait editing in various domains, offering a robust, interactive solution to a previously constrained problem. Project page: https://vcai.mpi-inf.mpg.de/projects/Lite2Relight/

cs.CV↗

arXiv2024

Emergent World Representations: Exploring a Sequence Model Trained on a Synthetic Task

Language models show a surprising range of capabilities, but the source of their apparent competence is unclear. Do these networks just memorize a collection of surface statistics, or do they rely on internal representations of the process that generates the sequences they see? We investigate this question by applying a variant of the GPT model to the task of predicting legal moves in a simple board game, Othello. Although the network has no a priori knowledge of the game or its rules, we uncover evidence of an emergent nonlinear internal representation of the board state. Interventional experiments indicate this representation can be used to control the output of the network and create "latent saliency maps" that can help explain predictions in human terms.

cs.LG↗

arXiv2024

Inference-Time Intervention: Eliciting Truthful Answers from a Language Model

We introduce Inference-Time Intervention (ITI), a technique designed to enhance the "truthfulness" of large language models (LLMs). ITI operates by shifting model activations during inference, following a set of directions across a limited number of attention heads. This intervention significantly improves the performance of LLaMA models on the TruthfulQA benchmark. On an instruction-finetuned LLaMA called Alpaca, ITI improves its truthfulness from 32.5% to 65.1%. We identify a tradeoff between truthfulness and helpfulness and demonstrate how to balance it by tuning the intervention strength. ITI is minimally invasive and computationally inexpensive. Moreover, the technique is data efficient: while approaches like RLHF require extensive annotations, ITI locates truthful directions using only few hundred examples. Our findings suggest that LLMs may have an internal representation of the likelihood of something being true, even as they produce falsehoods on the surface.

cs.LG↗

arXiv2024

They're All Doctors: Synthesizing Diverse Counterfactuals to Mitigate Associative Bias

Vision Language Models (VLMs) such as CLIP are powerful models; however they can exhibit unwanted biases, making them less safe when deployed directly in applications such as text-to-image, text-to-video retrievals, reverse search, or classification tasks. In this work, we propose a novel framework to generate synthetic counterfactual images to create a diverse and balanced dataset that can be used to fine-tune CLIP. Given a set of diverse synthetic base images from text-to-image models, we leverage off-the-shelf segmentation and inpainting models to place humans with diverse visual appearances in context. We show that CLIP trained on such datasets learns to disentangle the human appearance from the context of an image, i.e., what makes a doctor is not correlated to the person's visual appearance, like skin color or body type, but to the context, such as background, the attire they are wearing, or the objects they are holding. We demonstrate that our fine-tuned CLIP model, $CF_α$, improves key fairness metrics such as MaxSkew, MinSkew, and NDKL by 40-66\% for image retrieval tasks, while still achieving similar levels of performance in downstream tasks. We show that, by design, our model retains maximal compatibility with the original CLIP models, and can be easily controlled to support different accuracy versus fairness trade-offs in a plug-n-play fashion.

cs.CV↗

arXiv2024

Benchmarking Out-of-Distribution Generalization Capabilities of DNN-based Encoding Models for the Ventral Visual Cortex

We characterized the generalization capabilities of DNN-based encoding models when predicting neuronal responses from the visual cortex. We collected \textit{MacaqueITBench}, a large-scale dataset of neural population responses from the macaque inferior temporal (IT) cortex to over $300,000$ images, comprising $8,233$ unique natural images presented to seven monkeys over $109$ sessions. Using \textit{MacaqueITBench}, we investigated the impact of distribution shifts on models predicting neural activity by dividing the images into Out-Of-Distribution (OOD) train and test splits. The OOD splits included several different image-computable types including image contrast, hue, intensity, temperature, and saturation. Compared to the performance on in-distribution test images -- the conventional way these models have been evaluated -- models performed worse at predicting neuronal responses to out-of-distribution images, retaining as little as $20\%$ of the performance on in-distribution test images. The generalization performance under OOD shifts can be well accounted by a simple image similarity metric -- the cosine distance between image representations extracted from a pre-trained object recognition model is a strong predictor of neural predictivity under different distribution shifts. The dataset of images, neuronal firing rate recordings, and computational benchmarks are hosted publicly at: https://bit.ly/3zeutVd.

eess.SP↗

arXiv2024

Learning Gaze-aware Compositional GAN

Gaze-annotated facial data is crucial for training deep neural networks (DNNs) for gaze estimation. However, obtaining these data is labor-intensive and requires specialized equipment due to the challenge of accurately annotating the gaze direction of a subject. In this work, we present a generative framework to create annotated gaze data by leveraging the benefits of labeled and unlabeled data sources. We propose a Gaze-aware Compositional GAN that learns to generate annotated facial images from a limited labeled dataset. Then we transfer this model to an unlabeled data domain to take advantage of the diversity it provides. Experiments demonstrate our approach's effectiveness in generating within-domain image augmentations in the ETH-XGaze dataset and cross-domain augmentations in the CelebAMask-HQ dataset domain for gaze estimation DNN training. We also show additional applications of our work, which include facial image editing and gaze redirection.

cs.CV↗

arXiv2024

FDive: Learning Relevance Models using Pattern-based Similarity Measures

The detection of interesting patterns in large high-dimensional datasets is difficult because of their dimensionality and pattern complexity. Therefore, analysts require automated support for the extraction of relevant patterns. In this paper, we present FDive, a visual active learning system that helps to create visually explorable relevance models, assisted by learning a pattern-based similarity. We use a small set of user-provided labels to rank similarity measures, consisting of feature descriptor and distance function combinations, by their ability to distinguish relevant from irrelevant data. Based on the best-ranked similarity measure, the system calculates an interactive Self-Organizing Map-based relevance model, which classifies data according to the cluster affiliation. It also automatically prompts further relevance feedback to improve its accuracy. Uncertain areas, especially near the decision boundaries, are highlighted and can be refined by the user. We evaluate our approach by comparison to state-of-the-art feature selection techniques and demonstrate the usefulness of our approach by a case study classifying electron microscopy images of brain cells. The results show that FDive enhances both the quality and understanding of relevance models and can thus lead to new insights for brain research.

cs.LG↗

arXiv2024

Beyond Generating Code: Evaluating GPT on a Data Visualization Course

This paper presents an empirical evaluation of the performance of the Generative Pre-trained Transformer (GPT) model in Harvard's CS171 data visualization course. While previous studies have focused on GPT's ability to generate code for visualizations, this study goes beyond code generation to evaluate GPT's abilities in various visualization tasks, such as data interpretation, visualization design, visual data exploration, and insight communication. The evaluation utilized GPT-3.5 and GPT-4 to complete assignments of CS171, and included a quantitative assessment based on the established course rubrics, a qualitative analysis informed by the feedback of three experienced graders, and an exploratory study of GPT's capabilities in completing border visualization tasks. Findings show that GPT-4 scored 80% on quizzes and homework, and TFs could distinguish between GPT- and human-generated homework with 70% accuracy. The study also demonstrates GPT's potential in completing various visualization tasks, such as data cleanup, interaction with visualizations, and insight communication. The paper concludes by discussing the strengths and limitations of GPT in data visualization, potential avenues for incorporating GPT in broader visualization tasks, and the need to redesign visualization education.

cs.HC↗

arXiv2024

Sporthesia: Augmenting Sports Videos Using Natural Language

Augmented sports videos, which combine visualizations and video effects to present data in actual scenes, can communicate insights engagingly and thus have been increasingly popular for sports enthusiasts around the world. Yet, creating augmented sports videos remains a challenging task, requiring considerable time and video editing skills. On the other hand, sports insights are often communicated using natural language, such as in commentaries, oral presentations, and articles, but usually lack visual cues. Thus, this work aims to facilitate the creation of augmented sports videos by enabling analysts to directly create visualizations embedded in videos using insights expressed in natural language. To achieve this goal, we propose a three-step approach - 1) detecting visualizable entities in the text, 2) mapping these entities into visualizations, and 3) scheduling these visualizations to play with the video - and analyzed 155 sports video clips and the accompanying commentaries for accomplishing these steps. Informed by our analysis, we have designed and implemented Sporthesia, a proof-of-concept system that takes racket-based sports videos and textual commentaries as the input and outputs augmented videos. We demonstrate Sporthesia's applicability in two exemplar scenarios, i.e., authoring augmented sports videos using text and augmenting historical sports videos based on auditory comments. A technical evaluation shows that Sporthesia achieves high accuracy (F1-score of 0.9) in detecting visualizable entities in the text. An expert evaluation with eight sports analysts suggests high utility, effectiveness, and satisfaction with our language-driven authoring method and provides insights for future improvement and opportunities.

cs.HC↗

arXiv2024

RL-LABEL: A Deep Reinforcement Learning Approach Intended for AR Label Placement in Dynamic Scenarios

Labels are widely used in augmented reality (AR) to display digital information. Ensuring the readability of AR labels requires placing them occlusion-free while keeping visual linkings legible, especially when multiple labels exist in the scene. Although existing optimization-based methods, such as force-based methods, are effective in managing AR labels in static scenarios, they often struggle in dynamic scenarios with constantly moving objects. This is due to their focus on generating layouts optimal for the current moment, neglecting future moments and leading to sub-optimal or unstable layouts over time. In this work, we present RL-LABEL, a deep reinforcement learning-based method for managing the placement of AR labels in scenarios involving moving objects. RL-LABEL considers the current and predicted future states of objects and labels, such as positions and velocities, as well as the user's viewpoint, to make informed decisions about label placement. It balances the trade-offs between immediate and long-term objectives. Our experiments on two real-world datasets show that RL-LABEL effectively learns the decision-making process for long-term optimization, outperforming two baselines (i.e., no view management and a force-based method) by minimizing label occlusions, line intersections, and label movement distance. Additionally, a user study involving 18 participants indicates that RL-LABEL excels over the baselines in aiding users to identify, compare, and summarize data on AR labels within dynamic scenes.

cs.HC↗

arXiv2024

iBall: Augmenting Basketball Videos with Gaze-moderated Embedded Visualizations

We present iBall, a basketball video-watching system that leverages gaze-moderated embedded visualizations to facilitate game understanding and engagement of casual fans. Video broadcasting and online video platforms make watching basketball games increasingly accessible. Yet, for new or casual fans, watching basketball videos is often confusing due to their limited basketball knowledge and the lack of accessible, on-demand information to resolve their confusion. To assist casual fans in watching basketball videos, we compared the game-watching behaviors of casual and die-hard fans in a formative study and developed iBall based on the fndings. iBall embeds visualizations into basketball videos using a computer vision pipeline, and automatically adapts the visualizations based on the game context and users' gaze, helping casual fans appreciate basketball games without being overwhelmed. We confrmed the usefulness, usability, and engagement of iBall in a study with 16 casual fans, and further collected feedback from 8 die-hard fans.

cs.HC↗