Personalization techniques for large text-to-image (T2I) models allow users to incorporate new concepts from reference images. However, existing methods primarily rely on textual descriptions, leading to limited control over customized images and failing to support fine-grained and local editing (e.g., shape, pose, and details). In this paper, we identify sketches as an intuitive and versatile representation that can facilitate such control, e.g., contour lines capturing shape information and flow lines representing texture. This motivates us to explore a novel task of sketch concept extraction: given one or more sketch-image pairs, we aim to extract a special sketch concept that bridges the correspondence between the images and sketches, thus enabling sketch-based image synthesis and editing at a fine-grained level. To accomplish this, we introduce CustomSketching, a two-stage framework for extracting novel sketch concepts. Considering that an object can often be depicted by a contour for general shapes and additional strokes for internal details, we introduce a dual-sketch representation to reduce the inherent ambiguity in sketch depiction. We employ a shape loss and a regularization loss to balance fidelity and editability during optimization. Through extensive experiments, a user study, and several applications, we show our method is effective and superior to the adapted baselines.
This paper is a contribution to the "BraTS 2023 Local Synthesis of Healthy Brain Tissue via Inpainting Challenge". The task of this challenge is to transform tumor tissue into healthy tissue in brain magnetic resonance (MR) images. This idea originates from the problem that MR images can be evaluated using automatic processing tools, however, many of these tools are optimized for the analysis of healthy tissue. By solving the given inpainting task, we enable the automatic analysis of images featuring lesions, and further downstream tasks. Our approach builds on denoising diffusion probabilistic models. We use a 2D model that is trained using slices in which healthy tissue was cropped out and is learned to be inpainted again. This allows us to use the ground truth healthy tissue during training. In the sampling stage, we replace the slices containing diseased tissue in the original 3D volume with the slices containing the healthy tissue inpainting. With our approach, we achieve comparable results to the competing methods. On the validation set our model achieves a mean SSIM of 0.7804, a PSNR of 20.3525 and a MSE of 0.0113. In future we plan to extend our 2D model to a 3D model, allowing to inpaint the region of interest as a whole without losing context information of neighboring slices.
Self-Supervised Learning (SSL) has demonstrated promising results in 3D medical image analysis. However, the lack of high-level semantics in pre-training still heavily hinders the performance of downstream tasks. We observe that 3D medical images contain relatively consistent contextual position information, i.e., consistent geometric relations between different organs, which leads to a potential way for us to learn consistent semantic representations in pre-training. In this paper, we propose a simple-yet-effective Volume Contrast (VoCo) framework to leverage the contextual position priors for pre-training. Specifically, we first generate a group of base crops from different regions while enforcing feature discrepancy among them, where we employ them as class assignments of different regions. Then, we randomly crop sub-volumes and predict them belonging to which class (located at which region) by contrasting their similarity to different base crops, which can be seen as predicting contextual positions of different sub-volumes. Through this pretext task, VoCo implicitly encodes the contextual position priors into model representations without the guidance of annotations, enabling us to effectively improve the performance of downstream tasks that require high-level semantics. Extensive experimental results on six downstream tasks demonstrate the superior effectiveness of VoCo. Code will be available at https://github.com/Luffy03/VoCo.
Mobile robots in unknown cluttered environments with irregularly shaped obstacles often face sensing, energy, and communication challenges which directly affect their ability to explore these environments. In this paper, we introduce a novel deep learning method, Confidence-Aware Contrastive Conditional Consistency Model (4CNet), for mobile robot map prediction during resource-limited exploration in multi-robot environments. 4CNet uniquely incorporates: 1) a conditional consistency model for map prediction in irregularly shaped unknown regions, 2) a contrastive map-trajectory pretraining framework for a trajectory encoder that extracts spatial information from the trajectories of nearby robots during map prediction, and 3) a confidence network to measure the uncertainty of map prediction for effective exploration under resource constraints. We incorporate 4CNet within our proposed robot exploration with map prediction architecture, 4CNet-E. We then conduct extensive comparison studies with 4CNet-E and state-of-the-art heuristic and learning methods to investigate both map prediction and exploration performance in environments consisting of uneven terrain and irregularly shaped obstacles. Results showed that 4CNet-E obtained statistically significant higher prediction accuracy and area coverage with varying environment sizes, number of robots, energy budgets, and communication limitations. Real-world mobile robot experiments were performed and validated the feasibility and generalizability of 4CNet-E for mobile robot map prediction and exploration.
Pre-routing timing prediction has been recently studied for evaluating the quality of a candidate cell placement in chip design. It involves directly estimating the timing metrics for both pin-level (slack, slew) and edge-level (net delay, cell delay), without time-consuming routing. However, it often suffers from signal decay and error accumulation due to the long timing paths in large-scale industrial circuits. To address these challenges, we propose a two-stage approach. First, we propose global circuit training to pre-train a graph auto-encoder that learns the global graph embedding from circuit netlist. Second, we use a novel node updating scheme for message passing on GCN, following the topological sorting sequence of the learned graph embedding and circuit graph. This scheme residually models the local time delay between two adjacent pins in the updating sequence, and extracts the lookup table information inside each cell via a new attention mechanism. To handle large-scale circuits efficiently, we introduce an order preserving partition scheme that reduces memory consumption while maintaining the topological dependencies. Experiments on 21 real world circuits achieve a new SOTA R2 of 0.93 for slack prediction, which is significantly surpasses 0.59 by previous SOTA method. Code will be available at: https://github.com/Thinklab-SJTU/EDA-AI.
High-frequency communication systems bring extremely large aperture arrays (ELAA) and large bandwidths, integrating localization and (bi-static) sensing functions without extra infrastructure. Such systems are likely to operate in the near-field (NF), where the performance of localization and sensing is degraded if a simplified far-field channel model is considered. However, when taking advantage of the additional geometry information in the NF, e.g., the encapsulated information in the wavefront, localization and sensing performance can be improved. In this work, we formulate a joint synchronization, localization, and sensing problem in the NF. Considering the array size could be much larger than an obstacle, the effect of partial blockage (i.e., a portion of antennas are blocked) is investigated, and a blockage detection algorithm is proposed. The simulation results show that blockage greatly impacts performance for certain positions, and the proposed blockage detection algorithm can mitigate this impact by identifying the blocked antennas.
Clinical trials require numerous documents to be written -- protocols, consent forms, clinical study reports and others. Large language models (LLMs) offer the potential to rapidly generate first versions of these documents, however there are concerns about the quality of their output Here we report an evaluation of LLMs in generating parts of one such document, clinical trial protocols. We find that an offthe-shelf LLM delivers reasonable results, especially when assessing content relevance and the correct use of terminology. However, deficiencies remain: specifically clinical thinking and logic, and appropriate use of references. To improve performance, we used retrieval-augmented generation (RAG) to prompt an LLM with accurate up-to-date information. As a result of using RAG, the writing quality of the LLM improves substantially, which has implications for the practical useability of LLMs in clinical trial-related writing.
Explanations of AI systems rarely address the information needs of people affected by algorithmic decision-making (ADM). This gap between conveyed information and information that matters to affected stakeholders can impede understanding and adherence to regulatory frameworks such as the AI Act. To address this gap, we present the "XAI Novice Question Bank": A catalog of affected stakeholders' information needs in two ADM use cases (employment prediction and health monitoring), covering the categories data, system context, system usage, and system specifications. Information needs were gathered in an interview study where participants received explanations in response to their inquiries. Participants further reported their understanding and decision confidence, showing that while confidence tended to increase after receiving explanations, participants also met understanding challenges, such as being unable to tell why their understanding felt incomplete. Explanations further influenced participants' perceptions of the systems' risks and benefits, which they confirmed or changed depending on the use case. When risks were perceived as high, participants expressed particular interest in explanations about intention, such as why and to what end a system was put in place. With this work, we aim to support the inclusion of affected stakeholders into explainability by contributing an overview of information and challenges relevant to them when deciding on the adoption of ADM systems. We close by summarizing our findings in a list of six key implications that inform the design of future explanations for affected stakeholder audiences.
Vision transformers have achieved encouraging progress in various computer vision tasks. A common belief is that this is attributed to the competence of self-attention in modeling the global dependencies among feature tokens. Unfortunately, self-attention still faces some challenges in dense prediction tasks, such as the high computational complexity and absence of desirable inductive bias. To address these issues, we revisit the potential benefits of integrating vision transformer with Gabor filter, and propose a Learnable Gabor Filter (LGF) by using convolution. As an alternative to self-attention, we employ LGF to simulate the response of simple cells in the biological visual system to input images, prompting models to focus on discriminative feature representations of targets from various scales and orientations. Additionally, we design a Bionic Focal Vision (BFV) block based on the LGF. This block draws inspiration from neuroscience and introduces a Multi-Path Feed Forward Network (MPFFN) to emulate the working way of biological visual cortex processing information in parallel. Furthermore, we develop a unified and efficient pyramid backbone network family called Focal Vision Transformers (FViTs) by stacking BFV blocks. Experimental results show that FViTs exhibit highly competitive performance in various vision tasks. Especially in terms of computational efficiency and scalability, FViTs show significant advantages compared with other counterparts. Code is available at https://github.com/nkusyl/FViT
Multimedia online platforms (e.g., Amazon, TikTok) have greatly benefited from the incorporation of multimedia (e.g., visual, textual, and acoustic) content into their personal recommender systems. These modalities provide intuitive semantics that facilitate modality-aware user preference modeling. However, two key challenges in multi-modal recommenders remain unresolved: i) The introduction of multi-modal encoders with a large number of additional parameters causes overfitting, given high-dimensional multi-modal features provided by extractors (e.g., ViT, BERT). ii) Side information inevitably introduces inaccuracies and redundancies, which skew the modality-interaction dependency from reflecting true user preference. To tackle these problems, we propose to simplify and empower recommenders through Multi-modal Knowledge Distillation (PromptMM) with the prompt-tuning that enables adaptive quality distillation. Specifically, PromptMM conducts model compression through distilling u-i edge relationship and multi-modal node content from cumbersome teachers to relieve students from the additional feature reduction parameters. To bridge the semantic gap between multi-modal context and collaborative signals for empowering the overfitting teacher, soft prompt-tuning is introduced to perform student task-adaptive. Additionally, to adjust the impact of inaccuracies in multimedia data, a disentangled multi-modal list-wise distillation is developed with modality-aware re-weighting mechanism. Experiments on real-world data demonstrate PromptMM's superiority over existing techniques. Ablation tests confirm the effectiveness of key components. Additional tests show the efficiency and effectiveness.