Human perception and understanding is a major domain of computer vision which, like many other vision subdomains recently, stands to gain from the use of large models pre-trained on large datasets. We hypothesize that the most common pre-training strategy of relying on general purpose, object-centric image datasets such as ImageNet, is limited by an important domain shift. On the other hand, collecting domain specific ground truth such as 2D or 3D labels does not scale well. Therefore, we propose a pre-training approach based on self-supervised learning that works on human-centric data using only images. Our method uses pairs of images of humans: the first is partially masked and the model is trained to reconstruct the masked parts given the visible ones and a second image. It relies on both stereoscopic (cross-view) pairs, and temporal (cross-pose) pairs taken from videos, in order to learn priors about 3D as well as human motion. We pre-train a model for body-centric tasks and one for hand-centric tasks. With a generic transformer architecture, these models outperform existing self-supervised pre-training methods on a wide set of human-centric downstream tasks, and obtain state-of-the-art performance for instance when fine-tuning for model-based and model-free human mesh recovery.
We present USLR, a computational framework for longitudinal registration of brain MRI scans to estimate nonlinear image trajectories that are smooth across time, unbiased to any timepoint, and robust to imaging artefacts. It operates on the Lie algebra parameterisation of spatial transforms (which is compatible with rigid transforms and stationary velocity fields for nonlinear deformation) and takes advantage of log-domain properties to solve the problem using Bayesian inference. USRL estimates rigid and nonlinear registrations that: (i) bring all timepoints to an unbiased subject-specific space; and (i) compute a smooth trajectory across the imaging time-series. We capitalise on learning-based registration algorithms and closed-form expressions for fast inference. A use-case Alzheimer's disease study is used to showcase the benefits of the pipeline in multiple fronts, such as time-consistent image segmentation to reduce intra-subject variability, subject-specific prediction or population analysis using tensor-based morphometry. We demonstrate that such approach improves upon cross-sectional methods in identifying group differences, which can be helpful in detecting more subtle atrophy levels or in reducing sample sizes in clinical trials. The code is publicly available in https://github.com/acasamitjana/uslr
We present a novel diffusion-based approach to generate synthetic histopathological Whole Slide Images (WSIs) at an unprecedented gigapixel scale. Synthetic WSIs have many potential applications: They can augment training datasets to enhance the performance of many computational pathology applications. They allow the creation of synthesized copies of datasets that can be shared without violating privacy regulations. Or they can facilitate learning representations of WSIs without requiring data annotations. Despite this variety of applications, no existing deep-learning-based method generates WSIs at their typically high resolutions. Mainly due to the high computational complexity. Therefore, we propose a novel coarse-to-fine sampling scheme to tackle image generation of high-resolution WSIs. In this scheme, we increase the resolution of an initial low-resolution image to a high-resolution WSI. Particularly, a diffusion model sequentially adds fine details to images and increases their resolution. In our experiments, we train our method with WSIs from the TCGA-BRCA dataset. Additionally to quantitative evaluations, we also performed a user study with pathologists. The study results suggest that our generated WSIs resemble the structure of real WSIs.
Large multimodal models (LMMs) suffer from multimodal hallucination, where they provide incorrect responses misaligned with the given visual information. Recent works have conjectured that one of the reasons behind multimodal hallucination might be due to the vision encoder failing to ground on the image properly. To mitigate this issue, we propose a novel approach that leverages self-feedback as visual cues. Building on this approach, we introduce Volcano, a multimodal self-feedback guided revision model. Volcano generates natural language feedback to its initial response based on the provided visual information and utilizes this feedback to self-revise its initial response. Volcano effectively reduces multimodal hallucination and achieves state-of-the-art on MMHal-Bench, POPE, and GAVIE. It also improves on general multimodal abilities and outperforms previous models on MM-Vet and MMBench. Through a qualitative analysis, we show that Volcano's feedback is properly grounded on the image than the initial response. This indicates that Volcano can provide itself with richer visual information, helping alleviate multimodal hallucination. We publicly release Volcano models of 7B and 13B sizes along with the data and code at https://github.com/kaistAI/Volcano.
Large language models (LLMs) are fine-tuned using human comparison data with Reinforcement Learning from Human Feedback (RLHF) methods to make them better aligned with users' preferences. In contrast to LLMs, human preference learning has not been widely explored in text-to-image diffusion models; the best existing approach is to fine-tune a pretrained model using carefully curated high quality images and captions to improve visual appeal and text alignment. We propose Diffusion-DPO, a method to align diffusion models to human preferences by directly optimizing on human comparison data. Diffusion-DPO is adapted from the recently developed Direct Preference Optimization (DPO), a simpler alternative to RLHF which directly optimizes a policy that best satisfies human preferences under a classification objective. We re-formulate DPO to account for a diffusion model notion of likelihood, utilizing the evidence lower bound to derive a differentiable objective. Using the Pick-a-Pic dataset of 851K crowdsourced pairwise preferences, we fine-tune the base model of the state-of-the-art Stable Diffusion XL (SDXL)-1.0 model with Diffusion-DPO. Our fine-tuned base model significantly outperforms both base SDXL-1.0 and the larger SDXL-1.0 model consisting of an additional refinement model in human evaluation, improving visual appeal and prompt alignment. We also develop a variant that uses AI feedback and has comparable performance to training on human preferences, opening the door for scaling of diffusion model alignment methods.
We present SOccDPT, a memory-efficient approach for 3D semantic occupancy prediction from monocular image input using dense prediction transformers. To address the limitations of existing methods trained on structured traffic datasets, we train our model on unstructured datasets including the Indian Driving Dataset and Bengaluru Driving Dataset. Our semi-supervised training pipeline allows SOccDPT to learn from datasets with limited labels by reducing the requirement for manual labelling by substituting it with pseudo-ground truth labels to produce our Bengaluru Semantic Occupancy Dataset. This broader training enhances our model's ability to handle unstructured traffic scenarios effectively. To overcome memory limitations during training, we introduce patch-wise training where we select a subset of parameters to train each epoch, reducing memory usage during auto-grad graph construction. In the context of unstructured traffic and memory-constrained training and inference, SOccDPT outperforms existing disparity estimation approaches as shown by the RMSE score of 9.1473, achieves a semantic segmentation IoU score of 46.02% and operates at a competitive frequency of 69.47 Hz. We make our code and semantic occupancy dataset public.
Accelerating compute intensive non-real-time beam-forming algorithms in ultrasound imaging using deep learning architectures has been gaining momentum in the recent past. Nonetheless, the complexity of the state-of-the-art deep learning techniques poses challenges for deployment on resource-constrained edge devices. In this work, we propose a novel vision transformer based tiny beamformer (Tiny-VBF), which works on the raw radio-frequency channel data acquired through single-angle plane wave insonification. The output of our Tiny-VBF provides fast envelope detection requiring very low frame rate, i.e. 0.34 GOPs/Frame for a frame size of 368 x 128 in comparison to the state-of-the-art deep learning models. It also exhibited an 8% increase in contrast and gains of 5% and 33% in axial and lateral resolution respectively when compared to Tiny-CNN on in-vitro dataset. Additionally, our model showed a 4.2% increase in contrast and gains of 4% and 20% in axial and lateral resolution respectively when compared against conventional Delay-and-Sum (DAS) beamformer. We further propose an accelerator architecture and implement our Tiny-VBF model on a Zynq UltraScale+ MPSoC ZCU104 FPGA using a hybrid quantization scheme with 50% less resource consumption compared to the floating-point implementation, while preserving the image quality.
Applying NeRF to downstream perception tasks for scene understanding and representation is becoming increasingly popular. Most existing methods treat semantic prediction as an additional rendering task, \textit{i.e.}, the "label rendering" task, to build semantic NeRFs. However, by rendering semantic/instance labels per pixel without considering the contextual information of the rendered image, these methods usually suffer from unclear boundary segmentation and abnormal segmentation of pixels within an object. To solve this problem, we propose Generalized Perception NeRF (GP-NeRF), a novel pipeline that makes the widely used segmentation model and NeRF work compatibly under a unified framework, for facilitating context-aware 3D scene perception. To accomplish this goal, we introduce transformers to aggregate radiance as well as semantic embedding fields jointly for novel views and facilitate the joint volumetric rendering of both fields. In addition, we propose two self-distillation mechanisms, i.e., the Semantic Distill Loss and the Depth-Guided Semantic Distill Loss, to enhance the discrimination and quality of the semantic field and the maintenance of geometric consistency. In evaluation, we conduct experimental comparisons under two perception tasks (\textit{i.e.} semantic and instance segmentation) using both synthetic and real-world datasets. Notably, our method outperforms SOTA approaches by 6.94\%, 11.76\%, and 8.47\% on generalized semantic segmentation, finetuning semantic segmentation, and instance segmentation, respectively.
The recent surge in the research of diffusion models has accelerated the adoption of text-to-image models in various Artificial Intelligence Generated Content (AIGC) commercial products. While these exceptional AIGC products are gaining increasing recognition and sparking enthusiasm among consumers, the questions regarding whether, when, and how these models might unintentionally reinforce existing societal stereotypes remain largely unaddressed. Motivated by recent advancements in language agents, here we introduce a novel agent architecture tailored for stereotype detection in text-to-image models. This versatile agent architecture is capable of accommodating free-form detection tasks and can autonomously invoke various tools to facilitate the entire process, from generating corresponding instructions and images, to detecting stereotypes. We build the stereotype-relevant benchmark based on multiple open-text datasets, and apply this architecture to commercial products and popular open source text-to-image models. We find that these models often display serious stereotypes when it comes to certain prompts about personal characteristics, social cultural context and crime-related aspects. In summary, these empirical findings underscore the pervasive existence of stereotypes across social dimensions, including gender, race, and religion, which not only validate the effectiveness of our proposed approach, but also emphasize the critical necessity of addressing potential ethical risks in the burgeoning realm of AIGC. As AIGC continues its rapid expansion trajectory, with new models and plugins emerging daily in staggering numbers, the challenge lies in the timely detection and mitigation of potential biases within these models.
Spatial audio and 3-Dimensional sound rendering techniques play a pivotal and essential role in immersive audio experiences. Head-Related Transfer Functions (HRTFs) are acoustic filters which represent how sound interacts with an individual's unique head and ears anatomy. The use of HRTFs compliant to the subjects anatomical traits is crucial to ensure a personalized and unique spatial experience. This work proposes the implementation of an HRTF individualization method based on anthropometric features automatically extracted from ear images using a Convolutional Neural Network (CNN). Firstly, a CNN is implemented and tested to assess the performance of machine learning on positioning landmarks on ear images. The I-BUG dataset, containing ear images with corresponding 55 landmarks, was used to train and test the neural network. Subsequently, 12 relevant landmarks were selected to correspond to 7 specific anthropometric measurements established by the HUTUBS database. These landmarks serve as a reference for distance computation in pixels in order to retrieve the anthropometric measurements from the ear images. Once the 7 distances in pixels are extracted from the ear image, they are converted in centimetres using conversion factors, a best match method vector is implemented computing the Euclidean distance for each set in a database of 116 ears with their corresponding 7 anthropometric measurements provided by the HUTUBS database. The closest match of anthropometry can be identified and the corresponding set of HRTFs can be obtained for personnalized use. The method is evaluated in its validity instead of the accuracy of the results. The conceptual scope of each stage has been verified and substantiated to function correctly. The various steps and the available elements in the process are reviewed and challenged to define a greater algorithm entity designed for the desired task.