Investigating the Robustness and Properties of Detection Transformers (DETR) Toward Difficult Images
Transformer-based object detectors (DETR) have shown significant performance across machine vision tasks, ultimately in object detection. This detector is based on a self-attention mechanism along with the transformer encoder-decoder architecture to capture the global context in the image. The critical issue to be addressed is how this model architecture can handle different image nuisances, such as occlusion and adversarial perturbations. We studied this issue by measuring the performance of DETR with different experiments and benchmarking the network with convolutional neural network (CNN) based detectors like YOLO and Faster-RCNN. We found that DETR performs well when it comes to resistance to interference from information loss in occlusion images. Despite that, we found that the adversarial stickers put on the image require the network to produce a new unnecessary set of keys, queries, and values, which in most cases, results in a misdirection of the network. DETR also performed poorer than YOLOv5 in the image corruption benchmark. Furthermore, we found that DETR depends heavily on the main query when making a prediction, which leads to imbalanced contributions between queries since the main query receives most of the gradient flow.
相關內容
Multimodal large language models (MLLMs) have shown remarkable capabilities across a broad range of tasks but their knowledge and abilities in the geographic and geospatial domains are yet to be explored, despite potential wide-ranging benefits to navigation, environmental research, urban development, and disaster response. We conduct a series of experiments exploring various vision capabilities of MLLMs within these domains, particularly focusing on the frontier model GPT-4V, and benchmark its performance against open-source counterparts. Our methodology involves challenging these models with a small-scale geographic benchmark consisting of a suite of visual tasks, testing their abilities across a spectrum of complexity. The analysis uncovers not only where such models excel, including instances where they outperform humans, but also where they falter, providing a balanced view of their capabilities in the geographic domain. To enable the comparison and evaluation of future models, our benchmark will be publicly released.
Large language and vision models have transformed how social movements scholars identify protest and extract key protest attributes from multi-modal data such as texts, images, and videos. This article documents how we fine-tuned two large pretrained transformer models, including longformer and swin-transformer v2, to infer potential protests in news articles using textual and imagery data. First, the longformer model was fine-tuned using the Dynamic of Collective Action (DoCA) Corpus. We matched the New York Times articles with the DoCA database to obtain a training dataset for downstream tasks. Second, the swin-transformer v2 models was trained on UCLA-protest imagery data. UCLA-protest project contains labeled imagery data with information such as protest, violence, and sign. Both fine-tuned models will be available via \url{//github.com/Joshzyj/llvms4protest}. We release this short technical report for social movement scholars who are interested in using LLVMs to infer protests in textual and imagery data.
Unlabeled 3D objects present an opportunity to leverage pretrained vision language models (VLMs) on a range of annotation tasks -- from describing object semantics to physical properties. An accurate response must take into account the full appearance of the object in 3D, various ways of phrasing the question/prompt, and changes in other factors that affect the response. We present a method to marginalize over any factors varied across VLM queries, utilizing the VLM's scores for sampled responses. We first show that this probabilistic aggregation can outperform a language model (e.g., GPT4) for summarization, for instance avoiding hallucinations when there are contrasting details between responses. Secondly, we show that aggregated annotations are useful for prompt-chaining; they help improve downstream VLM predictions (e.g., of object material when the object's type is specified as an auxiliary input in the prompt). Such auxiliary inputs allow ablating and measuring the contribution of visual reasoning over language-only reasoning. Using these evaluations, we show how VLMs can approach, without additional training or in-context learning, the quality of human-verified type and material annotations on the large-scale Objaverse dataset.
Text-To-Image (TTI) models, such as DALL-E and StableDiffusion, have demonstrated remarkable prompt-based image generation capabilities. Multilingual encoders may have a substantial impact on the cultural agency of these models, as language is a conduit of culture. In this study, we explore the cultural perception embedded in TTI models by characterizing culture across three hierarchical tiers: cultural dimensions, cultural domains, and cultural concepts. Based on this ontology, we derive prompt templates to unlock the cultural knowledge in TTI models, and propose a comprehensive suite of evaluation techniques, including intrinsic evaluations using the CLIP space, extrinsic evaluations with a Visual-Question-Answer (VQA) model and human assessments, to evaluate the cultural content of TTI-generated images. To bolster our research, we introduce the CulText2I dataset, derived from four diverse TTI models and spanning ten languages. Our experiments provide insights regarding Do, What, Which and How research questions about the nature of cultural encoding in TTI models, paving the way for cross-cultural applications of these models.
The task of deepfakes detection is far from being solved by speech or vision researchers. Several publicly available databases of fake synthetic video and speech were built to aid the development of detection methods. However, existing databases typically focus on visual or voice modalities and provide no proof that their deepfakes can in fact impersonate any real person. In this paper, we present the first realistic audio-visual database of deepfakes SWAN-DF, where lips and speech are well synchronized and video have high visual and audio qualities. We took the publicly available SWAN dataset of real videos with different identities to create audio-visual deepfakes using several models from DeepFaceLab and blending techniques for face swapping and HiFiVC, DiffVC, YourTTS, and FreeVC models for voice conversion. From the publicly available speech dataset LibriTTS, we also created a separate database of only audio deepfakes LibriTTS-DF using several latest text to speech methods: YourTTS, Adaspeech, and TorToiSe. We demonstrate the vulnerability of a state of the art speaker recognition system, such as ECAPA-TDNN-based model from SpeechBrain, to the synthetic voices. Similarly, we tested face recognition system based on the MobileFaceNet architecture to several variants of our visual deepfakes. The vulnerability assessment show that by tuning the existing pretrained deepfake models to specific identities, one can successfully spoof the face and speaker recognition systems in more than 90% of the time and achieve a very realistic looking and sounding fake video of a given person.
Recent advances in imaging and high-performance computing have made it possible to image the entire human brain at the cellular level. This is the basis to study the multi-scale architecture of the brain regarding its subdivision into brain areas and nuclei, cortical layers, columns, and cell clusters down to single cell morphology Methods for brain mapping and cell segmentation exploit such images to enable rapid and automated analysis of cytoarchitecture and cell distribution in complete series of histological sections. However, the presence of inevitable processing artifacts in the image data caused by missing sections, tears in the tissue, or staining variations remains the primary reason for gaps in the resulting image data. To this end we aim to provide a model that can fill in missing information in a reliable way, following the true cell distribution at different scales. Inspired by the recent success in image generation, we propose a denoising diffusion probabilistic model (DDPM), trained on light-microscopic scans of cell-body stained sections. We extend this model with the RePaint method to impute missing or replace corrupted image data. We show that our trained DDPM is able to generate highly realistic image information for this purpose, generating plausible cell statistics and cytoarchitectonic patterns. We validate its outputs using two established downstream task models trained on the same data.
Although frequency range 2 (FR2) systems are an essential part of 5G-Advanced and future 3GPP releases, the mobility performance of multi-panel user equipment (MPUE) with hand blockage is still an area open for research and standardization. In this article, a comprehensive study on the mobility performance of MPUE with hand blockage is performed for conditional handover (CHO) and its potential enhancement denoted by fast conditional handover (FCHO). In contrast to CHO, in FCHO the MPUE can reuse earlier target cell preparations after each handover to autonomously execute subsequent handovers. This saves both the signaling overhead associated with the reconfiguration and re-preparation of target cells after each handover and reduces mobility failures. Results have shown that FCHO offers considerable mobility performance gains as compared to CHO for different hand blockage cases that are dependent on the hand position around the MPUE. For the worst-case hand blockage scenario, it is seen that mobility failures reduce by 10.5% and 19.3% for the 60 km/h and 120 km/h mobility scenarios, respectively. This gain comes at the expense of reserving the handover resources of an MPUE for a longer time given that the target cell configurations are not necessarily released after each handover. In this article, the longer resource reservation problem in FCHO is analysed and three different resource reservation optimization techniques are introduced. Results have shown that these optimization techniques not only reduce the resource reservation time but also significantly reduce the signaling overhead at the possible expense of a tolerable degradation in mobility performance.
Recent advancements in large language models (LLMs) have enabled a new research domain, LLM agents, for solving robotics and planning tasks by leveraging the world knowledge and general reasoning abilities of LLMs obtained during pretraining. However, while considerable effort has been made to teach the robot the "dos," the "don'ts" received relatively less attention. We argue that, for any practical usage, it is as crucial to teach the robot the "don'ts": conveying explicit instructions about prohibited actions, assessing the robot's comprehension of these restrictions, and, most importantly, ensuring compliance. Moreover, verifiable safe operation is essential for deployments that satisfy worldwide standards such as ISO 61508, which defines standards for safely deploying robots in industrial factory environments worldwide. Aiming at deploying the LLM agents in a collaborative environment, we propose a queryable safety constraint module based on linear temporal logic (LTL) that simultaneously enables natural language (NL) to temporal constraints encoding, safety violation reasoning and explaining, and unsafe action pruning. To demonstrate the effectiveness of our system, we conducted experiments in VirtualHome environment and on a real robot. The experimental results show that our system strictly adheres to the safety constraints and scales well with complex safety constraints, highlighting its potential for practical utility.
While large language models (LLMs) have demonstrated remarkable capabilities across a range of downstream tasks, a significant concern revolves around their propensity to exhibit hallucinations: LLMs occasionally generate content that diverges from the user input, contradicts previously generated context, or misaligns with established world knowledge. This phenomenon poses a substantial challenge to the reliability of LLMs in real-world scenarios. In this paper, we survey recent efforts on the detection, explanation, and mitigation of hallucination, with an emphasis on the unique challenges posed by LLMs. We present taxonomies of the LLM hallucination phenomena and evaluation benchmarks, analyze existing approaches aiming at mitigating LLM hallucination, and discuss potential directions for future research.
Deep neural networks (DNNs) are successful in many computer vision tasks. However, the most accurate DNNs require millions of parameters and operations, making them energy, computation and memory intensive. This impedes the deployment of large DNNs in low-power devices with limited compute resources. Recent research improves DNN models by reducing the memory requirement, energy consumption, and number of operations without significantly decreasing the accuracy. This paper surveys the progress of low-power deep learning and computer vision, specifically in regards to inference, and discusses the methods for compacting and accelerating DNN models. The techniques can be divided into four major categories: (1) parameter quantization and pruning, (2) compressed convolutional filters and matrix factorization, (3) network architecture search, and (4) knowledge distillation. We analyze the accuracy, advantages, disadvantages, and potential solutions to the problems with the techniques in each category. We also discuss new evaluation metrics as a guideline for future research.
小貼士
登錄享
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191